Scholarlink

Several analytic approaches were examined in order to estimate the possibility of identifying Alzheimer’s patients using features of PLR waveforms from chromatic stimuli. PLRs for three colours of light pulses (red: 635 nm, blue: 470 nm, white: CIE x = 0.28, y = 0.31) at two levels of intensity (10 and 100 \(\mbox{cd/m}^2\) ) were observed at 60 Hz for 10 s. Pulses consisted of pre-stimulus (2s), light pulse (1s) and restoration phases (7s). Fifteen features were extracted from each PLR waveform, such as pupil constriction velocity, pupil response delay etc. Participants were seven AD patients (age: 42–84, mean = 68.1) and 12 similar-aged control subjects (age: 62–89, mean = 72.1). There were significant differences in some of the features of PLRs extracted from the two groups (AD and non-AD participants), particularly with the features for blue light stimuli in high brightness, which produced significant reactions in AD patients. The classification performance of using 15 features of the response to blue light stimuli was the highest among responses for all three colours and was higher than the performance using the procedure in the previous study. Two factor scores were extracted from the 15 features across all measurement conditions, and logistic functions were introduced in order to calculate the probability of identifying AD patients. Function parameters were estimated using a Bayesian technique. Least absolute shrinkage and selection operator (LASSO) was applied to sets of PLR features from each light stimulus, together with the ages of subjects, and optimised result sets were obtained. Prediction performance was higher than with the previous procedure. The use of PLRs features from chromatic stimuli for identifying AD was developed and evaluated.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Patients with Alzheimer’s Disease Using Extracted Waveform Features of the Pupil Light Reflex in Response to Chromatic Stimuli

  • 章节

  • 发表日期：

    2026年

查看全文
  • Minoru Nakayama,
  • Wioletta Nowak

摘要

Several analytic approaches were examined in order to estimate the possibility of identifying Alzheimer’s patients using features of PLR waveforms from chromatic stimuli. PLRs for three colours of light pulses (red: 635 nm, blue: 470 nm, white: CIE x = 0.28, y = 0.31) at two levels of intensity (10 and 100 \(\mbox{cd/m}^2\) ) were observed at 60 Hz for 10 s. Pulses consisted of pre-stimulus (2s), light pulse (1s) and restoration phases (7s). Fifteen features were extracted from each PLR waveform, such as pupil constriction velocity, pupil response delay etc. Participants were seven AD patients (age: 42–84, mean = 68.1) and 12 similar-aged control subjects (age: 62–89, mean = 72.1). There were significant differences in some of the features of PLRs extracted from the two groups (AD and non-AD participants), particularly with the features for blue light stimuli in high brightness, which produced significant reactions in AD patients. The classification performance of using 15 features of the response to blue light stimuli was the highest among responses for all three colours and was higher than the performance using the procedure in the previous study. Two factor scores were extracted from the 15 features across all measurement conditions, and logistic functions were introduced in order to calculate the probability of identifying AD patients. Function parameters were estimated using a Bayesian technique. Least absolute shrinkage and selection operator (LASSO) was applied to sets of PLR features from each light stimulus, together with the ages of subjects, and optimised result sets were obtained. Prediction performance was higher than with the previous procedure. The use of PLRs features from chromatic stimuli for identifying AD was developed and evaluated.