#cognitive impairment

3posts

  1. An LSTM That Predicts Cognitive Impairment from Sleep Records
    Can sleep records from a ring-type wearable alone identify cognitive impairment? This post covers how an LSTM that combined five days of records achieved an AUC of 0.92, and which sleep metrics SHAP pointed out.
    Healthcare Data Analytics2026-10-10#sleep lifelog#cognitive impairment#wearable#time series classification#explainable ai#dementia screening
  2. Normal Pressure Hydrocephalus: Reading the Gaze Behind Wrong Answers
    What can gaze reveal at the moment a patient with normal pressure hydrocephalus gets a picture naming item wrong? After reading a paper on webcam eye tracking, this post summarizes the group differences that grew larger on incorrect responses and the limits of interpretation.
    Healthcare Data Analytics2026-10-10#normal pressure hydrocephalus#eye tracking#naming#lexical retrieval#cognitive impairment
  3. Can Acoustic Features of the Voice Tell Us About Cognitive Status?
    Can cognitive status be distinguished using only acoustic features extracted from short vocal recordings of 223 Korean speakers? This post summarizes a single paper covering model performance, important features, and the limitations posed by differences in age and education.
    Healthcare Data Analytics2026-10-09#acoustic features#voice biomarkers#cognitive impairment#dementia screening#explainable artificial intelligence#imbalanced data

Keywords

#dementia screening2#sleep lifelog1#wearable1#time series classification1#explainable ai1#normal pressure hydrocephalus1#eye tracking1#naming1#lexical retrieval1#acoustic features1#voice biomarkers1#explainable artificial intelligence1#imbalanced data1