noracodes/diabai-cgm-anomaly-detection

AI model by noracodes

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

This educational system flags unusual continuous glucose monitor (CGM) time-series patterns for technical review. It combines: It does not determine whether glucose is medically dangerous, diagnose a condition, or prove that a sensor failed. Validation experiments showed that Isolation Forest recognized abrupt spikes, drops, offsets, and noise but failed to recognize synthetic stuck-sensor events. Transparent rules detected stuck signals reliably and achieved better overall synthetic-event recall. The recommended interpretation is therefore: hybridalert is also returned for research comparison, but it generates more alerts and must not be interpreted as a medical alarm. The inference helper requires at least 13 consecutive readings sampled every 15 minutes, ordered from oldest to newest: Only the most recent 13 values are used. They provide the current reading plus 12 previous readings, representing three hours of past context. Missing gaps must be handled before calling the helper. The Isolation Forest uses ten current/past-only dynamics features:…

noracodes/diabai-cgm-anomaly-detection on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-17T08:33:19.011Z

Inside the original model card — Document outline
  1. DiabAI CGM Data-Quality Anomaly Detection
  2. Why rules and machine learning are both included
  3. Input
  4. Features
  5. Isolation Forest configuration
  6. Training data
  7. Evaluation limitation: no real anomaly labels
  8. Final held-out test results
  9. Synthetic corruption detection
  10. Authentic test alert rates
  11. Usage
  12. Intended use

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: cc-by-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

noracodes/diabai-cgm-anomaly-detection is a task-unspecified model repository published by noracodes on Hugging Face. The source reports the sklearn library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
Not reported
Library
sklearn
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
cc-by-4.0
Access
Not gated by Hugging Face
Created
2026-11-17T06:13:45.000Z
Last modified
2026-11-17T06:14:08.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-17T07:01:06.441Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models