Preoperative prediction model for risk of readmission after total joint replacement surgery: a random forest approach leveraging NLP and unfairness mitigation for improved patient care and cost-effectiveness.

BACKGROUND: The Center for Medicare and Medicaid Services (CMS) imposes payment penalties for readmissions following total joint replacement surgeries. This study focuses on total hip, knee, and shoulder arthroplasty procedures as they account for most joint replacement surgeries. Apart from being a burden to healthcare systems, readmissions are also troublesome for patients. There are several studies which only utilized structured data from Electronic Health Records (EHR) without considering any gender and payor bias adjustments. METHODS: For this study, dataset of 38,581 total knee, hip, and shoulder replacement surgeries performed from 2015 to 2021 at Novant Health was gathered. This data was used to train a random forest machine learning model to predict the combined endpoint of emergency department (ED) visit or unplanned readmissions within 30 days of discharge or discharge to Skilled Nursing Facility (SNF) following the surgery. 98 features of laboratory results, diagnoses, vitals, medications, and utilization history were extracted. A natural language processing (NLP) model finetuned from Clinical BERT was used to generate an NLP risk score feature for each patient based on their clinical notes. To address societal biases, a feature bias analysis was performed in conjunction with propensity score matching. A threshold optimization algorithm from the Fairlearn toolkit was used to mitigate gender and payor biases to promote fairness in predictions. RESULTS: The model achieved an Area Under the Receiver Operating characteristic Curve (AUROC) of 0.738 (95% confidence interval, 0.724 to 0.754) and an Area Under the Precision-Recall Curve (AUPRC) of 0.406 (95% confidence interval, 0.384 to 0.433). Considering an outcome prevalence of 16%, these metrics indicate the model's ability to accurately discriminate between readmission and non-readmission cases within the context of total arthroplasty surgeries while adjusting patient scores in the model to mitigate bias based on patient gender and payor. CONCLUSION: This work culminated in a model that identifies the most predictive and protective features associated with the combined endpoint. This model serves as a tool to empower healthcare providers to proactively intervene based on these influential factors without introducing bias towards protected patient classes, effectively mitigating the risk of negative outcomes and ultimately improving quality of care regardless of socioeconomic factors.

Safety Assessment of Palm-Derived Ingredients as Used in Cosmetics.

The Expert Panel for Cosmetic Ingredient Safety (Panel) reviewed the safety of 8 palm tree (Euterpe edulis (juçara) and Euterpe oleracea (açaí))-derived ingredients as used in cosmetic products; these ingredients are reported to function mostly as skin conditioning agents. The Panel reviewed relevant data relating to the safety of these ingredients in cosmetic formulations. Industry should continue to use good manufacturing practices to limit impurities. The Panel concluded that palm tree (açaí and juçara)-derived ingredients are safe in cosmetics in the present practices of use and concentration described in this safety assessment.

Safety Assessment of Polysilicone-11 as Used in Cosmetics.

The Expert Panel for Cosmetic Ingredient Safety (Panel) assessed the safety of Polysilicone-11 as used in cosmetic formulations. This ingredient is reported to function as a film former. The Panel considered the available data and concluded that Polysilicone-11 is safe in cosmetics in the present practices of use and concentration described in this safety assessment.

Safety Assessment of Capryloyl Salicylic Acid as Used in Cosmetics.

The Expert Panel for Cosmetic Ingredient Safety (Panel) reassessed the safety of Capryloyl Salicylic Acid in cosmetic products; this ingredient is reported to function as a skin conditioning agent. The Panel reviewed relevant data relating to the safety of this ingredient in cosmetic formulations, and concluded that the available data are insufficient to make a determination that Capryloyl Salicylic Acid is safe under the intended conditions of use in cosmetic formulations.

Safety Assessment of Soy-Derived Ingredients as Used in Cosmetics.

The Expert Panel for Cosmetic Ingredient Safety (Panel) reviewed the safety of 28 soy-derived ingredients as used in cosmetic products. These ingredients are reported to primarily function as antioxidants, skin protectants, skin-conditioning agents, and hair-conditioning agents. The Panel considered the available data relating to the safety of these ingredients in cosmetic formulations, and concluded that 24 of the 28 soy-derived ingredients are safe in cosmetics in the present practices of use and concentration described in this safety assessment. The Panel also concluded that the available data are insufficient to make a determination that Glycine Max (Soybean) Callus Culture, Glycine Max (Soybean) Callus Culture Extract, Glycine Max (Soybean) Callus Extract, and Glycine Max (Soybean) Phytoplacenta Conditioned Media are safe under the intended conditions of use in cosmetic formulations.

Safety Assessment of Cocos nucifera (Coconut)-Derived Ingredients as Used in Cosmetics.

The Expert Panel for Cosmetic Ingredient Safety (Panel) assessed the safety of 11 Cocos nucifera (coconut)-derived ingredients, most of which are reported to function as skin-conditioning agents in cosmetic products. The Panel reviewed the available data to determine the safety of these ingredients. The Panel concluded that 10 ingredients, derived from coconut flower, fruit, and liquid endosperm, are safe in cosmetics in the present practices of use and concentration described in this safety assessment, and that the available data are insufficient to make a determination of safety for Cocos Nucifera (Coconut) Shell Powder under the intended conditions of use in cosmetic formulations.

Amended Safety Assessment of Methylchloroisothiazolinone and Methylisothiazolinone as Used in Cosmetics.

The Expert Panel for Cosmetic Ingredient Safety (Panel) reassessed the safety of the mixture Methylchloroisothiazolinone (MCI)/Methylisothiazolinone (MI), which functions as a preservative in cosmetic products. The Panel reviewed relevant animal and human data provided in this safety assessment, and data from the previously published safety assessment of this mixture, and concluded that MCI/MI is safe in cosmetics when formulated to be nonsensitizing, based on the results of a quantitative risk assessment or similar methodology; however, at no point should concentrations exceed 7.5 ppm in leave-on products or 15 ppm in rinse-off products.

Amended Safety Assessment of Methylisothiazolinone as Used in Cosmetics.

The Expert Panel for Cosmetic Ingredient Safety (Panel) reassessed the safety of Methylisothiazolinone, which functions as a preservative in cosmetics. The Panel reviewed relevant animal and human data provided in this safety assessment, and data from the previously published safety assessments of Methylisothiazolinone, and concluded that Methylisothiazolinone is safe for use in rinse-off cosmetic products at concentrations up to 100 ppm (ie, 0.01%) and safe in leave-on cosmetic products when they are formulated to be nonsensitizing, which may be determined based on a quantitative risk assessment or similar methodology.