Scholarlink

Background <p>Early, scalable screening for cognitive impairment is needed beyond traditional paper-and-pencil tools.</p> Objective <p>To evaluate the diagnostic accuracy and usability of SPICK, a Korean-language, voice-based cognitive screener.</p> Methods <p>In a prospective multicenter validation study (ITT <i>N</i> = 399), the reference diagnosis cognitively impaired (mild cognitive impairment [MCI] or Alzheimer’s dementia [AD]) or cognitively unimpaired (CU) was determined independently by board-certified neurologists; SPICK provided the index test result. The primary endpoint was SPICK sensitivity and specificity versus prespecified thresholds (≥ 80% and ≥ 59%). Secondary endpoints included subgroup performance (MCI vs CU; AD vs CU), accuracy, area under the receiver operating characteristic (ROC) curve [AUC], and System Usability Scale (SUS).</p> Results <p>For cognitive impairment detection, SPICK achieved sensitivity 85.71% (95% confidence interval [CI] 81.46–89.31%) and specificity 74.29% (62.44–83.99%), meeting thresholds; AUC 0.800 and accuracy 83.71%. Subgroup analyses showed MCI sensitivity 79.64% (72.73–85.47%) and specificity 74.29% (62.44–83.99%), and AD sensitivity 91.98% (86.67–95.66%) and specificity 74.29% (62.44–83.99%). Among 395 participants with usability data, mean SUS was 67.32 (SD 19.10; median 70.0).</p> Conclusion <p>SPICK demonstrated clinically meaningful accuracy with acceptable usability, supporting its potential as an automated, voice-based screening tool for diverse clinical settings.</p>

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

Clinical validation of a voice-based AI tool for screening cognitive impairment: a prospective multicenter study

  • 期刊论文

  • 发表日期：

    2026年1月3日

查看全文
  • Bora Yoon,
  • Hyuk-je Lee,
  • Woojun Kim,
  • Yong Soo Shim,
  • Eun Ye Lim,
  • A-Hyun Cho,
  • In Wook Song,
  • Yun Jeong Hong,
  • Hye Eun Shin,
  • Bon D. Ku,
  • Soo Hyun Cho,
  • Hyejin Ku,
  • Dong-Hoon Shin,
  • Dong Won Yang

摘要

Background

Early, scalable screening for cognitive impairment is needed beyond traditional paper-and-pencil tools.

Objective

To evaluate the diagnostic accuracy and usability of SPICK, a Korean-language, voice-based cognitive screener.

Methods

In a prospective multicenter validation study (ITT N = 399), the reference diagnosis cognitively impaired (mild cognitive impairment [MCI] or Alzheimer’s dementia [AD]) or cognitively unimpaired (CU) was determined independently by board-certified neurologists; SPICK provided the index test result. The primary endpoint was SPICK sensitivity and specificity versus prespecified thresholds (≥ 80% and ≥ 59%). Secondary endpoints included subgroup performance (MCI vs CU; AD vs CU), accuracy, area under the receiver operating characteristic (ROC) curve [AUC], and System Usability Scale (SUS).

Results

For cognitive impairment detection, SPICK achieved sensitivity 85.71% (95% confidence interval [CI] 81.46–89.31%) and specificity 74.29% (62.44–83.99%), meeting thresholds; AUC 0.800 and accuracy 83.71%. Subgroup analyses showed MCI sensitivity 79.64% (72.73–85.47%) and specificity 74.29% (62.44–83.99%), and AD sensitivity 91.98% (86.67–95.66%) and specificity 74.29% (62.44–83.99%). Among 395 participants with usability data, mean SUS was 67.32 (SD 19.10; median 70.0).

Conclusion

SPICK demonstrated clinically meaningful accuracy with acceptable usability, supporting its potential as an automated, voice-based screening tool for diverse clinical settings.