Loh Kah Meng — AI Systems for Human Decision-Making
★ Featured today
‹<br>1 / 10<br>›
Explore this system
Philosophy
On Human–AI Relationship
Every project on this site is built on the same working belief: the goal of applied AI is not to<br>replace a person's judgment but to make that judgment sharper, faster, and better informed. A model<br>that quietly makes the call is a liability. A model that shows its reasoning, flags what it doesn't<br>know, and hands a clear decision back to a human — that's a tool worth trusting.
01
Augment, don't replace
Systems are designed as decision support — surfacing patterns, risks, and probabilities<br>for a human to weigh, rather than issuing verdicts a person is expected to accept on faith.
02
Transparency over accuracy theater
A model's headline metric is never the whole story. Every project here documents what the data<br>can't tell you — missingness, top-coding, sampling bias — alongside what the model gets right.
03
Built for the person who has to act
A dashboard nobody reads and a model nobody trusts are the same failure. Every system is designed<br>around the actual decision-maker: what they need to see, in language they already use.
The Pento‑Helix
Underneath those three principles sits a broader frame I work from: the Pento‑Helix.<br>Pento, for five — a structure meant to stay portable, flexible, and adaptable across<br>contexts, not fixed to one project. Helix, because it behaves like DNA: one constant<br>structure that expresses itself differently everywhere it's deployed, the way RNA carries out<br>what DNA encodes.
01Human–AI collaboration and synchronization
02Human–AI harmony
03Each side strengthening the other's skills and expertise, while understanding the other's limitations — mutual respect
04Shared social responsibility for what gets built
05Progressive, together — the constant thread across every project, and what this site's mark is built around: a dot held steady at the center — the Tao — with a spiral of motion, a Milky Way, turning around it.
The first four pillars above are how the Pento‑Helix takes shape in the<br>Human–AI Augment Systems work collected on this site. Other projects will express their own<br>version of the same four; the fifth never changes.
Selected Work
Nine decision-support systems, grouped by the human problem they solve
Every system here rests on one belief: AI should make people better decision-makers, not replace<br>them. That belief has a home — the Nurse Augmenting System , human-centered patient<br>care and the core of the AEGIS programme. The rest prove the same principle holds across domains: two<br>are deployed as live, working apps, and all carry honest, full write-ups of what each model can and<br>can't tell you.
NEW SERIES · NOW LIVE
Diagnostic Augmenting Systems
A new series of screening tools grounded in the physiological kinetics of the disease itself — each returns an interpretable three-class risk stratification, surfaces its own uncertainty as a confidence score, and flags the at-risk patient while a clinician stays in command. First release: DRAS , diabetes risk from a 2-hour OGTT.
Plans across 24 countries worldwide<br>Kinetics-grounded<br>Human-in-command
Enter the Diagnostic Augmenting Systems
Domain 01 · Biomedical Intelligence
Biomedical Intelligence
Predicting a patient’s risk so a clinician can act early — AI that augments the nurse, never replaces her.
Healthcare · Core Project
Nurse Augmenting System for Biomedical Intelligence and Personalized Care Augmentation
Eight independently trained models — spanning linear, tree, kernel, boosting, and ensemble methods<br>— converged on the same five predictors of 30-day heart-failure readmission. A hand-engineered<br>clinical score (HCAS), not raw accuracy, was the point.
8 / 8<br>models agree on<br>the top 5 predictors
predictors in the<br>HCAS clinical score
30-day<br>readmission<br>window
View case study
Healthcare · Core Project
Medication Adherence & Healthcare Claims Analysis
A star-schema claims model and a five-model adherence benchmark on 24,084 diabetes and hypertension<br>patients — surfacing that non-adherent patients cost 2.5× more, and including an honest report<br>of the one model, out of five, that quietly failed.
81.98%<br>champion accuracy<br>(Gradient Boosting)
2.5×<br>claims cost of a<br>non-adherent patient
24,084<br>patients<br>modeled
View case study
AEGIS Flagship · Wearable
Wearable
One wearable, two tiers — Lifestyle for everyone, Clinical for the hospital desktop.
Lifestyle
AEGIS Protector — Your Personal 25/8 Body Guard
The everyday wearable: it learns your normal, catches the earliest electrical signs of a heart attack — the K-wave — before you feel a thing, and gets help moving. One device from the wrist to the ward, with a live interactive demo.
learns you<br>personal baseline,<br>always adapting
K-wave<br>early cardiac<br>warning
home→ward<br>one device,<br>everywhere
View case study
Clinical
AEGIS Clinical —...