Conversational Interfaces for Clinical Data with Large Language Models

Provides tools and Shiny applications for interacting with clinical datasets through natural language using large language models. Built on 'ellmer' and 'shinychat', it emphasizes privacy-aware workflows where data remains local and only necessary summaries or tool results are shared with the model. Includes ready-to-use chat interfaces for exploratory analysis, summarization, and querying of clinical data.

clinChat

Conversational interfaces for clinical data using Large Language Models in R.

clinChat helps clinical researchers, biostatisticians, and data scientists explore structured clinical datasets through natural language chat interfaces. It is built on the modern R LLM stack (ellmer + shinychat) and prioritizes privacy: your data stays local; the model only sees tool results you explicitly allow.

Features

Privacy-aware chat with clinical data frames
Pre-built tools for summarization, filtering, column description, and basic statistics
Ready-to-launch Shiny chat applications
Easy integration with ellmer providers (OpenAI, Anthropic, local models, etc.)
Designed for clinical and pharmaceutical data review workflows

Installation

# Install dependencies first
install.packages(c("shiny", "ellmer", "shinychat", "dplyr"))

# Then install this package (once on CRAN or from GitHub)
# install.packages("clinChat")
# or
# remotes::install_github("shekharchalwadigrepo-hub/clinChat")

Quick Start

library(clinChat)

# Example 1: Clinical trial data
set.seed(42)
trial_data <- data.frame(
  subject_id = paste0("S", 1:50),
  age = sample(20:80, 50, replace = TRUE),
  sex = sample(c("M", "F"), 50, replace = TRUE),
  treatment = sample(c("Drug A", "Placebo"), 50, replace = TRUE),
  response = sample(c("Yes", "No"), 50, replace = TRUE)
)

chat <- create_clinical_chat(trial_data)
# chat$chat("What is the response rate by treatment?")

# Example 2: Lab values
lab_data <- data.frame(
  patient_id = 1:40,
  age = sample(30:70, 40, replace = TRUE),
  diagnosis = sample(c("Diabetes", "Hypertension", "None"), 40, replace = TRUE),
  hba1c = round(rnorm(40, 7.0, 1.2), 1)
)

chat2 <- create_clinical_chat(lab_data)
# chat2$chat("How many patients have diabetes? What is their mean HbA1c?")

Launch a Shiny App

run_clinchat_app(trial_data, title = "Trial Data Chat")

Privacy Notes

Raw patient-level data is never sent to the LLM by default.
Tools return aggregated summaries, counts, or filtered results that you control.
Prefer local models (via Ollama or similar) for maximum privacy.
Always review tool outputs before relying on model responses in regulated environments.