AI Clinical Decision Support System (CDSS) for Teleconsultations in eSanjeevani, India Telemedicine Service: A Prospective Implementation Study
Bibliographic record
Abstract
Abstract Background Most Western clinical decision support systems (CDSS) fail to contextualise to India’s healthcare realities, limiting their adoption by healthcare workers (HCWs) and patients. With the rapid evolution of India’s telemedicine ecosystem, there is an urgent need for an indigenous, validated, and scalable AI-based CDSS integrated within national platforms to improve diagnostic accuracy and care delivery. Methods This study, conducted between 2022–2024 by an AI Centre of Excellence of the Government of India, focused on developing, validating, and implementing a knowledge-based CDSS symptom entry Physician Assistance Form (PAF) within eSanjeevani—India’s national teleconsultation platform. The study was conducted in three phases, each of which was interdependent, overlapping, and dynamic in nature. Phase 1 The AI system development utilised retrospective eSanjeevani 1.0 data (64 million consultations), extracting 0.22 million SNOMED CT–aligned records to identify 29,000 unique symptoms, which were refined to 115 for model training in the initial plan during 2022. The upgraded eSanjeevani 2.0 (2023) incorporated AI-based differential diagnosis, which was later expanded to include 300 symptoms (2025) with branching logic that integrated patient age, gender, language, and multidimensional symptom attributes. Phase 2 Expert clinicians validated the symptom repository, logic flow, and AI-generated diagnoses. Phase 3 The validated CDSS was implemented in eSanjeevani 2.0, providing real-time differential diagnosis and departmental recommendations during assisted and non-assisted teleconsultations. Findings Integration of AI-CDSS improved structured data capture, enhanced diagnostic precision, and streamlined patient triage within teleconsultations. Interpretation India’s AI-CDSS initiative represents the first government-supported, large-scale CDSS integration in a developing country, offering a replicable, ethical, and contextually grounded model for other LMICs to advance equitable and quality telehealth services.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.015 | 0.033 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.004 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".