Wireframe anatomical render of a human torso and spine, representing INDIRA's oncology focus
INDIRA · Oncology — Breast CancerData acquisition

Indian Locoregional Recurrence Algorithm

Predicts 5- and 10-year locoregional recurrence risk in non-metastatic breast cancer — calibrated for Indian patients.

• Work with us
One
•  The benchmark to surpass

Modelled after INFLUENCE 3.0 — and rebuilt for Indian breast cancer biology.

INDIRA — Oncology — Breast Cancer

INFLUENCE 3.0 was derived from 36,000+ Dutch patients and has never been validated on Indian cohorts. INDIRA re-derives the model on Indian-representative data with formal competing-risk correction.

TNBC representation

~25% Indian-representative, versus ~12–15% in INFLUENCE 3.0.

HER2 reliability

Weighted for NCGEQAS pathology concordance across Indian labs.

Competing risks

Fine-Gray models from Phase 3 — not formally corrected in the benchmark.

Derivation cohort

Indian cohort literature IPD plus a SEER proxy, not Dutch registry data.

~47
Mean age at presentation in India, vs. 62–64 in the West
≥0.82
Target 5-year LRR AUC at Phase 3, vs. 0.77 published
<1%
Target calibration error (ICI) at Phase 3

Published figures and AlgoMD research targets. Targets are goals, not results.

Two•  The clinical rationale
[ IMAGE · 16:7 ]
[ IMAGE · 16:7 ]

A decade younger, and harder to predict

Indian breast cancer presents a decade younger, with higher TNBC and HER2-positive rates, more advanced staging and different therapy access. A Dutch-derived model cannot produce calibrated estimates for these patients.

Why it matters
Age ~47

Mean presentation age in India, versus 62–64 in Western countries.

~25% TNBC

Triple-negative rates roughly double those of Western cohorts.

36,000+ Dutch

Patients behind INFLUENCE 3.0 — none of them Indian.

270+ centres

National Cancer Grid institutions — the network INDIRA is designed around.

Three•  Active dataset acquisition

Building the Indian evidence base

INDIRA is in active data acquisition, combining registry extraction with individual patient data from published Indian cohorts.

01
SEER*Stat extraction

SEER 21 breast-cancer data for proxy training — extraction in progress.

02
Literature IPD

Seven published Indian cohorts digitised via Engauge and IPDfromKM.

03
ICGA portal

Registration for controlled-access Indian breast-cancer genomics data.

04
NCRP baseline

National LRR incidence data via the Cancer Samiksha portal.