Social determinants of health in prognostic machine learning models for orthopaedic outcomes: A systematic review

A Systematic Review of Artificial Intelligence Models for Time-to-Event Outcome Applied in Cardiovascular Disease Risk Prediction

Artificial intelligence (AI) based predictive models for early detection of cardiovascular disease (CVD) risk are increasingly being utilised. However, AI based risk prediction models that account for right-censored data have been overlooked. This systematic review (PROSPERO protocol CRD42023492655) includes 33 studies that utilised machine learning (ML) and deep learning (DL) models for survival outcome in CVD prediction. We provided details on the employed ML and DL models, eXplainable AI (XAI) techniques, and type of included variables, with a focus on social determinants of health (SDoH) and gender-stratification. Approximately half of the studies were published in 2023 with the majority from the United States. Random Survival Forest (RSF), Survival Gradient Boosting models, and Penalised Cox models were the most frequently employed ML models. DeepSurv was the most frequently employed DL model. DL models were better at predicting CVD outcomes than ML models. Permutation-based feature importance and Shapley values were the most utilised XAI methods for explaining AI models. Moreover, only one in five studies performed gender-stratification analysis and very few incorporate the wide range of SDoH factors in their prediction model. In conclusion, the evidence indicates that RSF and DeepSurv models are currently the optimal models for predicting CVD outcomes. This study also highlights the better predictive ability of DL survival models, compared to ML models. Future research should ensure the appropriate interpretation of AI models, accounting for SDoH, and gender stratification, as gender plays a significant role in CVD occurrence.

Association of Socioeconomic Status With Worse Overall Survival in Patients With Bone and Joint Cancer

BACKGROUND

The effect of socioeconomic status (SES) on the outcomes of patients with metastatic cancer to bone has not been adequately studied. We analyzed the association between the Yost Index, a composite geocoded SES score, and overall survival among patients who underwent nonprimary surgical resection for bone metastases.

METHODS

This population-based study used data from the National Cancer Institute's Surveillance, Epidemiology, and End Results database (2010 to 2018). We categorized bone and joint sites using International Classification of Disease-O-3 recodes. The Yost Index was geocoded using a factor analysis and categorized into quintiles using census tract-level American Community Service 5-year estimates and seven measures: median household income, median house value, median rent, percent below 150% of the poverty line, education index, percent working class, and percent unemployed. Multivariate Cox regression models were used to calculate adjusted hazard ratios of overall survival and 95% confidence intervals.

RESULTS

A total of 138,158 patients were included. Patients with the lowest SES had 34% higher risk of mortality compared with those with the highest SES (adjusted hazard ratio of 1.34, 95% confidence interval: 1.32 to 1.37, P < 0.001). Among patients who underwent nonprimary surgery of the distant bone tumor (n = 11,984), the age-adjusted mortality rate was 31.3% higher in the lowest SES patients compared with the highest SES patients (9.9 versus 6.8 per 100,000, P < 0.001). Patients in the lowest SES group showed more racial heterogeneity (63.0% White, 33.5% Black, 3.1% AAPI) compared with the highest SES group (83.9% White, 4.0% Black, 11.8% AAPI, P < 0.001). Higher SES patients are more likely to be married (77.5% versus 59.0%, P < 0.0001) and to live in metropolitan areas (99.6% versus 73.6%, P < 0.0001) compared with lower SES patients.

DISCUSSION

Our results may have implications for developing interventions to improve access and quality of care for patients from lower SES backgrounds, ultimately reducing disparities in orthopaedic surgery.

Daring discourse: artificial intelligence in pain medicine, opportunities and challenges

Artificial intelligence (AI) tools are currently expanding their influence within healthcare. For pain clinics, unfettered introduction of AI may cause concern in both patients and healthcare teams. Much of the concern stems from the lack of community standards and understanding of how the tools and algorithms function. Data literacy and understanding can be challenging even for experienced healthcare providers as these topics are not incorporated into standard clinical education pathways. Another reasonable concern involves the potential for encoding bias in healthcare screening and treatment using faulty algorithms. And yet, the massive volume of data generated by healthcare encounters is increasingly challenging for healthcare teams to navigate and will require an intervention to make the medical record manageable in the future. AI approaches that lighten the workload and support clinical decision-making may provide a solution to the ever-increasing menial tasks involved in clinical care. The potential for pain providers to have higher-quality connections with their patients and manage multiple complex data sources might balance the understandable concerns around data quality and decision-making that accompany introduction of AI. As a specialty, pain medicine will need to establish thoughtful and intentionally integrated AI tools to help clinicians navigate the changing landscape of patient care.