Care transitions
Readmission and deterioration risk
Why this patient was flagged, from the model's own inputs, in terms a care team can check against the chart.
Solutions · Healthcare
For the teams that build and govern clinical and operational models. See why a patient was flagged, check that an imaging model looked at the anatomy and not the artefact, and notice when a model meets a population it was not validated on.
Where it fits
Care transitions
Why this patient was flagged, from the model's own inputs, in terms a care team can check against the chart.
Imaging
Grad-CAM, occlusion and LIME on a classifier's input, with a check of what the model says when the region it relied on is hidden.
Operations
Numeric and yes/no predictions explained in their own units, and watched for drift as case mix changes.
Payers
A stored explanation for each score, retrievable by your own case id.
Go-live
Compare the patients a model meets in production with the population it was validated on, input by input.
Research
Exact, seeded and exportable results that another group can reproduce.
A worked example
Public dataDiabetes 130-US Hospitals, 1999–2008, UCI Machine Learning Repository (Strack et al., 2014).readmission-30dscikit-learn · gradient boosting
A gradient-boosted model estimates the risk that a patient with diabetes is readmitted within 30 days of discharge, from ten inputs known at discharge. Race and gender are left out, and patients are kept apart between training and test. A discharge is flagged for a follow-up call at 20%. The data is de-identified and public; every figure below is what the Kaimei API returned.
POST https://api.kaimei.ai/v1/explanations
One patient
Discharge A is scored at 59.7%, against an average of 12.2%. Almost all of it is history: 8 inpatient stays in the past year add +32.8 points, and 5 emergency visits add +6.4.
Discharge C sits just over the line at 21.3%. Its largest push is 2 prior stays (+5.7), then an 8-day stay (+1.8). A nurse can see at a glance what the model saw, and what it did not.
At this threshold the model flags 7.6% of discharges and finds 18% of the readmissions. That trade-off is the hospital's to set; Kaimei reports it.
prior_inpatient is the most influential input, followed by discharge and age. Together they carry 65% of the measured importance (permutation importance over 2000 rows).What it learned
prior_inpatient is the most influential input, followed by discharge and age. Together they carry 65% of the measured importance (permutation importance over 2000 rows).
The weaker effects are reported as they are. Length of stay and age do not move risk in one direction, and Kaimei says so rather than smoothing them over.
prior_inpatient increases the probability of readmitted, most sharply between 2 and 4 (range 9% → 23%).discharge = care facility pushes the probability of readmitted highest and discharge = home lowest (range 10% → 16%).days_in_hospital has a non-monotonic effect on the probability of readmitted: it peaks around 8 days (range 10% → 12%).0.6% of decisions flip under 5%-σ input noise. Most fragile inputs: lab_procedures, medications.
On 2,000 reference rows the model predicts readmitted 7% of the time; 46% of cases sit within ±0.10 of the decision threshold.
A new population
Five hundred held-out encounters are logged as normal traffic, and every input is stable. Then a geriatric unit joins the deployment: five hundred encounters of patients aged 85 and over, drawn from the same data. Age leaves the reference range at once, and discharge destination follows. The model flags 7.6% of them against 5.8% before. Whether its validation still holds for this ward is a clinical governance question. Kaimei makes sure it is asked on the first day.
age, discharge. 500 logged predictions against 5,000 reference rows.Population stability index per input. Bars are cut off at 0.5; the line marks 0.25, where Kaimei calls drift significant.
Imaging
For an image classifier Kaimei draws where the evidence for a class sits, outlines the smallest region holding half of it, and then asks the model twice more: with that region hidden, and with only that region shown.
If hiding the focus barely changes the answer, the model is relying on something else in the picture. One plain sentence states where the model looked and whether that region alone decides.
The model looks mostly at the centre of the photo: half of its evidence for dog sits in 12% of the picture. That region alone is enough to say dog (P(dog) = 99.7%); with it hidden, P(dog) falls from 90.4% to 5.0%.
Privacy
The API runs on your own infrastructure, against your own database. Patient-level inputs never leave your environment.
Self-hostingPoint Kaimei at a scoring endpoint you host. It sends inputs and reads scores; the model itself is never uploaded.
inference="remote"Upload an architecture with shapes and statistics only. It can be drawn and reviewed, and the weights stay with you.
weights="summary"An explanation request carries the input it explains, and logged predictions are stored. For protected health information, run Kaimei inside your own environment. What leaves your network
Who it is for
Upload a fitted model in one call. See what it relies on, where its effects are weak, and how a retrain differs from the version in use.
Read why a patient was flagged in plain terms, and be told when the population a model serves is no longer the one it was validated on.
Exact, seeded results for a paper or a submission file, stored with the model version and exportable as JSON.
Rules and guidance
| Rule or guidance | What it concerns | Where Kaimei helps |
|---|---|---|
| FDA guiding principles for machine learning in medical devicesGood Machine Learning Practice (2021) and Transparency for Machine Learning-Enabled Medical Devices (2024), with Health Canada and the MHRA | Development practice, monitoring of deployed models, and clear information for the people who use them. | Documented model behaviour, per-prediction explanations and monitoring of deployed models for the developer's files. |
| Predetermined change control plansFDA final guidance for AI-enabled device software functions, December 2024 (current version August 2025); the guidance for all devices is still a draft | How planned changes to an AI-enabled device are described and verified. | Version-by-version comparison of what a model learned, stored with each release. |
| EU AI ActAI that is a safety component of a medical device is high-risk under Annex I; those obligations apply from 2 August 2028 | Risk management, logging, transparency, human oversight, accuracy and robustness. | Logged predictions and explanations, robustness and drift analyses. |
| Hospital Readmissions Reduction ProgramCMS; payment reductions capped at 3% | Why hospitals model 30-day readmission in the first place. | A readmission model whose flags can be explained and whose population is watched. |
Kaimei produces evidence for these processes. It does not make a model, a notice or a filing compliant, and nothing on this page is legal advice. Rules are cited as they stood in November 2026; check what applies to you now.
Kaimei is a tool for the teams that build and govern models. It is not a medical device, it does not give clinical advice, and the example above is a research illustration on public data.
Coming soon
What we are building now, and what to use until each one ships.
Accuracy, calibration and attributions compared across the patient groups you define. Until then, explanations help investigate a concern; they are not a test.
Word- and passage-level attributions for models that read free text, such as discharge summaries and referral letters.
Explanations for the boxes and masks a model draws on a scan, not only for its label. Image classification works today.
Missing values, out-of-range readings and unit changes caught as predictions are logged. Until then, Kaimei compares live inputs with the reference population.
Said plainly. Kaimei does not validate a model clinically, and it does not establish cause and effect.
What works today, and everything on the way, is in Supported models and what’s coming.
Bring a clinical or operational model. Start with it running entirely inside your environment.