Developing a machine learning-based short form of the positive and negative syndrome scale.

Lin, Gong-HongGong-HongLinLiu, Jen-HsuanJen-HsuanLiuSHIH-CHIEH LEEWu, Bo-JianBo-JianWuLi, Shu-QiShu-QiLiChiu, Hsien-JaneHsien-JaneChiuWang, San-PingSan-PingWangCHING-LIN HSIEH2024-12-242024-12-242024-04https://scholars.lib.ntu.edu.tw/handle/123456789/724325The Positive and Negative Syndrome Scale (PANSS) consists of 30 items and takes up to 50 minutes to administer and score. Therefore, this study aimed to develop and validate a machine learning-based short form of the PANSS (PANSS-MLSF) that reproduces the PANSS scores. Moreover, the PANSS-MLSF estimated the removed-item scores. The PANSS-MLSF was developed using an artificial neural network, and the removed-item scores were estimated using the eXtreme Gradient Boosting classifier algorithm. The reliability of the PANSS-MLSF was examined using Cronbach's alpha. The concurrent validity was examined by the association (Pearson's r) between the PANSS-MLSF and the PANSS. The convergent validity was examined by the association (Pearson's r) between the PANSS-MLSF and the Clinical Global Impression-Severity, Mini-Mental State Examination, and Lawton Instrumental Activities of Daily Living Scale. The agreement of the estimated removed-item scores with their original scores was examined using Cohen's kappa. Our analysis included data from 573 patients with moderate severity. The two versions of the PANSS-MLSF comprised 15 items and 9 items were proposed. The PANSS-MLSF scores were similar to the PANSS scores (mean squared error=2.6-24.4 points). The reliability, concurrent validity, and convergent validity of the PANSS-MLSF were good. Moderate to good agreement between the estimated removed-item scores and the original item scores was found in 60% of the removed items. The PANSS-MLSF offers a viable way to reduce PANSS administration time, maintain score comparability, uphold reliability and validity, and even estimate scores for the removed items.enartificial intelligencemachine learningschizophreniashort forms[SDGs]SDG3[SDGs]SDG16Developing a machine learning-based short form of the positive and negative syndrome scale.journal article10.1016/j.ajp.2024.10396538394743