JSL_MedS_v2 (LLM - q8)

Description

This LLM model is trained to perform Q&A, Summarization, RAG, and Chat.

Predicted Entities

Copy S3 URI

How to use

from sparknlp_jsl.llm import LLMLoader

llm_loader_pretrained = LLMLoader(spark).pretrained("jsl_meds_q8_v2", "en", "clinical/models")

prompt = """
Based on the following text, what age group is most susceptible to breast cancer?

## Text:
The exact cause of breast cancer is unknown. However, several risk factors can increase your likelihood of developing breast cancer, such as:
- A personal or family history of breast cancer
- A genetic mutation, such as BRCA1 or BRCA2
- Exposure to radiation
- Age (most commonly occurring in women over 50)
- Early onset of menstruation or late menopause
- Obesity
- Hormonal factors, such as taking hormone replacement therapy
"""

response = llm_loader_pretrained.generate(prompt)

import com.johnsnowlabs.ml.gguf.LLMLoader
import com.johnsnowlabs.nlp.SparkAccessor.spark

val llmLoader = new LLMLoader().setSparkSession(spark).pretrained("jsl_meds_q8_v2", "en", "clinical/models")

val prompt = """
Based on the following text, what age group is most susceptible to breast cancer?

## Text:
The exact cause of breast cancer is unknown. However, several risk factors can increase your likelihood of developing breast cancer, such as:
- A personal or family history of breast cancer
- A genetic mutation, such as BRCA1 or BRCA2
- Exposure to radiation
- Age (most commonly occurring in women over 50)
- Early onset of menstruation or late menopause
- Obesity
- Hormonal factors, such as taking hormone replacement therapy
"""

val response = llmLoader.generate(prompt)

Results

"""
Based on the provided text, the age group most susceptible to breast cancer is women over the age of 50. This is explicitly mentioned in the text, indicating that breast cancer is most commonly occurring in this age group. It is important to note that while age is a significant risk factor, other factors such as genetic mutations, family history, and hormonal factors also contribute to the likelihood of developing breast cancer. Regular screenings and awareness of risk factors are crucial for early detection and effective management of breast cancer.
"""

Model Information

Model Name: jsl_meds_q8_v2
Compatibility: Healthcare NLP 5.4.1+
License: Licensed
Edition: Official
Language: en
Size: 3.7 GB

Benchmarking

We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. % indicates the preference rate

## Overall
| Model      | Factuality % | Clinical Relevancy % | Conciseness % |
|------------|--------------|----------------------|---------------|
| JSL-MedS   | 0.24         | 0.25                 | 0.38          |
| GPT4o      | 0.19         | 0.26                 | 0.27          |
| Neutral    | 0.43         | 0.36                 | 0.18          |
| None       | 0.14         | 0.13                 | 0.17          |
| Total      | 1.00         | 1.00                 | 1.00          |

## Summary 
| Model      | Factuality % | Clinical Relevancy % | Conciseness % |
|------------|--------------|----------------------|---------------|
| JSL-MedS   | 0.47         | 0.48                 | 0.42          |
| GPT4o      | 0.25         | 0.25                 | 0.25          |
| Neutral    | 0.22         | 0.22                 | 0.25          |
| None       | 0.07         | 0.05                 | 0.08          |
| Total      | 1.00         | 1.00                 | 1.00          |

## QA
| Model      | Factuality % | Clinical Relevancy % | Conciseness % |
|------------|--------------|----------------------|---------------|
| JSL-MedS   | 0.35         | 0.36                 | 0.42          |
| GPT4o      | 0.24         | 0.24                 | 0.29          |
| Neutral    | 0.33         | 0.33                 | 0.18          |
| None       | 0.09         | 0.07                 | 0.11          |
| Total      | 1.00         | 1.00                 | 1.00          |

## BioMedical
| Model      | Factuality % | Clinical Relevancy % | Conciseness % |
|------------|--------------|----------------------|---------------|
| JSL-MedS   | 0.33         | 0.24                 | 0.57          |
| GPT4o      | 0.12         | 0.08                 | 0.16          |
| Neutral    | 0.45         | 0.57                 | 0.16          |
| None       | 0.10         | 0.10                 | 0.10          |
| Total      | 1.00         | 1.00                 | 1.00          |

## OpenEnded
| Model      | Factuality % | Clinical Relevancy % | Conciseness % |
|------------|--------------|----------------------|---------------|
| JSL-MedS   | 0.35         | 0.30                 | 0.39          |
| GPT4o      | 0.30         | 0.33                 | 0.41          |
| Neutral    | 0.19         | 0.20                 | 0.02          |
| None       | 0.17         | 0.17                 | 0.19          |
| Total      | 1.00         | 1.00                 | 1.00          |