Anirudh Gangadharan

ECG is All You Need [Clinical Study — n=311]

• Demonstrated first proof-of-concept for cross-modal cardiac inference: LLM-generated echocardiographic reports from 12-lead ECG images alone, without fine-tuning.
• Retrospective analysis of 311 paired ECG–echocardiogram cases comparing three LLMs against cardiologist gold standard.
• Best model achieved r=0.394 (p<0.001) for ejection fraction prediction, with 64% of estimates within ±5% of true values.
• Aimed at democratizing cardiac imaging in resource-constrained settings where echocardiography is unavailable.

Screening for Left Ventricular Dysfunction from Photographed 12-Lead ECGs [Deep Learning — n=500]

• Trained a multi-task EfficientNet-B3 ensemble to predict ejection fraction and regional wall-motion abnormality directly from photographed 12-lead ECGs.
• Three-stage transfer learning (ImageNet → PTB-XL 21,430 ECGs → 500 paired records) with inverse-density loss weighting and out-of-fold cross-validation.
• Severe-EF detection AUROC 0.76, RWMA screen AUROC 0.70; best folds reach 0.83–0.86. Diagnosed and fixed shortcut-learning and regression-to-the-mean failure modes via Grad-CAM.
• Deployed as a multilingual WhatsApp triage tool with a public Hugging Face demo.

HemoglobinAI [Clinical Study – n=600]

• Developed a multimodal machine learning pipeline for non-invasive hemoglobin estimation using smartphone imaging.
• Compared palpebral conjunctiva and buccal mucosa images in 600 pregnant women using standardized color calibration.
• Implemented YOLOv8-based segmentation and evaluated seven regression models with 5-fold cross-validation.
• Demonstrated marginally superior predictive performance using palpebral conjunctiva imaging.

EyeScopeAI [ICMR STS Grant]

• Developing a fully offline computer vision system for refractive error screening in rural settings.
• Secured competitive national research funding (ICMR STS) to address healthcare access disparities through frugal innovation.

LumiSleep [Software]

• Top 10 in Manipal Med tech hackathon 2025, pre-incubated at Manipal Bioincubator.
• Led an inter-disciplinary team of engineers, biotech students , medical students, data-science psychiatry majors from UT Austin Texas, IIT Madras, Grant Medical College etc.
• We built a working prototype of the software and tested it on users for feedback.

DoctorsAI

• Led national scaling of student wings and physician community from 500 to 5000+ members worldwide.
• Moderated panels, co-ordinated across various stakeholders and worked on couple of Health AI projects
• Helped organise the DoctorsAI Global Summit 2025.

Matali

An ambulance routing simulation. It looks at travel time, hospital capacity and the type of injury to work out where to send a patient. Still a simulation.

Diphea

Working on an Android app that measures how you touch and move your phone. It turns those movements into features and compares them with your own baseline. A work in progress.

Neula

A desktop experiment with typing rhythm and mouse movements. It looks at timing and movement patterns, learns a personal baseline and flags changes. The data stays on your computer.

Spectral Manifold

A small experiment with sound and 3D visuals. It takes audio from the microphone and makes the shapes move with it.

Gadag Institute of Medical Sciences