Healthscribe Clinical Note Generator

🚀 HealthScribe (A Clinical Note Generator)

HealthScribe is a fine - tuned model that generates clinical notes from doctor - patient conversation data, enhancing the efficiency of medical record - keeping.

🚀 Quick Start

This model is a fine - tuned version of facebook/bart-large-cnn on a modified version of MTS-Dialog Dataset dataset. It is developed for the project HealthScirbe and integrated with a Flask web application. The web application enables users to generate clinical notes from transcribed ASR (Automatic Speech Recognition) data of doctor - patient conversations.

✨ Features

• Clinical Note Generation: Generate clinical notes from doctor - patient conversation data.
• Web Application Integration: Integrated with a Flask web application for easy use.

📚 Documentation

Model description

The model was developed for the project HealthScirbe and is integrated with a Flask web application. The project allows users to generate clinical notes from transcribed ASR data of doctor - patient conversations.

TEST DATA Sample For Inference (More given in test.txt)

You can refer to test.txt for further examples of conversations.

"Doctor: Hi there, I love that dress, very pretty! 
Patient: Thank you for complementing a seventy-two-year-old patient.
Doctor: No, I mean it, seriously. Okay, so you were admitted here in May two thousand nine. You have a history of hypertension, and on June eighteenth two thousand nine you had bad abdominal pain diarrhea and cramps.
Patient: Yes, they told me I might have C Diff? They did a CT of my abdomen and that is when they thought I got the infection.
Doctor: Yes, it showed evidence of diffuse colitis, so I believe they gave you IV antibiotics?
Patient: Yes they did. 
Doctor: Yeah I see here, Flagyl and Levaquin. They started IV Reglan as well for your vomiting.
Patient: Yes, I was very nauseous. Vomited as well.
Doctor: After all this I still see your white blood cells high. Are you still nauseous? 
Patient: No, I do not have any nausea or vomiting, but still have diarrhea. Due to all that diarrhea I feel very weak.
Doctor: Okay. Anything else any other symptoms?
Patient: Actually no. Everything's well.
Doctor: Great.
Patient: Yeah."

Intended uses & limitations

The model is used to generate clinical notes from doctor - patient conversation data (ASR). However, it has certain limitations:

• Low N/A Output Generation: Sometimes, it may produce a "None" output.
• Hallucination Issue: When the input data has very few character tokens or is extremely large, the model may start to hallucinate.

🔧 Technical Details

Training Metrics

Training and evaluation data

The model achieves the following results on the evaluation set:

• Loss: 0.1562
• Rouge1: 54.3238
• Rouge2: 34.2678
• Rougel: 46.5847
• Rougelsum: 51.2214
• Generation Length: 77.04

Training procedure

The model was trained on 1201 training samples and 100 validation samples of the modified MTS - Dialog.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.39.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2

📄 License

This project is licensed under the MIT license.