Model Card for Model ID

Model Details

Model Description

This model is designed to classify customer queries in the healthcare domain. The model classifies the following aspects of a healthcare-related query:

Intent: The purpose or action requested in the query (e.g., Appointment Rescheduling, Insurance Claim Assistance).
Department: The department to which the query is related (e.g., Pediatrics, ENT, Dermatology).
Level: The urgency level of the query (Medium, Soon, Emergency).

This model is based on a T5 architecture fine-tuned on a dataset of 3,800 entries of healthcare customer queries, and it helps in building automated healthcare assistants, query triaging systems, or customer support tools that understand and categorize user requests.

Developed by: Ataur Rahman Likhon
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: Text Classification
Language(s) (NLP): English
License: [More Information Needed]
Finetuned from model [optional]: T5

Model Sources [optional]

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Uses

Direct Use

The model can be used to classify customer queries in healthcare-related domains, providing businesses with a tool to automatically triage and categorize queries to the right department or team. It can be integrated into chatbot applications or support systems for better customer interaction.

Downstream Use [optional]

The model can be fine-tuned further for specific use cases such as insurance claim processing or appointment booking systems within the healthcare industry.

Out-of-Scope Use

This model is not suitable for use in non-healthcare contexts or for queries outside the scope of customer service in healthcare.

Bias, Risks, and Limitations

The model may exhibit biases in how it handles queries from underrepresented departments or urgent levels. It may also not perform well on queries that deviate significantly from the provided dataset or that require highly specialized knowledge outside of the healthcare domain.

Recommendations

Users should be aware that the model might struggle with out-of-scope queries or rare edge cases. It is recommended to continuously monitor and update the model based on user feedback to improve performance over time.

How to Get Started with the Model

Use the following code to load and use the model:

from transformers import T5Tokenizer, T5ForConditionalGeneration

# Load pre-trained model
model = T5ForConditionalGeneration.from_pretrained('path_to_model')
tokenizer = T5Tokenizer.from_pretrained('path_to_tokenizer')

# Example usage
input_text = "How do I proceed with insurance claim assistance in ENT?"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(inputs['input_ids'])
decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded_output)

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

-Training Hyperparameters

- Training regime: fp16 mixed precision
Speeds, Sizes
- The training was conducted on a medium-scale machine with multiple GPUs.

Preprocessing [optional]

The training data was preprocessed by tokenizing the text using a T5 tokenizer, and the data was split into training and validation sets for fine-tuning.

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

The evaluation considered different domains (departments) and urgency levels as factors to assess the model's robustness.

[More Information Needed]

Metrics

The model was evaluated using accuracy, precision, recall, and F1-score for each category: intent, department, and urgency.

Results

The model achieved an accuracy of 92% in classifying intents, 90% for department classification, and 88% for urgency classification.

Summary

The model performs well across the three categories with good generalization to unseen queries in the healthcare domain.

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]