Die verfügbaren MedLM-Modelle MedLM-medium und MedLM-large sind Foundation Models für die Beantwortung und Zusammenfassung medizinischer Fragen. Sie können über die Vertex AI MedLM API auf die Modelle zugreifen. Auf dieser Seite erhalten Sie einen Überblick über die verfügbaren MeDLM-Modelle, die APIs, die Sie für die Interaktion mit den Modellen verwenden, und Möglichkeiten zur Anpassung ihres Verhaltens.
Hinweise
- Informationen zu Kundenverantwortlichkeiten, regulatorischen Informationen und Best Practices für Responsible AI finden Sie unter MedLM-Modelle – Übersicht.
Die MedLM-Modellkarte enthält Modelldetails, z. B. die vorgesehene Verwendung von MedLM, eine Datenübersicht und Sicherheitsinformationen. Klicken Sie auf den folgenden Link, um eine PDF-Version der MedLM-Modellkarte herunterzuladen:
Prompt-Design
Zur Interaktion mit den MedLM-Modellen senden Sie Anweisungen in natürlicher Sprache, die auch als Prompts bezeichnet werden. Damit wird dem Modell mitgeteilt, was es generieren soll. LLMs können sich jedoch manchmal unvorhersehbar verhalten. Das gezielte Design ist ein iterativer Testprozess, der viel Zeit und Erfahrung erfordert. Weitere Informationen zu allgemeinen Strategien für das Prompt-Design finden Sie unter Einführung in das Prompt-Design. Informationen zum aufgabenspezifischen Erstellen von Text-Prompts finden Sie unter Text-Prompts erstellen.
Anwendungsfälle
- Zusammenfassung: Erstellen Sie eine kürzere Version eines Dokuments, die die entsprechenden Informationen aus dem Originaltext enthält. Sie können beispielsweise eine medizinische Notiz zusammenfassen, einen ambulanten Besuch beschreiben oder relevante Informationen für bestimmte Datenpunkte extrahieren wollen.
- Fragen beantworten: Geben Sie Antworten auf Fragen im Text ein. Sie könnten beispielsweise einen umfassenden, medizinisch basierten Ernährungsplan auf der Grundlage von Gesundheitszustand und Ernährungseinstellungen eines Patienten erstellen wollen.
Unterstützte Modelle
medlm-mediummedlm-large
Mehr erfahren
Die folgenden Beispiele zeigen die ersten Schritte mit der MedLM API über die folgenden Schnittstellen:
- Die Vertex AI REST API
- Vertex AI SDK für Python
- Vertex AI Studio
REST
Ersetzen Sie diese Werte in den folgenden Anfragedaten:
PROJECT_ID: Ihre Projekt-ID.MEDLM_MODEL: Das MedLM-Modell, entwedermedlm-mediumodermedlm-large.
HTTP-Methode und URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
JSON-Text der Anfrage:
{
"instances": [
{
"content": "Question: What causes you to get ringworm?"
}
],
"parameters": {
"temperature": 0,
"maxOutputTokens": 256,
"topK": 40,
"topP": 0.95
}
}
Wenn Sie die Anfrage senden möchten, wählen Sie eine der folgenden Optionen aus:
curl
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
cat > request.json << 'EOF'
{
"instances": [
{
"content": "Question: What causes you to get ringworm?"
}
],
"parameters": {
"temperature": 0,
"maxOutputTokens": 256,
"topK": 40,
"topP": 0.95
}
}
EOF
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
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
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
@'
{
"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
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
$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 (Colaboratory)
Führen Sie den folgenden Python-Code in Colaboratory aus.
!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)
Führen Sie den folgenden Code in Ihrem Colaboratory-Notebook aus. Geben Sie die Google Cloud-Projekt-ID ein. Informationen zum Ermitteln der Projekt-ID finden Sie unter Projekt-ID suchen.
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
Verwenden Sie Vertex AI Studio, um Ihre an die MedLM API gesendeten Prompts zu entwerfen, zu testen und anzupassen. Bevor Sie Vertex AI Studio für MedLM verwenden, müssen Sie die Voraussetzungen hier nachsehen: Vertex AI Studio testen.
So testen Sie einen MedLM-Prompt mit Vertex AI Studio in der Google Cloud Console:
- Rufen Sie im Bereich „Vertex AI“ der Google Cloud Console die Seite Vertex AI Studio auf.
- Klicken Sie auf Jetzt starten.
- Klicken Sie auf Prompt erstellen.
- Wählen Sie im Menü Modell die Option
MedLM-MediumoderMedLM-Largeaus. - Geben Sie im Feld Prompt Ihren Prompt ein.
- (Optional) Sie können die Werte für Temperaturen und Tokenlimits anpassen, um zu experimentieren, wie sie sich auf die Antwort auswirken. Wir empfehlen die Verwendung der Standardwerte. Wenn Sie sich nicht sicher sind, welche Werte Sie verwenden sollen, verwenden Sie die Standardwerte.
- Klicken Sie auf Senden, um eine Antwort zu generieren.
- Optional: Wenn Sie einen Prompt speichern möchten, klicken Sie auf Speichern.
- Optional: Klicken Sie auf Code abrufen, um den Python-Code oder einen
curl-Befehl für Ihren Prompt aufzurufen.
Prompts zur Beantwortung von Fragen
Die folgenden Abschnitte enthalten Beispiele für Prompts zur Beantwortung von Fragen. Jeder Beispiel-Prompt enthält die empfohlenen Modell- und Parameterwerte.
Beantworten von langen Fragen
Die folgenden Beispiele zeigen, wie die MedLM API eine als Abfrage formulierte medizinische Frage beantwortet.
REST
Ersetzen Sie diese Werte in den folgenden Anfragedaten:
PROJECT_ID: Ihre Projekt-ID.MEDLM_MODEL: Das MedLM-Modell, entwedermedlm-mediumodermedlm-large.
HTTP-Methode und URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
JSON-Text der Anfrage:
{
"instances": [
{
"content": "Question: What causes you to get ringworm?"
}
],
"parameters": {
"temperature": 0,
"maxOutputTokens": 256,
"topK": 40,
"topP": 0.95
}
}
Wenn Sie die Anfrage senden möchten, wählen Sie eine der folgenden Optionen aus:
curl
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
cat > request.json << 'EOF'
{
"instances": [
{
"content": "Question: What causes you to get ringworm?"
}
],
"parameters": {
"temperature": 0,
"maxOutputTokens": 256,
"topK": 40,
"topP": 0.95
}
}
EOF
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
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
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
@'
{
"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
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
$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
Auswahl von Multiple-Choice-Fragen
Die folgenden Beispiele zeigen, wie die MedLM API eine medizinische Multiple-Choice-Frage beantwortet. Der Prompt lautet so:
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
Ersetzen Sie diese Werte in den folgenden Anfragedaten:
PROJECT_ID: Ihre Projekt-ID.MEDLM_MODEL: Das MedLM-Modell, entwedermedlm-mediumodermedlm-large.
HTTP-Methode und URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
JSON-Text der Anfrage:
{
"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
}
}
Wenn Sie die Anfrage senden möchten, wählen Sie eine der folgenden Optionen aus:
curl
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
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
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
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
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
@'
{
"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
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
$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
Aufforderungen zur Zusammenfassung
Die folgenden Abschnitte enthalten Beispiele für Aufforderungen zur Zusammenfassung. Jeder Beispiel-Prompt enthält die empfohlenen Modell- und Parameterwerte.
Zusammenfassung nach dem Besuch erstellen
Die folgenden Beispiele zeigen, wie Sie für einen Patienten eine Zusammenfassung nach einem Besuch basierend auf einer Notiz für einen ambulanten Besuch erstellen. Der Prompt enthält Folgendes:
- Eine Präambel mit der Modellanweisung.
- Eine Beschreibung jedes Felds, das für die Zusammenfassung extrahiert werden soll.
Das Format der Zusammenfassung nach dem Besuch basiert auf Sieferd et al. (2019) und Empfehlungen der UK Academy of Medical Royal Colleges. Optional können Sie den Notizen und Zusammenfassungen Beispiele hinzufügen.
Der Prompt lautet so:
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
Ersetzen Sie diese Werte in den folgenden Anfragedaten:
PROJECT_ID: Ihre Projekt-ID.MEDLM_MODEL: Das MedLM-Modell, entwedermedlm-mediumodermedlm-large.INPUT_NOTE: Die zusammenzufassende Eingabenotiz.
HTTP-Methode und URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
JSON-Text der Anfrage:
{
"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
}
}
Wenn Sie die Anfrage senden möchten, wählen Sie eine der folgenden Optionen aus:
curl
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
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
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
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
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
@'
{
"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
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
$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
Aus einem Transkript eine Notiz zur Krankengeschichte und zur physischen Prüfung erstellen
Die folgenden Beispiele zeigen, wie Sie die klinische Dokumentation beschleunigen können, indem Sie eine Anfrage an die MedLM API senden, um einen Entwurf für einen Verlauf und eine physische Untersuchung (H&P) aus dem Transkript eines medizinischen Gesprächs zwischen einem Dienstleister und einem Patienten zu schreiben. “
Die H&P-Notiz ist eine umfassende klinische Notiz, die den medizinischen Verlauf der Patienten und die vom Anbieter durchgeführte physische Untersuchung dokumentiert. MedLM kann viele der erforderlichen klinischen Informationen erfassen, um eine solche Notiz aus dem Gespräch zwischen dem Anbieter und dem Patienten während des medizinischen Besuchs zu erstellen.
Angenommen, Sie haben ein Transkript einer medizinischen Unterhaltung im folgenden Format. Die Sprecher sind bekannt:
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
Ersetzen Sie diese Werte in den folgenden Anfragedaten:
PROJECT_ID: Ihre Projekt-ID.MEDLM_MODEL: Das MedLM-Modell, entwedermedlm-mediumodermedlm-large.
HTTP-Methode und URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
JSON-Text der Anfrage:
{
"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
}
}
Wenn Sie die Anfrage senden möchten, wählen Sie eine der folgenden Optionen aus:
curl
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
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
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
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
Speichern Sie den Anfragetext in einer Datei mit dem Namen request.json.
Führen Sie folgenden Befehl im Terminal aus, um diese Datei im aktuellen Verzeichnis zu erstellen oder zu überschreiben:
@'
{
"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
Führen Sie dann folgenden Befehl aus, um Ihre REST-Anfrage zu senden:
$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 (Colaboratory)
Führen Sie den folgenden Python-Code in Colaboratory aus.
!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)
Führen Sie den folgenden Code in Ihrem Colaboratory-Notebook aus. Geben Sie die Google Cloud-Projekt-ID ein. Informationen zum Ermitteln der Projekt-ID finden Sie unter Projekt-ID suchen.
Geben Sie das medizinische Transkript ein, sofern angegeben.
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
Wichtige Hinweise:
- Die generierte Notiz kann Ungenauigkeiten enthalten und muss vor der Genehmigung von einem Arzt überprüft werden.
- Die generierte Notiz entspricht möglicherweise nicht genau dem Format oder der erforderlichen Vorlage der klinischen Abteilung oder Spezialabteilung. Es dient als Ausgangspunkt für die Erstellung eines Diagramms zum Patienten.
- Die Qualität der generierten Notiz wird durch die Accuracy des bereitgestellten Transkripts begrenzt.
Gleichstellungsorientierte Bewertungen und Risikominderungen implementieren
Je nach Frage und Formulierung kann MedLM für einige Gruppen im Vergleich zu anderen Gruppen weniger genaue Ergebnisse liefern. Wenn die Leistung der Ausgaben des Modells über demografische Gruppen hinweg variiert, besteht das Risiko, dass Ungleichbehandlungen im Gesundheitsbereich und schädliche Vorurteile verbreitet werden können. Diese Ungenauigkeiten bei der Ausgabe gelten nicht nur für MedLM und sind oft auf bestimmte Faktoren zurückzuführen, darunter vorhandene soziale und strukturelle Ungleichheiten, medizinische Missverständnisse, negative Stereotypen und fehlende Vielfalt in den Trainingsdaten.
Ziehen Sie die Implementierung von gleichstellungsorientierten Bewertungen und Praktiken zur Risikominderung in Betracht. Dazu gehören die folgenden:
- Modelleistung/-verhalten für die vorgesehenen Anwendungsfälle in verschiedenen Bevölkerungsgruppen (z. B. ethnische Herkunft, sozioökonomischer Status, Geografie, Geschlechtsidentität, sexuelle Orientierung, Alter, Sprachpräferenz, Kaste usw.) bewerten.
- Feedback zur Leistung einholen.
- Interdisziplinäre Experten und externe Partner einbinden, die sich auf die Definition und Bewältigung sozialer und struktureller Aspekte für Gesundheitsdienstleistungen spezialisiert haben.
- Kontinuierliches Monitoring, um Probleme von Verzerrungen zu bewerten und zu beheben.
Je nach Anwendungsfall sollten Sie Ihren Prompt um gleichstellungsorientierte Anweisungen erweitern, die die Qualität der MedLM-Ausgaben unter Berücksichtigung von Bias und Gleichheit verbessern können.
Der folgende Text verbessert beispielsweise die Qualität der Ergebnisse bei medizinischen Fragen, bei denen die ethnische Herkunft relevant ist, wenn er am Anfang eines Prompts steht, wie in Omiye et al. (2023) gezeigt:
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.
Änderungen an Prompts wirken sich auf die Modellausgabe aus. Daher wird eine vollständige Bewertung empfohlen, um sicherzustellen, dass andere Leistungsbereiche nicht betroffen sind.
Weitere Informationen zur Modellleistung finden Sie auf der MedLM-Modellkarte.