Systematic review of prediction models for postacute care destination decision-making

Clinical prediction models for knee pain in patients with knee osteoarthritis: a systematic review

OBJECTIVE

To identify and describe existing models for predicting knee pain in patients with knee osteoarthritis.

METHODS

The electronic databases PubMed, EMBASE, CINAHL, Web of Science, and Cochrane Library were searched from their inception to May 2023 for any studies to develop and validate a prediction model for predicting knee pain in patients with knee osteoarthritis. Two reviewers independently screened titles, abstracts, and full-text qualifications, and extracted data. Risk of bias was assessed using the PROBAST. Data extraction of eligible articles was extracted by a data extraction form based on CHARMS. The quality of evidence was graded according to GRADE. The results were summarized with descriptive statistics.

RESULTS

The search identified 2693 records. Sixteen articles reporting on 26 prediction models were included targeting occurrence (n = 9), others (n = 7), progression (n = 5), persistent (n = 2), incident (n = 1), frequent (n = 1), and flares (n = 1) of knee pain. Most of the studies (94%) were at high risk of bias. Model discrimination was assessed by the AUROC ranging from 0.62 to 0.81. The most common predictors were age, BMI, gender, baseline pain, and joint space width. Only frequent knee pain had a moderate quality of evidence; all other types of knee pain had a low quality of evidence.

CONCLUSION

There are many prediction models for knee pain in patients with knee osteoarthritis that do show promise. However, the clinical extensibility, applicability, and interpretability of predictive tools should be considered during model development.

Systematic reviews of machine learning in healthcare: a literature review

INTRODUCTION

The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery.

METHODS

A systematic literature review (SLR) of published SLRs evaluating ML applications in healthcare settings published between1 January 2010 and 27 March 2023 was conducted.

RESULTS

In total 220 SLRs covering 10,462 ML algorithms were reviewed. The main application of AI in medicine related to the clinical prediction and disease prognosis in oncology and neurology with the use of imaging data. Accuracy, specificity, and sensitivity were provided in 56%, 28%, and 25% SLRs respectively. Internal and external validation was reported in 53% and less than 1% of the cases respectively. The most common modeling approach was neural networks (2,454 ML algorithms), followed by support vector machine and random forest/decision trees (1,578 and 1,522 ML algorithms, respectively).

EXPERT OPINION

The review indicated considerable reporting gaps in terms of the ML's performance, both internal and external validation. Greater accessibility to healthcare data for developers can ensure the faster adoption of ML algorithms into clinical practice.

Self-reported gaps in care coordination and preventable adverse outcomes among older adults receiving home health care

BACKGROUND

Older adults see multiple outpatient providers and increasingly use home health care (HHC) services. Previous studies attempting to draw inferences about the association between HHC use and patient outcomes have been mixed. Whether HHC is associated with care coordination and how both influence outcomes are unknown. In addition, prior studies have not taken the patient perspective into account. We examined the association between receiving HHC and self-reported gaps in care coordination and separately, preventable adverse outcomes.

METHODS

The analysis for this cross-sectional study was conducted between October 2021 and June 2022, using data on 4296 Medicare beneficiaries from the Reasons for Geographic and Racial Differences in Stroke (REGARDS) study who completed a survey on care coordination from 2017 to 2018. The associations between the receipt of HHC and two outcomes (a gap in care coordination, and separately, a preventable adverse event) were examined with Poisson models with robust standard errors. Potential confounders were accounted for through propensity score-based inverse probability weighting.

RESULTS

Among 4296 participants, 430 (10%) received HHC and they were older and had more comorbidities and ambulatory visits than those without HHC. HHC was not associated with differences in self-reported gaps in care coordination (33.3% HHC vs. 32.5% no-HHC, p = 0.70). HHC recipients reported more preventable drug-drug interactions (9.1% vs. 4.0%, p < 0.001) but not more preventable ED visits or hospital admissions. In IPW-adjusted models, HHC was not associated with gaps in care coordination (p = 0.60) but was associated with double the risk of a preventable adverse outcome (aRR 2.06; CI: 1.37, 3.10, p < 0.001).

CONCLUSIONS

HHC recipients were significantly more likely (than those without HHC) to report a potentially preventable adverse event (particularly a drug-drug interaction), suggesting an opportunity to improve patient safety by leveraging the observations of older adults receiving HHC.

Machine learning applied to electronic health record data in home healthcare: A scoping review

OBJECTIVE

Despite recent calls for home healthcare (HHC) to integrate informatics, the application of machine learning in HHC is relatively unknown. Thus, this study aimed to synthesize and appraise the literature describing the application of machine learning to predict adverse outcomes (e.g., hospitalization, mortality) using electronic health record (EHR) data in the HHC setting. Our secondary aim was to evaluate the comprehensiveness of predictors used in the machine learning algorithms guided by the Biopsychosocial Model.

METHODS

During March 2022 we conducted a literature search in four databases: PubMed, Embase, CINAHL, and Scopus. Inclusion criteria were 1) describing services provided in the HHC setting, 2) applying machine learning algorithms to predict adverse outcomes, defined as outcomes related to patient deterioration, 3) using EHR data and 4) focusing on the adult population. Predictors were mapped to the Biopsychosocial Model. A risk of bias analysis was conducted using the Prediction Model Risk Of Bias Assessment Tool.

RESULTS

The final sample included 20 studies. Eighteen studies used predictors from standardized assessments integrated in the EHR. The most common outcome of interest was hospitalization (55%), followed by mortality (25%). Psychological predictors were frequently excluded (35%). Tree based algorithms were most frequently applied (75%). Most studies demonstrated high or unclear risk of bias (75%).

CONCLUSION

Future studies in HHC should consider incorporating machine learning algorithms into clinical decision support systems to identify patients at risk. Based on the Biopsychosocial model, psychological and interpersonal characteristics should be used along with biological characteristics to enhance risk prediction. To facilitate the widespread adoption of machine learning, stakeholders should encourage standardization in the HHC setting.

Nonlinear Machine Learning in Warfarin Dose Prediction: Insights from Contemporary Modelling Studies

Objective: This study aimed to systematically assess the characteristics and risk of bias of previous studies that have investigated nonlinear machine learning algorithms for warfarin dose prediction. Methods: We systematically searched PubMed, Embase, Cochrane Library, Chinese National Knowledge Infrastructure (CNKI), China Biology Medicine (CBM), China Science and Technology Journal Database (VIP), and Wanfang Database up to March 2022. We assessed the general characteristics of the included studies with respect to the participants, predictors, model development, and model evaluation. The methodological quality of the studies was determined, and the risk of bias was evaluated using the Prediction model Risk of Bias Assessment Tool (PROBAST). Results: From a total of 8996 studies, 23 were assessed in this study, of which 23 (100%) were retrospective, and 11 studies focused on the Asian population. The most common demographic and clinical predictors were age (21/23, 91%), weight (17/23, 74%), height (12/23, 52%), and amiodarone combination (11/23, 48%), while CYP2C9 (14/23, 61%), VKORC1 (14/23, 61%), and CYP4F2 (5/23, 22%) were the most common genetic predictors. Of the included studies, the MAE ranged from 1.47 to 10.86 mg/week in model development studies, from 2.42 to 5.18 mg/week in model development with external validation (same data) studies, from 12.07 to 17.59 mg/week in model development with external validation (another data) studies, and from 4.40 to 4.84 mg/week in model external validation studies. All studies were evaluated as having a high risk of bias. Factors contributing to the risk of bias include inappropriate exclusion of participants (10/23, 43%), small sample size (15/23, 65%), poor handling of missing data (20/23, 87%), and incorrect method of selecting predictors (8/23, 35%). Conclusions: Most studies on nonlinear-machine-learning-based warfarin prediction models show poor methodological quality and have a high risk of bias. The analysis domain is the major contributor to the overall high risk of bias. External validity and model reproducibility are lacking in most studies. Future studies should focus on external validity, diminish risk of bias, and enhance real-world clinical relevance.