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

BACKGROUND AND HYPOTHESIS

The 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.

STUDY DESIGN

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.

STUDY RESULTS

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.

CONCLUSION

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.

The Development of a Short Form of the Indonesian Version of the Wechsler Adult Intelligence Scale-Fourth Edition

(1) Background: The Wechsler intelligence scales are very popular in clinical practice and for research purposes. However, they are time consuming to administer. Therefore, researchers and psychologists have explored the possibility of shorter test battery compositions. (2) Methods: In this study, we investigated 13 potential short forms of the Indonesian version of the Wechsler Adult Intelligence Scale-Fourth Edition (WAIS-IV-ID). An existing standardization data set of 1745 Indonesian participants collected for the validation of the WAIS-IV-ID was used to examine the short forms' validity. These ranged from 2-subtest versions to 7-subtest versions. Regression analyses with goodness-of-fit measures were performed, and regression equations were determined for each short form to estimate the Full Scale IQ (FSIQ) score. Discrepancies between the FSIQ and the estimated FSIQ (FSIQEst) scores were examined and classification accuracies were calculated for each short form (% agreement of intelligence classification between the FSIQEst and FSIQ). (3) Results: None of the 13 short form FSIQEst values significantly differed from the FSIQ scores based on the full WAIS-IV-ID, and strong correlations were observed between each of these values. The classification accuracies of the short forms were between 56.8% and 81.0%. The 4-subtest short form of the WAIS-IV-ID consisting of the subtests Matrix Reasoning, Information, Arithmetic, and Coding had the optimal balance between best classification values and a short administration duration. The validity of this short form was demonstrated in a second study in an independent sample (N = 20). (4) Conclusions: Based on the results presented here, the WAIS-IV-ID short forms are able to reliably estimate the FSIQ, with a significant shorter administration duration. The WAIS-IV-ID short form consisting of four subtests, Matrix Reasoning, Information, Arithmetic, and Coding, was the best version according to our criteria.

Computerized-adaptive testing versus short forms for pediatric inflammatory bowel disease patient-reported outcome assessment

Introduction

Computerized-adaptive testing (CAT) may increase reliability or reduce respondent burden for assessing patient-reported outcomes compared with static short forms (SFs). We compared CAT versus SF administration of the Patient-Reported Outcomes Measurement Information System® (PROMIS®) Pediatric measures in pediatric inflammatory bowel disease (IBD).

Methods

Participants completed 4-item CAT, 5- or 6-item CAT, and 4-item SF versions of the PROMIS Pediatric measures. We compared average T-scores, intra-class correlations (ICCs), floor and ceiling effects, and standard error of measurement (SEM) across forms, along with mean effect sizes between active versus quiescent IBD disease activity groups.

Results

Average PROMIS T-scores across forms were <3 points (minimally important difference) of each other. All forms correlated highly with each other (ICCs ≥0.90) and had similar ceiling effects, but the CAT-5/6 had lower floor effects. The CAT-5/6 had lower SEM than the CAT-4 and SF-4, and the CAT-4 had a lower SEM than the SF-4. Mean effect sizes were similar across forms when contrasting disease activity groups.

Conclusions

The CAT and SF forms produced similar score results, but the CAT had better precision and lower floor effects. Researchers should consider PROMIS pediatric CAT if they anticipate that their sample will skew toward symptom extremes.

Correlates of Social Cognition and Psychopathic Traits in a Community-Based Sample of Males

Social cognition is the ability to identify, understand, and interpret mental states and emotions. Psychopathic traits are typically described in two ways; Primary: shallow affect, emotional detachment, and relationship difficulties, and Secondary Psychopathic Traits: antisocial traits, impulsiveness, and emotional dysregulation. People with high psychopathic traits tend to perform lower on measures of social cognition. This study investigated the relationship of social cognition (mentalising) to primary and secondary psychopathic traits in a non-clinical sample, and investigated the psychometric properties of the Reading the Mind in the Eyes Test (RMET) Short Forms (A and B). A community-based male sample (N = 1,000; age range 18-78) was recruited through an online platform. Psychopathic traits were measured using Levenson, Kiehl, and Fitzpatrick's Self-Report Psychopathy Scale, and stratified into Primary and Secondary Psychopathic traits. Secondary validation of the RMET Short Forms was completed investigating scale reliability, and validity. Findings suggest excellent psychometrics in a large community cohort for the RMET Short Forms (A and B), with significant negative correlations on social cognitive performance and high self-report psychopathy. The item valence within the social cognitive measure (positive, negative, and neutral affect stimuli) was also examined, and correlated significantly with both Primary and Secondary Psychopathic traits. This study provides further validation of the RMET Short Forms (A and B), and adds to the literature on the scale by investigating performance on short-form specific valence. This study further suggests that in a non-clinical community sample of males, that higher psychopathic traits correlated significantly, and negatively, with social cognitive performance.

Comparing Boston naming test short forms in a rehabilitation sample

The Boston Naming Test (BNT) has multiple short forms that do not include the noose item that have been primarily examined in dementia populations. This study compared BNT short forms with standard administration (BNT-S) in physical medicine and rehabilitation patients who underwent outpatient evaluation. The sample (N = 480) was 34% female and 91% white with average age of 46 years (SD = 15) and average education of 14 years (SD = 3). Five 15-item short forms were calculated: Consortium to Establish a Registry for Alzheimer's disease (CERAD-15); Lansing; and Mack 1, 2, and 4 (Mack-15.1, -15.2). Three 30-item short forms were calculated: Mack A, Saxon A, and BNT odd items. BNT-S and short forms were compared with Spearman correlations. Cronbach's alpha was calculated for all BNT forms. Impaired BNT scores were determined with norm-referenced scores (T < 36 and T < 40). Area under the curve (AUC) values were compared across short forms with impaired BNT as criterion. BNT-S showed strong correlations with 30-item (rho = 0.92-0.93) and 15-item short forms (rho = 0.80-0.87) except for CERAD-15 (rho = 0.69). Internal consistency was acceptable for all short forms (alpha = 0.72-0.86). BNT-S was impaired in 17% and 33% of participants at 35 T and 39 T cutoffs, respectively. BNT short forms showed excellent to outstanding classification accuracy predicting impairment using both cutoffs. BNT short forms warrant further study in rehabilitation settings.

Equivalent short forms of the Situational Feature Recognition Test 2: Psychometric properties and analysis of interform equivalence and test-retest reliability

OBJECTIVE

To obtain two equivalent short forms of the "Situational Feature Recognition Test, Version 2," a social perception test, and their psychometric properties.

METHODS

Patients with schizophrenia (n = 101) were assessed at two different times. Statistical analyses were performed as follows: (1) Cronbach's alpha was used to assess reliability; (2) Spearman correlations, Wilcoxon signed-rank test, and a 2 (form) × 2 (time) repeated measures multivariate analysis of variance were used to analyse interform equivalence; (3) Sensitivity to change was studied by a 2 (group) × 2 (time) repeated measures multivariate analysis of variance; (4) Spearman correlations were employed to assess test-retest reliability, convergent and discriminant validity, and relationship with functionality and symptoms.

RESULTS

The short forms showed good internal consistency at both times. Significant and moderate correlation between forms was found along with no statistically significant form x time interaction. Hits and false positives of both forms were moderately correlated at both times. Group x time interaction was significant especially for hits when assessing sensitivity to change. Both forms were significantly correlated with other social cognition domains and with functionality.

CONCLUSIONS

Results of this study support the use of short forms of the Situational Feature Recognition Test, Version 2 especially in clinical trials and longitudinal studies among patients with schizophrenia.

Comparing Scores From Full Length, Short Form, and Adaptive Tests of the Social Interaction Anxiety and Social Phobia Scales

The current study developed and examined the performance of a computerized adaptive version of the Social Interaction Anxiety and Social Phobia Scales (SIAS/SPS) and compared results with a previously developed static short form (SIAS-6/SPS-6) in terms of measurement precision, concordance with the full forms, and sensitivity to treatment. Among an online sample of Australian adults, there were relatively minor differences in the performance of the adaptive tests and static short forms when compared with the full scales. Moreover, both adaptive and static short forms generated similar effect sizes across treatment in a clinical sample. This provides further evidence for the use of static or adaptive short forms of the SIAS/SPS rather than the lengthier 20-item versions. However, at the individual level, the adaptive tests were able to maintain an acceptable level of precision, using few items as possible, across the severity continua in contrast to the static short forms.

Responsiveness and Minimal Important Change of the Pain Self-Efficacy Questionnaire and Short Forms in Patients With Chronic Low Back Pain

The Pain Self-Efficacy Questionnaire (PSEQ) is a valid and reliable patient-reported instrument used to assess pain self-efficacy in patients with chronic low back pain (CLBP). Recently, the 2-item (PSEQ-2) and the 4-item (PSEQ-4) short versions were developed showing satisfactory measurement properties in mixed populations with chronic pain. The aim of this study was to examine responsiveness and minimal important change (MIC) of PSEQ, PSEQ-2, and PSEQ-4 in patients with CLBP. We used a sample of 104 patients undergoing multimodal physical therapy designed to partly change pain self-efficacy beliefs. Responsiveness was assessed by testing 16 a priori formulated hypotheses regarding effect sizes, areas under the curve, and correlations with changes in other instruments measuring other constructs. The MIC was calculated using an external anchor specific for pain self-efficacy and the receiver operator characteristic (ROC) method. The PSEQ and the PSEQ-4 met all hypotheses, whereas the PSEQ-2 met all but 1. The MICs were 5.5 for the PSEQ (9% of the scale range) and 1.5 for PSEQ-2 (13% scale range) and PSEQ-4 (6% scale range). MIC values were different for patients with low or high baseline values for all 3 instruments. The PSEQ and its short versions are adequately responsive instruments in patients with CLBP.

PERSPECTIVE

This study suggests that the PSEQ and its short versions are responsive measures of pain self-efficacy in patients with CLBP, adding to previous literature on their validity and reliability. Considering their similar responsiveness, the 4-item PSEQ could replace the original 10-item version in busy clinical or research settings.

Assessing the validity of the RAND negative impact of asthma on quality of life short forms

BACKGROUND

In response to recommendations from the 2010 National Institutes of Health Asthma Outcomes Workshop, we developed a system for measuring the negative impact of asthma on quality of life (QoL), which was referred to as the RAND Negative Impact of Asthma on Quality of Life (RAND-IAQL) item bank. The bank contains 65 items that focus on the patient's perception of the impact or bother of asthma on his or her life.

OBJECTIVE

Evidence for the validity of 2 short forms, the RAND-IAQL 4-item and 12-item Short Forms, from the bank is presented.

METHODS

Using a sample of 2032 adults with asthma, we validated our short forms against the Asthma Quality of Life Questionnaire-Marks (AQLQ-M), the Asthma Control Test, and generic measures of QoL developed by the Patient-reported Outcomes Measurement Information System (PROMIS). Discriminant validity was examined by comparing scores of respondents who differed according to multiple health indicators.

RESULTS

Our sample ranged in age from 18 to 99 years (mean, 43 years), with 14% Hispanic, 11% Asian, 19% African American, and 56% non-Hispanic white race/ethnicity. Men had a significantly worse impact of asthma on QoL than women. The impact of asthma on QoL was greatest in African American and Hispanic subjects compared with that seen in non-Hispanic white subjects. Our measures correlated highly with the AQLQ-M and more strongly with the PROMIS global physical than mental scales. They differentiated between adults with asthma according to their perceived severity, level of control, presence or absence of exacerbations, and physical comorbidity.

CONCLUSION

The RAND-IAQL item bank, measuring the impact of asthma on QoL, will complement other patient-reported outcomes, such as measures of asthma symptoms, functioning, and control.

Developing a short-form structured diagnostic interview for common mental disorders using signal detection theory

Diagnostic instruments must be relatively free from respondent burden and cost effective to administer whilst remaining faithful to the psychiatric nomenclature. It seems logical to develop short-form alternatives to rather lengthy and complicated diagnostic interviews to facilitate large scale data collection. The current study examines one method, signal detection theory, for developing a short-form interview based on the Composite International Diagnostic Interview version 3.0. The method was able to retain the smallest number of items to predict a lifetime and 30 day DSM-IV diagnosis for 10 disorders. Concordance analyses between the full-form and the short-form modules, demonstrated an excellent level of agreement in the whole sample and various subsamples of the Australian population as well as in an international comparison sample of the US population. The good concordance between the long form and the short form demonstrates the ability of signal detection theory to assist in the development of valid short forms, which could replace lengthy diagnostic interviews when the aim is to reduce respondent burden and overall research costs.

Criterion validity of a Wechsler-III Scale Short Form in a sample of brazilian elderly

Although a normative process, changes in cognitive functioning vary among older adults. The differential diagnosis between normal and pathological aging must be made early using psychometrically adequate measures.