Los modelos de MedLM disponibles, MedLM-medium y MedLM-large, son modelos básicos para responder preguntas médicas y hacer resúmenes. Puedes acceder a los modelos mediante la API MedLM de Vertex AI. En esta página se ofrece una descripción general de los modelos de MedLM disponibles, las APIs que se usan para interactuar con los modelos y las formas de personalizar su comportamiento.
Antes de empezar
- Consulta la descripción general de los modelos MedLM para obtener información sobre las responsabilidades de los clientes, la información normativa y las prácticas recomendadas de IA responsable.
Consulta la tarjeta del modelo MedLM para obtener información sobre el modelo, como el uso previsto, un resumen de los datos y la información de seguridad. Haz clic en el siguiente enlace para descargar una versión PDF de la tarjeta del modelo MedLM:
Diseño de peticiones
Para interactuar con los modelos de MedLM, debes enviar instrucciones en lenguaje natural, también llamadas peticiones, que le indiquen al modelo lo que quieres que genere. Sin embargo, los LLMs a veces pueden comportarse de forma impredecible. El diseño de peticiones es un proceso iterativo de prueba y error que requiere tiempo y práctica para dominarlo. Para obtener información sobre las estrategias generales de diseño de peticiones, consulta el artículo Introducción al diseño de peticiones. Para obtener instrucciones sobre el diseño de peticiones específicas para tareas de texto, consulta el artículo Descripción general de las estrategias de peticiones.
Casos prácticos
- Resumen: crea una versión más corta de un documento que incluye información pertinente del texto original. Por ejemplo, puedes resumir una nota médica que describa una consulta ambulatoria y extraer información relevante para puntos de datos específicos.
- Respuesta a preguntas: proporciona respuestas a preguntas en texto. Por ejemplo, puedes hacer una pregunta médica general para obtener respuestas de la base de conocimientos.
Modelos admitidos
medlm-medium
medlm-large
Empezar
En los siguientes ejemplos se muestra cómo empezar a usar la API MedLM con las siguientes interfaces:
- API REST de Vertex AI
- SDK de Vertex AI para Python
- Vertex AI Studio
REST
Antes de usar los datos de la solicitud, haz las siguientes sustituciones:
PROJECT_ID
: tu ID de proyecto.MEDLM_MODEL
: el modelo de MedLM,medlm-medium
omedlm-large
.
Método HTTP y URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Cuerpo JSON de la solicitud:
{ "instances": [ { "content": "Question: What causes you to get ringworm?" } ], "parameters": { "temperature": 0, "maxOutputTokens": 256, "topK": 40, "topP": 0.95 } }
Para enviar tu solicitud, elige una de estas opciones:
curl
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
cat > request.json << 'EOF' { "instances": [ { "content": "Question: What causes you to get ringworm?" } ], "parameters": { "temperature": 0, "maxOutputTokens": 256, "topK": 40, "topP": 0.95 } } EOF
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
@' { "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
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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)
Ejecuta el siguiente código de Python en 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)
Ejecuta el siguiente código en tu cuaderno de Colaboratory. Introduce tu Google Cloud ID de proyecto donde se te indique. Para encontrar el ID de tu proyecto, consulta Localizar el ID de un proyecto.
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}")
Vertex AI Studio
Usa Vertex AI Studio para diseñar, probar y personalizar las peticiones que envías a la API MedLM. Antes de usar Vertex AI Studio para MedLM, consulta los requisitos previos en el artículo Enviar peticiones de texto a Gemini mediante Vertex AI Studio.
Para probar una petición de MedLM con Vertex AI Studio en laGoogle Cloud consola, haz lo siguiente:
- En la sección Vertex AI de la Google Cloud consola, ve a la página Vertex AI Studio.
- Haz clic en Empezar.
- Haz clic en Crear petición.
- En el menú Modelo, selecciona
MedLM-Medium
oMedLM-Large
. - En el campo Petición, escribe tu petición.
- (Opcional) Puedes ajustar los valores de Temperatura y Límite de tokens para probar cómo afectan a la respuesta. Te recomendamos que utilices los valores predeterminados. Si no sabes qué valores usar, utiliza los predeterminados.
- Haz clic en Enviar para generar una respuesta.
- (Opcional) Para guardar una petición, haz clic en Guardar.
- (Opcional) Para ver el código de Python o un comando
curl
de tu petición, haz clic en Obtener código.
Peticiones de búsqueda de respuestas
En las siguientes secciones se incluyen ejemplos de peticiones de respuesta a preguntas. Cada petición de ejemplo incluye el modelo y los valores de los parámetros recomendados.
Búsqueda de respuestas a preguntas largas
En los siguientes ejemplos se muestra cómo responde la API MedLM a una pregunta médica larga formulada como consulta.
REST
Antes de usar los datos de la solicitud, haz las siguientes sustituciones:
PROJECT_ID
: tu ID de proyecto.MEDLM_MODEL
: el modelo de MedLM,medlm-medium
omedlm-large
.
Método HTTP y URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Cuerpo JSON de la solicitud:
{ "instances": [ { "content": "Question: What causes you to get ringworm?" } ], "parameters": { "temperature": 0, "maxOutputTokens": 256, "topK": 40, "topP": 0.95 } }
Para enviar tu solicitud, elige una de estas opciones:
curl
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
cat > request.json << 'EOF' { "instances": [ { "content": "Question: What causes you to get ringworm?" } ], "parameters": { "temperature": 0, "maxOutputTokens": 256, "topK": 40, "topP": 0.95 } } EOF
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
@' { "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
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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
Responder a preguntas con varias opciones
En los siguientes ejemplos se muestra cómo responde la API MedLM a una pregunta médica con varias opciones. La petición es la siguiente:
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
Antes de usar los datos de la solicitud, haz las siguientes sustituciones:
PROJECT_ID
: tu ID de proyecto.MEDLM_MODEL
: el modelo de MedLM,medlm-medium
omedlm-large
.
Método HTTP y URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Cuerpo JSON de la solicitud:
{ "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 } }
Para enviar tu solicitud, elige una de estas opciones:
curl
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
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
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
@' { "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
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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
Peticiones de resumen
En las siguientes secciones se incluyen ejemplos de peticiones de resumen. Cada petición de ejemplo incluye el modelo y los valores de los parámetros recomendados.
Redactar un resumen posterior a la visita
En los siguientes ejemplos se muestra cómo generar un resumen posterior a la consulta de un paciente a partir de una nota de consulta ambulatoria. La petición contiene lo siguiente:
- Un preámbulo que contiene las instrucciones del modelo.
- Una descripción de cada campo que se va a extraer para el resumen.
El formato del resumen posterior a la visita se basa en Sieferd et al. (2019) y en las recomendaciones de la Academia de Universidades Médicas del Reino Unido. También puedes añadir ejemplos de pocas tomas antes de las notas y los resúmenes.
La petición es la siguiente:
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
Antes de usar los datos de la solicitud, haz las siguientes sustituciones:
PROJECT_ID
: tu ID de proyecto.MEDLM_MODEL
: el modelo de MedLM,medlm-medium
omedlm-large
.INPUT_NOTE
: la nota de entrada que se va a resumir.
Método HTTP y URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Cuerpo JSON de la solicitud:
{ "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 } }
Para enviar tu solicitud, elige una de estas opciones:
curl
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
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
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
@' { "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
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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
Redactar una nota de anamnesis y exploración física a partir de una transcripción
En los siguientes ejemplos se muestra cómo acelerar la documentación clínica enviando una solicitud a la API MedLM para escribir un borrador de historial y una nota de exploración física a partir de la transcripción de una conversación médica entre un profesional sanitario y un paciente.
La nota de H&P es una nota clínica completa que documenta el historial médico del paciente y la exploración física realizada por el proveedor. MedLM puede recopilar gran parte de la información clínica necesaria para redactar una nota de este tipo a partir de la conversación entre el profesional sanitario y el paciente durante la consulta médica.
Supongamos que tienes una transcripción de una conversación médica con el siguiente formato. Se conoce a los participantes de la conversación:
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
Antes de usar los datos de la solicitud, haz las siguientes sustituciones:
PROJECT_ID
: tu ID de proyecto.MEDLM_MODEL
: el modelo de MedLM,medlm-medium
omedlm-large
.
Método HTTP y URL:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict
Cuerpo JSON de la solicitud:
{ "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 } }
Para enviar tu solicitud, elige una de estas opciones:
curl
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
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
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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
Guarda el cuerpo de la solicitud en un archivo llamado request.json
.
Ejecuta el siguiente comando en el terminal para crear o sobrescribir este archivo en el directorio actual:
@' { "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
A continuación, ejecuta el siguiente comando para enviar tu solicitud 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)
Ejecuta el siguiente código de Python en 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)
Ejecuta el siguiente código en tu cuaderno de Colaboratory. Introduce tu Google Cloud ID de proyecto donde se te indique. Para encontrar el ID de tu proyecto, consulta Localizar el ID de un proyecto.
Introduce la transcripción médica donde se te indique.
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
Ten en cuenta lo siguiente:
- La nota generada puede contener imprecisiones y debe revisarla un médico antes de firmarla.
- Es posible que la nota generada no se ajuste estrictamente al formato o a la plantilla requeridos por el departamento o la especialidad clínica. Se trata de un punto de partida para registrar el estado del paciente.
- La calidad de la nota generada está limitada por la precisión de la transcripción proporcionada.
Implementar evaluaciones y medidas de mitigación centradas en la equidad
Es posible que MedLM genere resultados menos precisos para algunos grupos que para otros en función de la pregunta y de cómo se formule. Las diferencias en el rendimiento de los resultados del modelo entre grupos demográficos pueden exacerbar las desigualdades en materia de salud y perpetuar prejuicios dañinos. Estas imprecisiones en los resultados no son exclusivas de MedLM y suelen deberse a varios factores, como las desigualdades sociales y estructurales, los conceptos erróneos sobre medicina, los estereotipos negativos y la falta de diversidad en los datos de entrenamiento.
Considera la posibilidad de implementar evaluaciones y medidas de mitigación centradas en la equidad. Entre ellas, se incluyen las siguientes:
- Evaluar el rendimiento y el comportamiento del modelo en los casos prácticos previstos en diferentes poblaciones (como raza y etnia, nivel socioeconómico, ubicación geográfica, identidad de género, orientación sexual, edad, preferencia de idioma, casta, etc.).
- Obtener comentarios sobre el rendimiento.
- Colaborar con expertos interdisciplinares y partners externos especializados en definir y abordar los aspectos sociales y estructurales de la salud.
- Realizar esfuerzos de monitorización continua para evaluar y abordar los problemas de sesgo.
En función de tu caso práctico, puedes complementar tu petición con instrucciones centradas en la equidad, lo que puede mejorar la calidad de los resultados de MedLM en cuanto a sesgos y equidad.
Por ejemplo, el siguiente texto, cuando se coloca al principio de una petición, mejora la calidad de los resultados de las preguntas sobre medicina basada en la raza, tal como se muestra en 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.
Cambiar las peticiones influye en los resultados del modelo, por lo que se recomienda hacer evaluaciones completas para asegurarse de que no se vean afectadas otras áreas del rendimiento.
Consulta la tarjeta del modelo MedLM para obtener más información sobre el rendimiento del modelo.