The BAPRAS screening tool for reimbursement in a postbariatric population

Machine learning applications and challenges in graft-versus-host disease: a scoping review

PURPOSE OF REVIEW

This review delves into the potential of artificial intelligence (AI), particularly machine learning (ML), in enhancing graft-versus-host disease (GVHD) risk assessment, diagnosis, and personalized treatment.

RECENT FINDINGS

Recent studies have demonstrated the superiority of ML algorithms over traditional multivariate statistical models in donor selection for allogeneic hematopoietic stem cell transplantation. ML has recently enabled dynamic risk assessment by modeling time-series data, an upgrade from the static, "snapshot" assessment of patients that conventional statistical models and older ML algorithms offer. Regarding diagnosis, a deep learning model, a subset of ML, can accurately identify skin segments affected with chronic GVHD with satisfactory results. ML methods such as Q-learning and deep reinforcement learning have been utilized to develop adaptive treatment strategies (ATS) for the personalized prevention and treatment of acute and chronic GVHD.

SUMMARY

To capitalize on these promising advancements, there is a need for large-scale, multicenter collaborations to develop generalizable ML models. Furthermore, addressing pertinent issues such as the implementation of stringent ethical guidelines is crucial before the widespread introduction of AI into GVHD care.

General population normative scores for interpreting the BODY-Q

The BODY-Q is a patient-reported outcome measure used to assess outcomes in patients undergoing weight loss and/or body contouring surgery (BC) following massive weight loss. Normative values for the BODY-Q are needed to improve data interpretation and enable comparison. Thus, the aim of this study was to determine normative values for the BODY-Q. Participants were recruited internationally through two crowdsourcing platforms. The participants were invited to complete the BODY-Q scales through an URL link provided within the crowdsourcing platforms. General linear analyses were performed to compare normative means between countries and continents adjusted for relevant covariates. Normative reference values were stratified by age, body mass index (BMI), and gender. The BODY-Q was completed by 4051 (2052 North American and 1999 European) participants. The mean age was 36 years (±14.7 SD) and ranged from 17 to 76 years, the mean BMI was 26.4 (±6.7 SD) kg/m² , and the sample consisted of 1996 (49.3%) females and 2023 (49.9%) males. Younger age and higher BMI were negatively associated with all BODY-Q scales (p < .001). This study provides normative values for the BODY-Q scales to aid in the interpretation of BODY-Q scores in research and clinical practise. These values enable us to understand the impact of weight loss and BC on patients' lives.

The PRS Rainbow Classification for Assessing Postbariatric Contour Deformities

Supplemental Digital Content is available in the text.

Background:

There is a need for a reliable classification system to grade contour deformities and to inform reimbursement of body contouring surgery after massive weight loss. We developed the PRS Rainbow Classification, which uses select photographs to provide standardized references for evaluating patient photographs, to classify contour deformities in postbariatric patients. To assess the reliability of the PRS Rainbow Classification to classify contour deformities in massive weight loss patients.

Methods:

Ten independent experienced plastic surgeons, 7 experienced medical advisors of the healthcare insurance company, and 10 laypersons evaluated 50 photographs per anatomical region (arms, breast, abdomen, and medial thighs). Each participant rated the patient photographs on a scale of 1–3 in an online survey. The inter-observer and the intra-observer reliabilities were determined using intra-class correlation coefficients (ICCs). The ICC analyses were performed for each anatomical region.

Results:

Inter-observer reliability was moderate to good in the body regions “arms,” “abdomen,” “medial thighs,” with mean ICC values of 0.678 [95% confidence interval (CI), 0.591–0.768], 0.685 (95% CI, 0.599–0.773), and 0.658 (95% CI, 0.569–0.751), respectively. Inter-observer reliability was comparable within the 3 different professional groups. Intra-observer reliability (test–retest reliability) was moderate to good, with a mean overall ICC value of 0.723 (95% CI, 0.572–0.874) for all groups and all 4 body regions.

Conclusions:

The moderate to good reliability found in this study validates the use of the PRS Rainbow Classification as a reproducible and reliable classification system to assess contour deformities after massive weight loss. It holds promise as a key part of instruments to classify body contour deformities and to assess reimbursement of body contouring surgery.