Recursive Partitioning vs Computerized Adaptive Testing to Reduce the Burden of Health Assessments in Cleft Lip and/or Palate: Comparative Simulation Study

BACKGROUND

Computerized adaptive testing (CAT) has been shown to deliver short, accurate, and personalized versions of the CLEFT-Q patient-reported outcome measure for children and young adults born with a cleft lip and/or palate. Decision trees may integrate clinician-reported data (eg, age, gender, cleft type, and planned treatments) to make these assessments even shorter and more accurate.

OBJECTIVE

We aimed to create decision tree models incorporating clinician-reported data into adaptive CLEFT-Q assessments and compare their accuracy to traditional CAT models.

METHODS

We used relevant clinician-reported data and patient-reported item responses from the CLEFT-Q field test to train and test decision tree models using recursive partitioning. We compared the prediction accuracy of decision trees to CAT assessments of similar length. Participant scores from the full-length questionnaire were used as ground truth. Accuracy was assessed through Pearson's correlation coefficient of predicted and ground truth scores, mean absolute error, root mean squared error, and a two-tailed Wilcoxon signed-rank test comparing squared error.

RESULTS

Decision trees demonstrated poorer accuracy than CAT comparators and generally made data splits based on item responses rather than clinician-reported data.

CONCLUSIONS

When predicting CLEFT-Q scores, individual item responses are generally more informative than clinician-reported data. Decision trees that make binary splits are at risk of underfitting polytomous patient-reported outcome measure data and demonstrated poorer performance than CATs in this study.

Functional outcomes in the Cleft Care UK study--Part 3: oral health and audiology

Objectives

To compare oral health and hearing outcomes from the Clinical Standards Advisory Group (CSAG, 1998) and the Cleft Care UK (CCUK, 2013) studies.

Setting and sample population

Two UK‐based cross‐sectional studies of 5‐year‐olds born with non‐syndromic unilateral cleft lip and palate undertaken 15 years apart. CSAG children were treated in a dispersed model of care with low‐volume operators. CCUK children were treated in a centralized, high volume operator system.

Materials and methods

Oral health data were collected using a standardized proforma. Hearing was assessed using pure tone audiometry and middle ear status by otoscopy and tympanometry. ENT and hearing history were collected from medical notes and parental report.

Results

Oral health was assessed in 264 of 268 children (98.5%). The mean dmft was 2.3, 48% were caries free, and 44.7% had untreated caries. There was no evidence this had changed since the CSAG survey. Oral hygiene was generally good, 96% were enrolled with a dentist. Audiology was assessed in 227 of 268 children (84.7%). Forty‐three per cent of children received at least one set of grommets – a 17.6% reduction compared to CSAG. Abnormal middle ear status was apparent in 50.7% of children. There was no change in hearing levels, but more children with hearing loss were managed with hearing aids.

Conclusions

Outcomes for dental caries and hearing were no better in CCUK than in CSAG, although there was reduced use of grommets and increased use of hearing aids. The service specifications and recommendations should be scrutinized and implemented.