I modelli MedLM disponibili, MedLM-medium e MedLM-large, sono modelli di base per la risposta a domande mediche e il riassunto. Puoi accedere ai modelli utilizzando l'API Vertex AI MedLM. Questa pagina fornisce una panoramica dei modelli MedLM disponibili, delle API utilizzate per interagire con i modelli e dei modi per personalizzarne i comportamenti.
Prima di iniziare
- Consulta la panoramica dei modelli MedLM per informazioni, tra cui le responsabilità del cliente, le informazioni sulle normative e le best practice per l'IA responsabile.
Consulta la scheda del modello MedLM per i dettagli del modello, come l'uso previsto, la panoramica dei dati e le informazioni sulla sicurezza di MedLM. Fai clic sul seguente link per scaricare una versione PDF della scheda del modello MedLM:
Progettazione dei prompt
Per interagire con i modelli MedLM, invii istruzioni in linguaggio naturale, chiamate anche prompt, che indicano al modello cosa vuoi che generi. Tuttavia, a volte gli LLM possono comportarsi in modi imprevedibili. La progettazione di prompt è un processo iterativo di prove ed errori che richiede tempo ed esercitazione per acquisire competenza. Per informazioni sulle strategie generali di progettazione dei prompt, consulta Introduzione alla progettazione dei prompt. Per indicazioni sulla progettazione di prompt specifici per le attività per il testo, consulta Progettare prompt di testo.
Casi d'uso
- Riassunto: crea una versione più breve di un documento che incorpora informazioni pertinenti tratte dal testo originale. Ad esempio, potresti voler riassumere una nota medica che descrive una visita ambulatoriale ed estrarre informazioni pertinenti per punti dati specifici.
- Risposta alle domande: fornisci risposte alle domande nel testo. Ad esempio, potresti voler generare un piano nutrizionale completo e basato su principi di salute basato sulle condizioni di salute dei pazienti e sulle preferenze alimentari.
Modelli supportati
medlm-mediummedlm-large
Inizia
I seguenti esempi mostrano come iniziare a utilizzare l'API MedLM utilizzando le seguenti interfacce:
- L'API REST Vertex AI
- SDK Vertex AI per Python
- Vertex AI Studio
REST
Prima di utilizzare i dati della richiesta, effettua le seguenti sostituzioni:
PROJECT_ID: il tuo ID progetto.MEDLM_MODEL: il modello MedLM,medlm-mediumomedlm-large.
Metodo HTTP e URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Corpo JSON della richiesta:
{
"instances": [
{
"content": "Question: What causes you to get ringworm?"
}
],
"parameters": {
"temperature": 0,
"maxOutputTokens": 256,
"topK": 40,
"topP": 0.95
}
}
Per inviare la richiesta, scegli una delle seguenti opzioni:
arricciatura
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
cat > request.json << 'EOF'
{
"instances": [
{
"content": "Question: What causes you to get ringworm?"
}
],
"parameters": {
"temperature": 0,
"maxOutputTokens": 256,
"topK": 40,
"topP": 0.95
}
}
EOF
Quindi esegui questo comando per inviare la richiesta REST:
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
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
@'
{
"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
Quindi esegui questo comando per inviare la richiesta REST:
$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)
Esegui il seguente codice Python in 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)
Esegui il seguente codice nel blocco note Colaboratory. Inserisci il tuo ID progetto Google Cloud dove indicato. Per trovare l'ID progetto, consulta Individuare l'ID progetto.
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'
# MedLM models are only available in us-central1.
vertexai.init(project=PROJECT_ID, location='us-central1')
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
Usa Vertex AI Studio per progettare, testare e personalizzare i prompt inviati all'API MedLM. Prima di utilizzare Vertex AI Studio per MedLM, consulta Prova Vertex AI Studio per conoscere i prerequisiti.
Per testare un prompt MedLM utilizzando Vertex AI Studio nella console Google Cloud, segui questi passaggi:
- Nella sezione Vertex AI della console Google Cloud, vai alla pagina di Vertex AI Studio.
- Fai clic su Inizia.
- Fai clic su Crea prompt.
- Nel menu Modello, seleziona
MedLM-MediumoMedLM-Large. - Nel campo Prompt, inserisci il prompt.
- (Facoltativo) Puoi regolare i valori di Temperatura e Limite di token per sperimentare in che modo influiscono sulla risposta. Consigliamo di utilizzare i valori predefiniti. Se hai dubbi su quali valori utilizzare, utilizza i valori predefiniti.
- Fai clic su Invia per generare una risposta.
- (Facoltativo) Per salvare una richiesta, fai clic su Salva.
- (Facoltativo) Per visualizzare il codice Python o un comando
curlper il prompt, fai clic su Genera codice.
Prompt di risposta a domande
Le seguenti sezioni contengono esempi di richieste di risposta alle domande. Ogni prompt di esempio include i valori del modello e dei parametri consigliati.
Risposte alle domande nel formato lungo
I seguenti esempi mostrano in che modo l'API MedLM risponde a una domanda medica di lunga durata formulata come query.
REST
Prima di utilizzare i dati della richiesta, effettua le seguenti sostituzioni:
PROJECT_ID: il tuo ID progetto.MEDLM_MODEL: il modello MedLM,medlm-mediumomedlm-large.
Metodo HTTP e URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Corpo JSON della richiesta:
{
"instances": [
{
"content": "Question: What causes you to get ringworm?"
}
],
"parameters": {
"temperature": 0,
"maxOutputTokens": 256,
"topK": 40,
"topP": 0.95
}
}
Per inviare la richiesta, scegli una delle seguenti opzioni:
arricciatura
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
cat > request.json << 'EOF'
{
"instances": [
{
"content": "Question: What causes you to get ringworm?"
}
],
"parameters": {
"temperature": 0,
"maxOutputTokens": 256,
"topK": 40,
"topP": 0.95
}
}
EOF
Quindi esegui questo comando per inviare la richiesta REST:
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
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
@'
{
"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
Quindi esegui questo comando per inviare la richiesta REST:
$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
Risposte a domande a scelta multipla
I seguenti esempi mostrano in che modo l'API MedLM risponde a una domanda medica a scelta multipla. Il prompt è il seguente:
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
Prima di utilizzare i dati della richiesta, effettua le seguenti sostituzioni:
PROJECT_ID: il tuo ID progetto.MEDLM_MODEL: il modello MedLM,medlm-mediumomedlm-large.
Metodo HTTP e URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Corpo JSON della richiesta:
{
"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
}
}
Per inviare la richiesta, scegli una delle seguenti opzioni:
arricciatura
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
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
Quindi esegui questo comando per inviare la richiesta REST:
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
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
@'
{
"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
Quindi esegui questo comando per inviare la richiesta REST:
$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
Prompt di riassunto
Le seguenti sezioni contengono esempi di prompt di riepilogo. Ogni prompt di esempio include i valori del modello e dei parametri consigliati.
Scrivere un riepilogo al termine della visita
Gli esempi riportati di seguito mostrano come generare un riepilogo dopo la visita per un paziente in base a una nota per la visita ambulatoriale. Il prompt contiene quanto segue:
- Un preambolo contenente l'istruzione del modello.
- Una descrizione di ogni campo da estrarre per il riepilogo.
Il formato del riepilogo al termine della visita si basa su Sieferd et al. (2019) e sulle raccomandazioni dell'UK Academy of Medical Royal Colleges. Facoltativamente, puoi aggiungere alcuni esempi prima delle note e dei riepiloghi.
Il prompt è il seguente:
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
Prima di utilizzare i dati della richiesta, effettua le seguenti sostituzioni:
PROJECT_ID: il tuo ID progetto.MEDLM_MODEL: il modello MedLM,medlm-mediumomedlm-large.INPUT_NOTE: la nota di input da riassumere.
Metodo HTTP e URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Corpo JSON della richiesta:
{
"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
}
}
Per inviare la richiesta, scegli una delle seguenti opzioni:
arricciatura
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
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
Quindi esegui questo comando per inviare la richiesta REST:
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
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
@'
{
"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
Quindi esegui questo comando per inviare la richiesta REST:
$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
Scrivi una nota di anamnesi e di esame fisico (H&P) partendo da una trascrizione
I seguenti esempi mostrano come accelerare la documentazione clinica inviando all'API MedLM una richiesta di scrittura di una bozza di storia e nota di esame fisico (H&P) dalla trascrizione di una conversazione medica tra un medico e un paziente.
La nota H&P è una nota clinica completa che documenta la storia medica del paziente e l'esame fisico effettuato dal fornitore. MedLM può raccogliere molte delle informazioni cliniche necessarie per redigere una nota di questo tipo dalla conversazione tra il fornitore e il paziente durante la visita medica.
Supponiamo che tu abbia una trascrizione di una conversazione medica nel seguente formato. I partecipanti alla conversazione sono noti:
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
Prima di utilizzare i dati della richiesta, effettua le seguenti sostituzioni:
PROJECT_ID: il tuo ID progetto.MEDLM_MODEL: il modello MedLM,medlm-mediumomedlm-large.
Metodo HTTP e URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Corpo JSON della richiesta:
{
"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
}
}
Per inviare la richiesta, scegli una delle seguenti opzioni:
arricciatura
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
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
Quindi esegui questo comando per inviare la richiesta REST:
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
Salva il corpo della richiesta in un file denominato request.json.
Esegui questo comando nel terminale per creare o sovrascrivere questo file nella directory attuale:
@'
{
"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
Quindi esegui questo comando per inviare la richiesta REST:
$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)
Esegui il seguente codice Python in 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)
Esegui il seguente codice nel blocco note Colaboratory. Inserisci il tuo ID progetto Google Cloud dove indicato. Per trovare l'ID progetto, consulta Individuare l'ID progetto.
Inserisci il libretto medico dove indicato.
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'
# MedLM models are only available in us-central1.
vertexai.init(project=PROJECT_ID, location='us-central1')
# 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
Tieni presente quanto segue:
- La nota generata potrebbe contenere inesattezze e deve essere esaminata da un medico prima dell'approvazione.
- La nota generata potrebbe non rispettare rigorosamente il formato o il modello richiesto del reparto clinico o dello specialista. È inteso come punto di partenza per tracciare un grafico del paziente.
- La qualità della nota generata è limitata dall'accuratezza della trascrizione fornita.
Implementare valutazioni e mitigazioni incentrate sull’equità
MedLM potrebbe produrre risultati meno precisi per alcuni gruppi rispetto ad altri, a seconda della domanda e della sua formulazione. Prestazioni diverse dei risultati del modello nei vari gruppi demografici ha il potenziale di esacerbare le disuguaglianze sanitarie e perpetuare bias dannosi. Queste imprecisioni nei risultati non sono specifiche di MedLM e spesso derivano da più fattori, come disuguaglianze sociali e strutturali esistenti, errate convinzioni mediche, stereotipi negativi e mancanza di diversità nei dati di addestramento.
Valuta la possibilità di implementare valutazioni e mitigazioni incentrate sull'equità. Sono incluse le seguenti app:
- Valutazione delle prestazioni e del comportamento del modello per i casi d'uso previsti in varie popolazioni (ad esempio gruppo etnico, stato socioeconomico, area geografica, identità di genere, orientamento sessuale, età, preferenza della lingua, casta e così via).
- Ottenere feedback sulle prestazioni.
- Coinvolgimento di esperti interdisciplinari e partner esterni specializzati nella definizione e nell'ambito degli aspetti sociali e strutturali della salute.
- Monitoraggio costante per valutare e risolvere i problemi legati ai bias.
A seconda del tuo caso d'uso, valuta la possibilità di arricchire il prompt con istruzioni incentrate sull'equità, che possono migliorare la qualità dei risultati di MedLM nel rispetto dei bias e dell'equità.
Ad esempio, il testo seguente, quando inserito all'inizio di un prompt, migliora la qualità dei risultati delle domande di medicina basata sul gruppo etnico, come mostrato in 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.
La modifica dei prompt influisce sugli output del modello, pertanto consigliamo di valutare le valutazioni complete per assicurarti che non siano interessate altre aree di prestazioni.
Per ulteriori considerazioni sulle prestazioni del modello, consulta la scheda del modello MedLM.