Membuat prompt MedLM

Model MedLM yang tersedia, MedLM-medium dan MedLM-large, adalah model dasar untuk menjawab dan meringkas pertanyaan medis. Anda dapat mengakses model tersebut menggunakan Vertex AI MedLM API. Halaman ini memberi Anda ringkasan tentang model MedLM yang tersedia, API yang Anda gunakan untuk berinteraksi dengan model, dan cara menyesuaikan perilakunya.

Sebelum memulai

• Lihat ringkasan model MedLM untuk mengetahui informasi yang mencakup tanggung jawab pelanggan, informasi peraturan, dan praktik terbaik Responsible AI.

• Lihat kartu model MedLM untuk mengetahui detail model, seperti tujuan penggunaan MedLM, ringkasan data, dan informasi keamanan. Klik link berikut untuk mendownload versi PDF kartu model MedLM:

  Download kartu model MedLM

Prompt design

Untuk berinteraksi dengan model MedLM, Anda mengirim petunjuk natural language, yang juga disebut prompt, yang memberi tahu model apa yang ingin Anda hasilkan. Namun, LLM terkadang dapat berperilaku dengan cara yang tidak dapat diprediksi. Desain perintah adalah proses iteratif uji coba yang membutuhkan waktu dan praktik untuk menguasainya. Untuk mempelajari strategi desain perintah umum, lihat Pengantar desain perintah. Untuk panduan desain perintah khusus tugas untuk teks, lihat Mendesain perintah teks.

Kasus penggunaan

• Rangkum: Membuat versi dokumen yang lebih pendek yang menggabungkan informasi yang relevan dari teks asli. Misalnya, Anda mungkin ingin meringkas catatan medis yang menjelaskan kunjungan rawat jalan, dan mengekstrak informasi yang relevan untuk titik data tertentu.
• Penjawaban pertanyaan: Berikan jawaban atas pertanyaan dalam teks. Misalnya, Anda mungkin ingin membuat rencana nutrisi yang komprehensif dan didasarkan secara medis berdasarkan kondisi kesehatan pasien dan preferensi diet.

Model yang didukung

• medlm-medium
• medlm-large

Mulai

Contoh berikut menunjukkan cara memulai MedLM API menggunakan antarmuka berikut:

• REST API Vertex AI
• Vertex AI SDK untuk Python
• Vertex AI Studio

REST

Perhatian: Output yang dihasilkan mungkin tidak selalu sepenuhnya dapat diandalkan. Karena sifat LLM dan AI Generatif, output mungkin memiliki informasi yang salah atau bias dan harus ditinjau. Semua ringkasan atau jawaban harus dianggap sebagai draf dan bukan final.

Sebelum menggunakan salah satu data permintaan, lakukan penggantian berikut:

• PROJECT_ID: Project ID Anda.
• MEDLM_MODEL: Model MedLM, medlm-medium atau medlm-large.

Metode HTTP dan URL:

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict

Isi JSON permintaan:

{
  "instances": [
    {
      "content": "Question: What causes you to get ringworm?"
    }
  ],
  "parameters": {
    "temperature": 0,
    "maxOutputTokens": 256,
    "topK": 40,
    "topP": 0.95
  }
}

Untuk mengirim permintaan Anda, pilih salah satu opsi berikut:

curl

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login, atau menggunakan Cloud Shell, yang secara otomatis membuat Anda login ke CLI gcloud. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

cat > request.json << 'EOF'
{
  "instances": [
    {
      "content": "Question: What causes you to get ringworm?"
    }
  ],
  "parameters": {
    "temperature": 0,
    "maxOutputTokens": 256,
    "topK": 40,
    "topP": 0.95
  }
}
EOF

Kemudian, jalankan perintah berikut untuk mengirim permintaan REST Anda:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict"

PowerShell

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

@'
{
  "instances": [
    {
      "content": "Question: What causes you to get ringworm?"
    }
  ],
  "parameters": {
    "temperature": 0,
    "maxOutputTokens": 256,
    "topK": 40,
    "topP": 0.95
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

Kemudian jalankan perintah berikut untuk mengirim permintaan REST Anda:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict" | Select-Object -Expand Content

 

Python (Kolaborasi)

Jalankan kode Python berikut di Colaboratory.

!pip install google-cloud-aiplatform

# The following restarts the runtime.
import IPython

app = IPython.Application.instance()
# Note that this will result in a pop-up telling you that the session has
# crashed for an unknown reason. This can be safely ignored and you can continue
# with the following cells after getting this message.
app.kernel.do_shutdown(True)

Jalankan kode berikut di notebook Colaboratory Anda. Masukkan ID project Google Cloud Anda di tempat yang ditunjukkan. Untuk menemukan project ID Anda, baca artikel Menemukan project ID.

from google.colab import auth as google_auth
import vertexai
from vertexai.preview.language_models import TextGenerationModel

google_auth.authenticate_user()

# TODO: Replace with project ID from Cloud Console
# (https://support.google.com/googleapi/answer/7014113)
PROJECT_ID = 'my-project'

vertexai.init(project=PROJECT_ID)

parameters = {
    "candidate_count": 1,
    "max_output_tokens": 256,
    "temperature": 0.0,
    "top_k": 40,
    "top_p": 0.80,
}

model_instance = TextGenerationModel.from_pretrained("medlm-medium")
response = model_instance.predict(
    "Question: What causes you to get ringworm?",
    **parameters
)

print(f"Response from Model: {response.text}")

Generative AI Studio

Gunakan Vertex AI Studio untuk mendesain, menguji, dan menyesuaikan prompt yang dikirim ke MedLM API. Sebelum menggunakan Vertex AI Studio untuk MedLM, lihat Mencoba Vertex AI Studio untuk mengetahui prasyarat.

Untuk menguji prompt MedLM menggunakan Vertex AI Studio di Konsol Google Cloud, lakukan hal berikut:

1. Di bagian Vertex AI pada Konsol Google Cloud, buka halaman Vertex AI Studio.

   Buka Vertex AI Studio

2. Klik Get started.
3. Klik Create prompt.
4. Di menu Model, pilih MedLM-Medium atau MedLM-Large.
5. Di kolom Prompt, masukkan perintah Anda.
6. (Opsional) Anda dapat menyesuaikan nilai Temperature dan Token limit untuk bereksperimen dengan pengaruhnya terhadap respons. Sebaiknya gunakan nilai default. Jika Anda tidak yakin nilai mana yang harus digunakan, gunakan nilai default.
7. Klik Kirim untuk membuat respons.
8. (Opsional) Untuk menyimpan perintah, klik Simpan.
9. (Opsional) Guna melihat kode Python atau perintah curl untuk perintah Anda, klik Get code.

Dialog penjawaban pertanyaan

Bagian berikut berisi contoh perintah untuk menjawab pertanyaan. Setiap contoh perintah menyertakan model dan parameter value yang direkomendasikan.

Menjawab pertanyaan berdurasi panjang

Contoh berikut menunjukkan cara MedLM API menjawab pertanyaan medis panjang yang dirumuskan sebagai kueri.

REST

Perhatian: Output yang dihasilkan mungkin tidak selalu sepenuhnya dapat diandalkan. Karena sifat LLM dan AI Generatif, output mungkin memiliki informasi yang salah atau bias dan harus ditinjau. Semua ringkasan atau jawaban harus dianggap sebagai draf dan bukan final.

Sebelum menggunakan salah satu data permintaan, lakukan penggantian berikut:

• PROJECT_ID: Project ID Anda.
• MEDLM_MODEL: Model MedLM, medlm-medium atau medlm-large.

Metode HTTP dan URL:

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict

Isi JSON permintaan:

{
  "instances": [
    {
      "content": "Question: What causes you to get ringworm?"
    }
  ],
  "parameters": {
    "temperature": 0,
    "maxOutputTokens": 256,
    "topK": 40,
    "topP": 0.95
  }
}

Untuk mengirim permintaan Anda, pilih salah satu opsi berikut:

curl

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login, atau menggunakan Cloud Shell, yang secara otomatis membuat Anda login ke CLI gcloud. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

cat > request.json << 'EOF'
{
  "instances": [
    {
      "content": "Question: What causes you to get ringworm?"
    }
  ],
  "parameters": {
    "temperature": 0,
    "maxOutputTokens": 256,
    "topK": 40,
    "topP": 0.95
  }
}
EOF

Kemudian, jalankan perintah berikut untuk mengirim permintaan REST Anda:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict"

PowerShell

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

@'
{
  "instances": [
    {
      "content": "Question: What causes you to get ringworm?"
    }
  ],
  "parameters": {
    "temperature": 0,
    "maxOutputTokens": 256,
    "topK": 40,
    "topP": 0.95
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

Kemudian jalankan perintah berikut untuk mengirim permintaan REST Anda:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict" | Select-Object -Expand Content

 

Perhatian: Output yang dihasilkan mungkin tidak selalu sepenuhnya dapat diandalkan. Karena sifat LLM dan AI Generatif, output mungkin memiliki informasi yang salah atau bias dan harus ditinjau. Semua ringkasan atau jawaban harus dianggap sebagai draf dan bukan final.

Menjawab pertanyaan pilihan ganda

Contoh berikut menunjukkan cara MedLM API menjawab pertanyaan medis pilihan ganda. Promptnya adalah sebagai berikut:

Instructions: This text contains multiple-choice questions about medical knowledge. Solve each question step-by-step, starting by summarizing the available information. Select a single option from the four choices provided as the final answer.

Question 1: Which medication causes the maximum increase in prolactin level?
(A) Risperidone
(B) Clozapine
(C) Olanzapine
(D) Aripiprazole

Explanation: To solve this question, let's refer to authoritative sources. Clozapine generally does not elevate prolactin levels. Atypicals like olanzapine and aripiprazole cause little to no elevation. Risperidone, on the other hand, is known to result in a sustained elevated prolactin level. Therefore, risperidone is likely to cause the maximum increase in prolactin level.

Answer: (A)

Question 2: What is the recommended age for routine screening mammography?
(A) 20 years
(B) 30 years
(C) 40 years
(D) 50 years

Explanation: The age of routine screening may vary depending on the country. In the United States, according to the American Cancer Society, it is recommended to start routine screening mammography at 40 years of age. In Europe, it is typically closer to 50 years. For a patient based in the US, the best answer is 40 years.

Answer: (C)

Question 3: A 65-year-old male experiences severe back pain and paralysis in his left lower limb. Imaging studies show compression of nerve elements at the intervertebral foramen between vertebrae L5 and S1. Which structure is most likely causing this compression?
(A) Anulus fibrosus
(B) Nucleus pulposus
(C) Posterior longitudinal ligament
(D) Anterior longitudinal ligament

Explanation: This man's symptoms and imaging findings are consistent with a herniated intervertebral disk. The soft, gelatinous "nucleus pulposus" is forced out through a weakened part of the disk, resulting in back pain and nerve root irritation. In this case, the impingement is resulting in paralysis, which should be considered a medical emergency. Overall, the structure that is causing the compression and symptoms is the nucleus pulposus.

Answer: (B)

Question 4: Which cells in the lungs are also known as APUD cells?
(A) Dendritic cells
(B) Type I pneumocytes
(C) Type II pneumocytes
(D) Neuroendocrine cells

Explanation: Neuroendocrine cells, also known as Kultschitsky-type cells, Feyrter cells, and APUD cells, are found in the basal layer of the surface epithelium and in the bronchial glands.

Answer: (D)

Question 5: Which microorganism indicates remote contamination of water?
(A) Streptococci
(B) Staphylococci
(C) Clostridium perfringens
(D) Vibrio

Explanation: The presence of Clostridium perfringens in water indicates remote contamination because it is a spore-forming bacterium that can survive in the environment for extended periods of time.

Answer: (C)

REST

Perhatian: Output yang dihasilkan mungkin tidak selalu sepenuhnya dapat diandalkan. Karena sifat LLM dan AI Generatif, output mungkin memiliki informasi yang salah atau bias dan harus ditinjau. Semua ringkasan atau jawaban harus dianggap sebagai draf dan bukan final.

Sebelum menggunakan salah satu data permintaan, lakukan penggantian berikut:

• PROJECT_ID: Project ID Anda.
• MEDLM_MODEL: Model MedLM, medlm-medium atau medlm-large.

Metode HTTP dan URL:

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict

Isi JSON permintaan:

{
  "instances": [
    {
      "content": "Instructions: The following are multiple choice questions about medical knowledge. Solve them in a step-by-step fashion, starting by summarizing the available information. Output a single option from the four options as the final answer. \n \nQuestion: Maximum increase in prolactin level is caused by: \n(A) Risperidone (B) Clozapine (C) Olanzapine (D) Aripiprazole \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. Clozapine generally does not raise prolactin levels. Atypicals such as olanzapine and aripiprazole cause small if no elevation. Risperidone is known to result in a sustained elevated prolactin level. Therefore risperidone is likely to cause the maximum increase in prolactin level. \nAnswer: (A) \n \nQuestion: What is the age of routine screening mammography? \n(A) 20 years (B) 30 years (C) 40 years (D) 50 years \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. The age of routine screening depends on the country you are interested in and varies widely. For the US, it is 40 years of age according to the American Cancer Society. In Europe, it is typically closer to 50 years. For a patient based in the US, the best answer is 40 years. \nAnswer: (C) \n \nQuestion: A 65-year-old male complains of severe back pain and inability to move his left lower limb. Radiographic studies demonstrate the compression of nerve elements at the intervertebral foramen between vertebrae L5 and S1. Which structure is most likely responsible for this space-occupying lesion? \n(A) Anulus fibrosus (B) Nucleus pulposus (C) Posterior longitudinal ligament (D) Anterior longitudinal ligament \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. This man describes a herniated invertebral disk through a tear in the surrounding annulus fibrosus. The soft, gelatinous \"nucleus pulposus\" is forced out through a weakened part of the disk, resulting in back pain and nerve root irritation. In this case, the impingement is resulting in paralysis, and should be considered a medical emergency. Overall, the structure that is causing the compression and symptoms is the nucleus pulposus. \nAnswer: (B) \n \nQuestion: Neuroendocrine cells in the lungs are: \n(A) Dendritic cells (B) Type I pneumocytes (C) Type II pneumocytes (D) APUD cells \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. Neuroendocrine cells, which are also known as Kultschitsky-type cells, Feyrter cells and APUD cells, are found in the basal layer of the surface epithelium and in the bronchial glands. \nAnswer: (D) \n \nQuestion: Presence of it indicates remote contamination of water \n(A) Streptococci (B) Staphalococci (C) Clastridium pertringes (D) Nibrio \n"
    }
  ],
  "parameters": {
    "temperature": 0.2,
    "maxOutputTokens": 256
  }
}

Untuk mengirim permintaan Anda, pilih salah satu opsi berikut:

curl

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login, atau menggunakan Cloud Shell, yang secara otomatis membuat Anda login ke CLI gcloud. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

cat > request.json << 'EOF'
{
  "instances": [
    {
      "content": "Instructions: The following are multiple choice questions about medical knowledge. Solve them in a step-by-step fashion, starting by summarizing the available information. Output a single option from the four options as the final answer. \n \nQuestion: Maximum increase in prolactin level is caused by: \n(A) Risperidone (B) Clozapine (C) Olanzapine (D) Aripiprazole \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. Clozapine generally does not raise prolactin levels. Atypicals such as olanzapine and aripiprazole cause small if no elevation. Risperidone is known to result in a sustained elevated prolactin level. Therefore risperidone is likely to cause the maximum increase in prolactin level. \nAnswer: (A) \n \nQuestion: What is the age of routine screening mammography? \n(A) 20 years (B) 30 years (C) 40 years (D) 50 years \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. The age of routine screening depends on the country you are interested in and varies widely. For the US, it is 40 years of age according to the American Cancer Society. In Europe, it is typically closer to 50 years. For a patient based in the US, the best answer is 40 years. \nAnswer: (C) \n \nQuestion: A 65-year-old male complains of severe back pain and inability to move his left lower limb. Radiographic studies demonstrate the compression of nerve elements at the intervertebral foramen between vertebrae L5 and S1. Which structure is most likely responsible for this space-occupying lesion? \n(A) Anulus fibrosus (B) Nucleus pulposus (C) Posterior longitudinal ligament (D) Anterior longitudinal ligament \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. This man describes a herniated invertebral disk through a tear in the surrounding annulus fibrosus. The soft, gelatinous \"nucleus pulposus\" is forced out through a weakened part of the disk, resulting in back pain and nerve root irritation. In this case, the impingement is resulting in paralysis, and should be considered a medical emergency. Overall, the structure that is causing the compression and symptoms is the nucleus pulposus. \nAnswer: (B) \n \nQuestion: Neuroendocrine cells in the lungs are: \n(A) Dendritic cells (B) Type I pneumocytes (C) Type II pneumocytes (D) APUD cells \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. Neuroendocrine cells, which are also known as Kultschitsky-type cells, Feyrter cells and APUD cells, are found in the basal layer of the surface epithelium and in the bronchial glands. \nAnswer: (D) \n \nQuestion: Presence of it indicates remote contamination of water \n(A) Streptococci (B) Staphalococci (C) Clastridium pertringes (D) Nibrio \n"
    }
  ],
  "parameters": {
    "temperature": 0.2,
    "maxOutputTokens": 256
  }
}
EOF

Kemudian, jalankan perintah berikut untuk mengirim permintaan REST Anda:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict"

PowerShell

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

@'
{
  "instances": [
    {
      "content": "Instructions: The following are multiple choice questions about medical knowledge. Solve them in a step-by-step fashion, starting by summarizing the available information. Output a single option from the four options as the final answer. \n \nQuestion: Maximum increase in prolactin level is caused by: \n(A) Risperidone (B) Clozapine (C) Olanzapine (D) Aripiprazole \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. Clozapine generally does not raise prolactin levels. Atypicals such as olanzapine and aripiprazole cause small if no elevation. Risperidone is known to result in a sustained elevated prolactin level. Therefore risperidone is likely to cause the maximum increase in prolactin level. \nAnswer: (A) \n \nQuestion: What is the age of routine screening mammography? \n(A) 20 years (B) 30 years (C) 40 years (D) 50 years \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. The age of routine screening depends on the country you are interested in and varies widely. For the US, it is 40 years of age according to the American Cancer Society. In Europe, it is typically closer to 50 years. For a patient based in the US, the best answer is 40 years. \nAnswer: (C) \n \nQuestion: A 65-year-old male complains of severe back pain and inability to move his left lower limb. Radiographic studies demonstrate the compression of nerve elements at the intervertebral foramen between vertebrae L5 and S1. Which structure is most likely responsible for this space-occupying lesion? \n(A) Anulus fibrosus (B) Nucleus pulposus (C) Posterior longitudinal ligament (D) Anterior longitudinal ligament \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. This man describes a herniated invertebral disk through a tear in the surrounding annulus fibrosus. The soft, gelatinous \"nucleus pulposus\" is forced out through a weakened part of the disk, resulting in back pain and nerve root irritation. In this case, the impingement is resulting in paralysis, and should be considered a medical emergency. Overall, the structure that is causing the compression and symptoms is the nucleus pulposus. \nAnswer: (B) \n \nQuestion: Neuroendocrine cells in the lungs are: \n(A) Dendritic cells (B) Type I pneumocytes (C) Type II pneumocytes (D) APUD cells \nExplanation: Let's solve this step-by-step, referring to authoritative sources as needed. Neuroendocrine cells, which are also known as Kultschitsky-type cells, Feyrter cells and APUD cells, are found in the basal layer of the surface epithelium and in the bronchial glands. \nAnswer: (D) \n \nQuestion: Presence of it indicates remote contamination of water \n(A) Streptococci (B) Staphalococci (C) Clastridium pertringes (D) Nibrio \n"
    }
  ],
  "parameters": {
    "temperature": 0.2,
    "maxOutputTokens": 256
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

Kemudian jalankan perintah berikut untuk mengirim permintaan REST Anda:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict" | Select-Object -Expand Content

 

Perhatian: Output yang dihasilkan mungkin tidak selalu sepenuhnya dapat diandalkan. Karena sifat LLM dan AI Generatif, output mungkin memiliki informasi yang salah atau bias dan harus ditinjau. Semua ringkasan atau jawaban harus dianggap sebagai draf dan bukan final.

Perintah pembuatan ringkasan

Bagian berikut berisi contoh perintah perangkuman. Setiap contoh perintah menyertakan model dan parameter value yang direkomendasikan.

Tulis ringkasan setelah kunjungan

Contoh berikut menunjukkan cara membuat ringkasan setelah kunjungan untuk pasien berdasarkan catatan kunjungan pasien rawat jalan. Prompt berisi hal berikut:

• Pembukaan yang berisi instruksi model.
• Deskripsi setiap kolom yang akan diekstrak untuk ringkasan.

Format ringkasan setelah kunjungan didasarkan pada Sieferd et al. (2019) dan rekomendasi dari UK Academy of Medical Royal Colleges. Secara opsional, Anda dapat menambahkan contoh beberapa foto sebelum catatan dan ringkasan.

Promptnya adalah sebagai berikut:

Please read through the provided medical note describing an outpatient visit and extract the relevant information for each of the following 12 fields:

- Patient name/age/gender: This should summarize the patient's name, age and gender. It should use the format: "[Patient name], [age] year old [gender]". If the name is not mentioned in the note, please answer "Not available".
- Today I was seen by: This field should provide the name of the provider. If the provider seen for the note being summarized is not mentioned, please answer "Not available".
- I came in today for: This field should indicate the chief complaint or complaints that caused the visit.
- New health issues identified today are: This field should indicate any new diagnoses or other issues identified as a result of the visit being summarized. If the issue is a pre-existing condition identified in the past, please answer "No new diagnosis".
- Other health issues I have are: This field should indicate any pre-existing health issues identified in notes.
- Today we accomplished: This field should summarize the main topics of discussion and results of any procedures performed during the current visit. The summary could be a short list of procedures, or could be a text description of the patient's experience. Please be as brief as possible when providing details, such as test results or medication names. Describing the experience from the patient's point of view, using phrases like "my visit", "my condition".
- My important numbers: This field should provide the results of any measurements relevant to the  visit, including vitals. Provide the results of any numeric measurements relevant to the visit, including vitals, laboratory studies, or pain scores. Please include the numbers that should be monitored. Do not fabricate numbers that are not presented in the note.

- Changes to my medications are: This field should specify any medications that were added, for which the doses were updated, or which are no longer needed after the visit. Please specify both newly added and stopped medications when possible. If no changes are apparent from the note, please answer "no changes".
- Other medications I have are: If the note indicates any existing medications for the patient that the patient should continue taking without changes, list them here. If no medications are indicated in the note, please  "Not specified".
- My next steps are: This field should document the patient's next steps, including any actions they should take, test results they should expect, and follow-up visits they should schedule, along with the appropriate time frames for each.
- I should seek immediate medical attention if: If the note specifies any conditions for which the patient should immediately seek care, specify it here. Be sure to only include conditions that are mentioned in the note. If no conditions are mentioned, write "Not specified".
- Other comments from my provider: This is an optional extra field that captures any additional relevant information the provider indicated in the notes that it would be useful for the patient to know. Do not include information that is already listed in the previous field.
For each field, write at a sixth-grade reading level and avoid using abbreviations or jargon.

Output the summary in the following format:
- Patient name/age/gender:
- Today I was seen by:
- I came in today for:
- New health issues identified today are:
- Other health issues I have are:
- Today we accomplished:
- My important numbers:
- Changes to my medications are:
- Other medications I have are:
- My next steps are:
- I should seek immediate medical attention if:
- Other comments from my provider:

Note:

INPUT_NOTE

After Visit Summary:

REST

Perhatian: Output yang dihasilkan mungkin tidak selalu sepenuhnya dapat diandalkan. Karena sifat LLM dan AI Generatif, output mungkin memiliki informasi yang salah atau bias dan harus ditinjau. Semua ringkasan atau jawaban harus dianggap sebagai draf dan bukan final.

Sebelum menggunakan salah satu data permintaan, lakukan penggantian berikut:

• PROJECT_ID: Project ID Anda.
• MEDLM_MODEL: Model MedLM, medlm-medium atau medlm-large.
• INPUT_NOTE: Catatan input yang akan diringkas.

Metode HTTP dan URL:

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict

Isi JSON permintaan:

{
  "instances": [
    {
      "content": "Please read through the provided medical note describing an outpatient visit and extract the relevant information for each of the following 12 fields:\n\n- Patient name/age/gender: This should summarize the patient\u2019s name, age and gender. It should use the format: '[Patient name], [age] year old [gender]'. If the name is not mentioned in the note, please answer \"Not available\".\n- Today I was seen by: This field should provide the name of the provider. If the provider seen for the note being summarized is not mentioned, please answer 'Not available'.\n- I came in today for: This field should indicate the chief complaint or complaints that caused the visit.\n- New health issues identified today are: This field should indicate any new diagnoses or other issues identified as a result of the visit being summarized. If the issue is a pre-existing condition identified in the past, please answer 'No new diagnosis'.\n- Other health issues I have are: This field should indicate any pre-existing health issues identified in notes.\n- Today we accomplished: This field should summarize the main topics of discussion and results of any procedures performed during the current visit. The summary could be a short list of procedures, or could be a text description of the patient\u2019s experience. Please be as brief as possible when providing details, such as test results or medication names. Describing the experience from the patient\u2019s point of view, using phrases like 'my visit', 'my condition'.\n- My important numbers: This field should provide the results of any measurements relevant to the  visit, including vitals. Provide the results of any numeric measurements relevant to the visit, including vitals, laboratory studies, or pain scores. Please include the numbers that should be monitored. Do not fabricate numbers that are not presented in the note.\n\n\n\n\n\n\n\n\n- Changes to my medications are: This field should specify any medications that were added, for which the doses were updated, or which are no longer needed after the visit. Please specify both newly added and stopped medications when possible. If no changes are apparent from the note, please answer 'no changes'.\n- Other medications I have are: If the note indicates any existing medications for the patient that the patient should continue taking without changes, list them here. If no medications are indicated in the note, please  'Not specified'.\n- My next steps are: This field should document the patient\u2019s next steps, including any actions they should take, test results they should expect, and follow-up visits they should schedule, along with the appropriate time frames for each.\n- I should seek immediate medical attention if: If the note specifies any conditions for which the patient should immediately seek care, specify it here. Be sure to only include conditions that are mentioned in the note. If no conditions are mentioned, write 'Not specified'.\n- Other comments from my provider: This is an optional extra field that captures any additional relevant information the provider indicated in the notes that it would be useful for the patient to know. Do not include information that is already listed in the previous field.\nFor each field, write at a sixth-grade reading level and avoid using abbreviations or jargon.\n\nOutput the summary in the following format:\n- Patient name/age/gender:\n- Today I was seen by:\n- I came in today for:\n- New health issues identified today are:\n- Other health issues I have are:\n- Today we accomplished:\n- My important numbers:\n- Changes to my medications are:\n- Other medications I have are:\n- My next steps are:\n- I should seek immediate medical attention if:\n- Other comments from my provider:\n\n Note:\n\n INPUT_NOTE \n\nAfter Visit Summary:"
    }
  ],
  "parameters": {
    "candidate_count": 1,
    "temperature": 0,
    "maxOutputTokens": 1024,
    "topK": 40,
    "topP": 0.80
  }
}

Untuk mengirim permintaan Anda, pilih salah satu opsi berikut:

curl

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login, atau menggunakan Cloud Shell, yang secara otomatis membuat Anda login ke CLI gcloud. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

cat > request.json << 'EOF'
{
  "instances": [
    {
      "content": "Please read through the provided medical note describing an outpatient visit and extract the relevant information for each of the following 12 fields:\n\n- Patient name/age/gender: This should summarize the patient\u2019s name, age and gender. It should use the format: '[Patient name], [age] year old [gender]'. If the name is not mentioned in the note, please answer \"Not available\".\n- Today I was seen by: This field should provide the name of the provider. If the provider seen for the note being summarized is not mentioned, please answer 'Not available'.\n- I came in today for: This field should indicate the chief complaint or complaints that caused the visit.\n- New health issues identified today are: This field should indicate any new diagnoses or other issues identified as a result of the visit being summarized. If the issue is a pre-existing condition identified in the past, please answer 'No new diagnosis'.\n- Other health issues I have are: This field should indicate any pre-existing health issues identified in notes.\n- Today we accomplished: This field should summarize the main topics of discussion and results of any procedures performed during the current visit. The summary could be a short list of procedures, or could be a text description of the patient\u2019s experience. Please be as brief as possible when providing details, such as test results or medication names. Describing the experience from the patient\u2019s point of view, using phrases like 'my visit', 'my condition'.\n- My important numbers: This field should provide the results of any measurements relevant to the  visit, including vitals. Provide the results of any numeric measurements relevant to the visit, including vitals, laboratory studies, or pain scores. Please include the numbers that should be monitored. Do not fabricate numbers that are not presented in the note.\n\n\n\n\n\n\n\n\n- Changes to my medications are: This field should specify any medications that were added, for which the doses were updated, or which are no longer needed after the visit. Please specify both newly added and stopped medications when possible. If no changes are apparent from the note, please answer 'no changes'.\n- Other medications I have are: If the note indicates any existing medications for the patient that the patient should continue taking without changes, list them here. If no medications are indicated in the note, please  'Not specified'.\n- My next steps are: This field should document the patient\u2019s next steps, including any actions they should take, test results they should expect, and follow-up visits they should schedule, along with the appropriate time frames for each.\n- I should seek immediate medical attention if: If the note specifies any conditions for which the patient should immediately seek care, specify it here. Be sure to only include conditions that are mentioned in the note. If no conditions are mentioned, write 'Not specified'.\n- Other comments from my provider: This is an optional extra field that captures any additional relevant information the provider indicated in the notes that it would be useful for the patient to know. Do not include information that is already listed in the previous field.\nFor each field, write at a sixth-grade reading level and avoid using abbreviations or jargon.\n\nOutput the summary in the following format:\n- Patient name/age/gender:\n- Today I was seen by:\n- I came in today for:\n- New health issues identified today are:\n- Other health issues I have are:\n- Today we accomplished:\n- My important numbers:\n- Changes to my medications are:\n- Other medications I have are:\n- My next steps are:\n- I should seek immediate medical attention if:\n- Other comments from my provider:\n\n Note:\n\n INPUT_NOTE \n\nAfter Visit Summary:"
    }
  ],
  "parameters": {
    "candidate_count": 1,
    "temperature": 0,
    "maxOutputTokens": 1024,
    "topK": 40,
    "topP": 0.80
  }
}
EOF

Kemudian, jalankan perintah berikut untuk mengirim permintaan REST Anda:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict"

PowerShell

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

@'
{
  "instances": [
    {
      "content": "Please read through the provided medical note describing an outpatient visit and extract the relevant information for each of the following 12 fields:\n\n- Patient name/age/gender: This should summarize the patient\u2019s name, age and gender. It should use the format: '[Patient name], [age] year old [gender]'. If the name is not mentioned in the note, please answer \"Not available\".\n- Today I was seen by: This field should provide the name of the provider. If the provider seen for the note being summarized is not mentioned, please answer 'Not available'.\n- I came in today for: This field should indicate the chief complaint or complaints that caused the visit.\n- New health issues identified today are: This field should indicate any new diagnoses or other issues identified as a result of the visit being summarized. If the issue is a pre-existing condition identified in the past, please answer 'No new diagnosis'.\n- Other health issues I have are: This field should indicate any pre-existing health issues identified in notes.\n- Today we accomplished: This field should summarize the main topics of discussion and results of any procedures performed during the current visit. The summary could be a short list of procedures, or could be a text description of the patient\u2019s experience. Please be as brief as possible when providing details, such as test results or medication names. Describing the experience from the patient\u2019s point of view, using phrases like 'my visit', 'my condition'.\n- My important numbers: This field should provide the results of any measurements relevant to the  visit, including vitals. Provide the results of any numeric measurements relevant to the visit, including vitals, laboratory studies, or pain scores. Please include the numbers that should be monitored. Do not fabricate numbers that are not presented in the note.\n\n\n\n\n\n\n\n\n- Changes to my medications are: This field should specify any medications that were added, for which the doses were updated, or which are no longer needed after the visit. Please specify both newly added and stopped medications when possible. If no changes are apparent from the note, please answer 'no changes'.\n- Other medications I have are: If the note indicates any existing medications for the patient that the patient should continue taking without changes, list them here. If no medications are indicated in the note, please  'Not specified'.\n- My next steps are: This field should document the patient\u2019s next steps, including any actions they should take, test results they should expect, and follow-up visits they should schedule, along with the appropriate time frames for each.\n- I should seek immediate medical attention if: If the note specifies any conditions for which the patient should immediately seek care, specify it here. Be sure to only include conditions that are mentioned in the note. If no conditions are mentioned, write 'Not specified'.\n- Other comments from my provider: This is an optional extra field that captures any additional relevant information the provider indicated in the notes that it would be useful for the patient to know. Do not include information that is already listed in the previous field.\nFor each field, write at a sixth-grade reading level and avoid using abbreviations or jargon.\n\nOutput the summary in the following format:\n- Patient name/age/gender:\n- Today I was seen by:\n- I came in today for:\n- New health issues identified today are:\n- Other health issues I have are:\n- Today we accomplished:\n- My important numbers:\n- Changes to my medications are:\n- Other medications I have are:\n- My next steps are:\n- I should seek immediate medical attention if:\n- Other comments from my provider:\n\n Note:\n\n INPUT_NOTE \n\nAfter Visit Summary:"
    }
  ],
  "parameters": {
    "candidate_count": 1,
    "temperature": 0,
    "maxOutputTokens": 1024,
    "topK": 40,
    "topP": 0.80
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

Kemudian jalankan perintah berikut untuk mengirim permintaan REST Anda:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict" | Select-Object -Expand Content

 

Perhatian: Output yang dihasilkan mungkin tidak selalu sepenuhnya dapat diandalkan. Karena sifat LLM dan AI Generatif, output mungkin memiliki informasi yang salah atau bias dan harus ditinjau. Semua ringkasan atau jawaban harus dianggap sebagai draf dan bukan final.

Membuat catatan riwayat dan pemeriksaan fisik (H&P) dari transkrip

Contoh berikut menunjukkan cara mempercepat dokumentasi klinis dengan mengirimkan permintaan ke MedLM API untuk menulis draf histori dan catatan pemeriksaan fisik (H&P) dari transkrip percakapan medis antara penyedia dan pasien.

Catatan H&P adalah catatan klinis komprehensif yang mendokumentasikan riwayat medis pasien dan pemeriksaan fisik yang dilakukan oleh penyedia. MedLM dapat mengumpulkan banyak informasi klinis yang diperlukan untuk membuat draf catatan seperti itu dari percakapan antara penyedia dan pasien selama kunjungan medis.

Misalkan Anda memiliki transkrip percakapan medis dalam format berikut. Pembicara dalam percakapan dikenal sebagai:

PROVIDER: Welcome! How can we help you this morning?
PATIENT: I think I hurt my ankle while playing football last night. Now even walking hurts.
PROVIDER: I am sorry to hear that. Can you tell me how it happened?
PATIENT: I was playing soccer last night and I think I trip and twisted my ankle.
PROVIDER: Did it start hurting right away? Did you try anything to alleviate the pain?
PATIENT: It got worse last night. I took some ibuprofen, but it really didn't help.

REST

Perhatian: Output yang dihasilkan mungkin tidak selalu sepenuhnya dapat diandalkan. Karena sifat LLM dan AI Generatif, output mungkin memiliki informasi yang salah atau bias dan harus ditinjau. Semua ringkasan atau jawaban harus dianggap sebagai draf dan bukan final.

Sebelum menggunakan salah satu data permintaan, lakukan penggantian berikut:

• PROJECT_ID: Project ID Anda.
• MEDLM_MODEL: Model MedLM, medlm-medium atau medlm-large.

Metode HTTP dan URL:

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict

Isi JSON permintaan:

{
  "instances": [
    {
      "content": "You are charting a patient record. Read through the provided transcript of a conversation between a healthcare provider and a patient and write a history and physical examination note.\n\nTranscript: \n PROVIDER: Welcome! How can we help you this morning?\nPATIENT: I think I hurt my ankle while playing football last night. Now even walking hurts.\nPROVIDER: I am sorry to hear that. Can you tell me how it happened?\nPATIENT: I was playing soccer last night and I think I trip and twisted my ankle.\nPROVIDER: Did it start hurting right away? Did you try anything to alleviate the pain?\nPATIENT: It got worse last night. I took some ibuprofen, but it really didn't help.\n\nHistory and Physical Note:"
    }
  ],
  "parameters": {
    "candidate_count": 1,
    "temperature": 0,
    "maxOutputTokens": 1024,
    "topK": 40,
    "topP": 0.80
  }
}

Untuk mengirim permintaan Anda, pilih salah satu opsi berikut:

curl

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login, atau menggunakan Cloud Shell, yang secara otomatis membuat Anda login ke CLI gcloud. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

cat > request.json << 'EOF'
{
  "instances": [
    {
      "content": "You are charting a patient record. Read through the provided transcript of a conversation between a healthcare provider and a patient and write a history and physical examination note.\n\nTranscript: \n PROVIDER: Welcome! How can we help you this morning?\nPATIENT: I think I hurt my ankle while playing football last night. Now even walking hurts.\nPROVIDER: I am sorry to hear that. Can you tell me how it happened?\nPATIENT: I was playing soccer last night and I think I trip and twisted my ankle.\nPROVIDER: Did it start hurting right away? Did you try anything to alleviate the pain?\nPATIENT: It got worse last night. I took some ibuprofen, but it really didn't help.\n\nHistory and Physical Note:"
    }
  ],
  "parameters": {
    "candidate_count": 1,
    "temperature": 0,
    "maxOutputTokens": 1024,
    "topK": 40,
    "topP": 0.80
  }
}

EOF

Kemudian, jalankan perintah berikut untuk mengirim permintaan REST Anda:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict"

PowerShell

Catatan: Perintah berikut mengasumsikan bahwa Anda telah login ke CLI gcloud dengan akun pengguna Anda dengan menjalankan gcloud init atau gcloud auth login. Anda dapat memeriksa akun yang aktif saat ini dengan menjalankan gcloud auth list.

Simpan isi permintaan dalam file bernama request.json. Jalankan perintah berikut di terminal untuk membuat atau menimpa file ini di direktori saat ini:

@'
{
  "instances": [
    {
      "content": "You are charting a patient record. Read through the provided transcript of a conversation between a healthcare provider and a patient and write a history and physical examination note.\n\nTranscript: \n PROVIDER: Welcome! How can we help you this morning?\nPATIENT: I think I hurt my ankle while playing football last night. Now even walking hurts.\nPROVIDER: I am sorry to hear that. Can you tell me how it happened?\nPATIENT: I was playing soccer last night and I think I trip and twisted my ankle.\nPROVIDER: Did it start hurting right away? Did you try anything to alleviate the pain?\nPATIENT: It got worse last night. I took some ibuprofen, but it really didn't help.\n\nHistory and Physical Note:"
    }
  ],
  "parameters": {
    "candidate_count": 1,
    "temperature": 0,
    "maxOutputTokens": 1024,
    "topK": 40,
    "topP": 0.80
  }
}

'@  | Out-File -FilePath request.json -Encoding utf8

Kemudian jalankan perintah berikut untuk mengirim permintaan REST Anda:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict" | Select-Object -Expand Content

 

Python (Kolaborasi)

Jalankan kode Python berikut di Colaboratory.

!pip install google-cloud-aiplatform

# The following restarts the runtime.
import IPython

app = IPython.Application.instance()
# Note that this will result in a pop-up telling you that the session has
# crashed for an unknown reason. This can be safely ignored and you can continue
# with the following cells after getting this message.
app.kernel.do_shutdown(True)

Jalankan kode berikut di notebook Colaboratory Anda. Masukkan ID project Google Cloud Anda di tempat yang ditunjukkan. Untuk menemukan project ID Anda, baca artikel Menemukan project ID.

Masukkan transkrip medis jika ditunjukkan.

from google.colab import auth as google_auth
import vertexai
from vertexai.preview.language_models import TextGenerationModel

google_auth.authenticate_user()

# TODO: Replace with project ID from Cloud Console
# (https://support.google.com/googleapi/answer/7014113)
PROJECT_ID = 'my-project'

vertexai.init(project=PROJECT_ID)

# TODO: Replace with transcript.
transcript = """
# TODO: Replace with transcript.
"""

note_generation_prompt = f"""\
You are charting a patient record.
Read through the provided transcript of a conversation between a
healthcare provider and a patient and write a history and physical
examination note.

Transcript:
{transcript}

History and Physical note:
"""

parameters = {
    "candidate_count": 1,
    "max_output_tokens": 1024,
    "temperature": 0.0,
    "top_p": 0.80,
    "top_k": 40
}

model_instance = TextGenerationModel.from_pretrained("medlm-medium")
response = model_instance.predict(
    note_generation_prompt,
    **parameters
)
note = response.text

Perhatian: Output yang dihasilkan mungkin tidak selalu sepenuhnya dapat diandalkan. Karena sifat LLM dan AI Generatif, output mungkin memiliki informasi yang salah atau bias dan harus ditinjau. Semua ringkasan atau jawaban harus dianggap sebagai draf dan bukan final.

Perhatikan hal-hal berikut:

• Catatan yang dibuat mungkin tidak akurat dan harus ditinjau oleh dokter sebelum penandatanganan.
• Catatan yang dibuat mungkin tidak benar-benar mematuhi format atau template yang diperlukan dari departemen atau spesialisasi klinis. Ini dimaksudkan sebagai titik awal untuk memetakan pasien.
• Kualitas catatan yang dihasilkan dibatasi oleh akurasi transkripsi yang diberikan.

Menerapkan evaluasi dan mitigasi yang berfokus pada kesetaraan

MedLM mungkin memberikan hasil yang kurang akurat untuk beberapa grup dibandingkan dengan grup lainnya, bergantung pada pertanyaan dan frasanya. Perbedaan performa output model di seluruh kelompok demografi berpotensi memperburuk ketidaksetaraan kesehatan dan menyebabkan bias berbahaya. Ketidakakuratan output ini tidak hanya terjadi pada MedLM, dan sering kali disebabkan oleh banyak faktor, seperti ketidaksetaraan sosial dan struktural yang ada, kesalahpahaman medis, stereotip negatif, dan kurangnya keberagaman dalam data pelatihan.

Pertimbangkan untuk menerapkan evaluasi dan mitigasi yang berfokus pada kesetaraan. Contoh ini meliputi:

• Menilai performa dan perilaku model untuk kasus penggunaan yang dimaksudkan dalam berbagai populasi (seperti ras dan etnisitas, status sosial ekonomi (SES), geografis, identitas gender, orientasi seksual, usia, preferensi bahasa, kasta, dan sebagainya).
• Memperoleh masukan performa.
• Berinteraksi dengan pakar interdisipliner dan partner eksternal yang berspesialisasi dalam mendefinisikan dan menangani aspek sosial dan struktural kesehatan.
• Melakukan upaya pemantauan berkelanjutan untuk menilai dan mengatasi masalah bias.

Bergantung pada kasus penggunaan Anda, pertimbangkan untuk meningkatkan perintah dengan petunjuk yang berfokus pada kesetaraan, yang dapat meningkatkan kualitas output MedLM dengan mempertimbangkan bias dan kesetaraan.

Misalnya, teks berikut, ketika ditempatkan di awal perintah, akan meningkatkan kualitas hasil pada pertanyaan pengobatan berbasis ras seperti yang ditunjukkan dalam Omiye et al. (2023):

You are a medical knowledge assistant who provides useful, complete, and
scientifically-grounded answers to queries. Your answers are unbiased and
up-to-date, and you follow the latest clinical guidelines. You are aware that
guidelines may have changed recently in order to address bias and inaccurate
information about disadvantaged groups. You are committed to providing the best
possible care to all patients, regardless of their race, gender, or
geographical location. You are always learning and growing, and you are open to
feedback. Only account for race, gender, or geographical location in your
answer if you are 100% sure it is correct and unbiased, with no possibility of
making a mistake or providing a response based on outdated guidelines.

Perubahan perintah akan memengaruhi output model, sehingga evaluasi penuh direkomendasikan untuk memastikan area performa lainnya tidak terpengaruh.

Lihat kartu model MedLM untuk pertimbangan tambahan tentang performa model.