Skip to content
SIH Buddyby Ganeev Singh
Dev
All problem statements
SIH26003Strong pickacceptance 5/5

AI-Based Cognitive Gaming and Memory Assistance Platform for Elderly Dementia Patients in North Eastern Region (NER)

Ministry of Development of North Eastern Region (MDoNER) · Space Technology · Software

The safest high-ceiling pick in the MDoNER block, but the description asks for five components rather than a games app, so budget for the reminder and caregiver halves from the start.

What it actually is

Elderly people with dementia in the Northeast have almost no access to cognitive therapy, and their families carry the whole load without guidance. The ask is an app with brain-training games plus everyday memory support, in languages and imagery the patient recognises. A caregiver should be able to see whether the person is getting better or worse over time.

What to build

A tablet-first app with a patient mode containing adaptive cognitive games across the four domains the description names — memory, attention and concentration, daily routine recall, and pattern and object recognition — with difficulty that auto-adjusts to the patient's performance, a memory-assist screen carrying the reminder categories specified (medicines, hydration, daily activities, medical appointments), voice-assisted multilingual interaction with culturally familiar NER visuals and sounds, full offline operation with sync when connectivity returns, and a separate caregiver dashboard plotting per-domain cognitive scores over time with a decline alert.

Smallest thing that wins the room

Play two rounds of the recall game with deliberately wrong answers, watch the difficulty drop live, then flip to the caregiver dashboard and show the memory-domain line bending downward with a flagged alert.

How crowded this one gets

A guess, projected from the 2025 statements — the last year where both the submission counts and the winners were published.

Moderate95–220 teams expectedroughly 1 in 80–186 wins it

Quieter than 68% of the 226 · #73 of 226 by expected field

A normal-sized field. Your idea has to be good, not miraculous.

Why: central ministry statements sat below the average.

This is a guess, not a fact

Nobody has published 2026’s numbers yet. This is an analysed estimate from last year’s pattern, so please do not take it as the truth — check the live counter on the SIH portal before you decide anything. The range covers the middle half of likely outcomes, so one statement in two lands outside it. Entry closes at 500 ideas per statement, so no range goes past that — a statement that reaches the cap fills and shuts rather than drawing an unlimited crowd. The model reads only three things a team can see before choosing — software or hardware, the theme, and what kind of body posted it — and those explain about a quarter of the variation in last year’s field sizes (R² 0.25 on held-out statements). Trust the band more than the number, and the ordering more than either. It cannot see how good your idea is, which is the part that actually decides it.

The scores

The number is the shorthand. The line under it is the reason.

What you will be writing

  • Flutter or React Native
  • Bhashini API for Indic TTS/STT
  • SQLite / Hive offline store with sync
  • MediaPipe face detection for family album
  • fl_chart caregiver analytics
  • MoCA/MMSE-aligned domain scoring
  • Geriatric care
  • Cognitive health
  • Assistive technology

Prior art to read before you start

cognitive training games for dementia · caregiver monitoring dashboard · multilingual elderly assistive app

Analysed by Claude Opus. Every score above is a judgment call with its reasoning attached — kindly cross-check this against the official statement on the SIH portal before your team commits to it.