Dataset Information

Machine Learning in Aging: An Example of Developing Prediction Models for Serious Fall Injury in Older Adults.

ABSTRACT:

Background

Advances in computational algorithms and the availability of large datasets with clinically relevant characteristics provide an opportunity to develop machine learning prediction models to aid in diagnosis, prognosis, and treatment of older adults. Some studies have employed machine learning methods for prediction modeling, but skepticism of these methods remains due to lack of reproducibility and difficulty in understanding the complex algorithms that underlie models. We aim to provide an overview of two common machine learning methods: decision tree and random forest. We focus on these methods because they provide a high degree of interpretability.

Method

We discuss the underlying algorithms of decision tree and random forest methods and present a tutorial for developing prediction models for serious fall injury using data from the Lifestyle Interventions and Independence for Elders (LIFE) study.

Results

Decision tree is a machine learning method that produces a model resembling a flow chart. Random forest consists of a collection of many decision trees whose results are aggregated. In the tutorial example, we discuss evaluation metrics and interpretation for these models. Illustrated using data from the LIFE study, prediction models for serious fall injury were moderate at best (area under the receiver operating curve of 0.54 for decision tree and 0.66 for random forest).

Conclusions

Machine learning methods offer an alternative to traditional approaches for modeling outcomes in aging, but their use should be justified and output should be carefully described. Models should be assessed by clinical experts to ensure compatibility with clinical practice.

SUBMITTER: Speiser JL

PROVIDER: S-EPMC8011704 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ImportanceAlthough a serious fall injury is often a devastating event, little is known about the course of disability (ie, functional trajectories) before a serious fall injury or the relationship between these trajectories and those that follow the fall.ObjectivesTo identify distinct sets of functional trajectories in the year immediately before and after a serious fall injury, to evaluate the relationship between the prefall and postfall trajectories, and to determine whether these results differed based on the type of injury.Design, setting, and participantsProspective cohort study conducted in greater New Haven, Connecticut, from March 16, 1998, to June 30, 2012, in 754 community-living persons aged 70 years or older who were initially nondisabled in their basic activities of daily living. Of the 130 participants who subsequently sustained a serious fall injury, 62 had a hip fracture and 68 had another fall-related injury leading to hospitalization.Main outcomes and measuresFunctional trajectories, based on 13 basic, instrumental, and mobility activities assessed during monthly interviews, were identified in the year before and the year after the serious fall injury.ResultsBefore the fall, 5 distinct trajectories were identified: no disability in 16 participants (12.3%), mild disability in 34 (26.2%), moderate disability in 34 (26.2%), progressive disability in 23 (17.7%), and severe disability in 23 (17.7%). After the fall, 4 distinct trajectories were identified: rapid recovery in 12 participants (9.2%), gradual recovery in 35 (26.9%), little recovery in 26 (20.0%), and no recovery in 57 (43.8%). For both hip fractures and other serious fall injuries, the probabilities of the postfall trajectories were greatly influenced by the prefall trajectories, such that rapid recovery was observed only among persons who had no disability or mild disability, and a substantive recovery, defined as rapid or gradual, was highly unlikely among those who had progressive or severe disability. The postfall trajectories were consistently worse for hip fractures than for the other serious injuries.Conclusions and relevanceThe functional trajectories before and after a serious fall injury are quite varied but highly interconnected, suggesting that the likelihood of recovery is greatly constrained by the prefall trajectory.

Project description:BackgroundRapid identification of high-risk polytrauma patients is crucial for early intervention and improved outcomes. This study aimed to develop and validate machine learning models for predicting 72 h mortality in adult polytrauma patients using readily available clinical parameters.MethodsA retrospective analysis was conducted on polytrauma patients from the Dryad database and our institution. Missing values pertinent to eligible individuals within the Dryad database were compensated for through the k-nearest neighbor algorithm, subsequently randomizing them into training and internal validation factions on a 7:3 ratio. The patients of our institution functioned as external validation cohorts. The predictive efficacy of random forest (RF), neural network, and XGBoost models was assessed through an exhaustive suite of performance indicators. The SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) methods were engaged to explain the supreme-performing model. Conclusively, restricted cubic spline analysis and multivariate logistic regression were employed as sensitivity analyses to verify the robustness of the findings.ResultsParameters including age, body mass index, Glasgow Coma Scale, Injury Severity Score, pH, base excess, and lactate emerged as pivotal predictors of 72 h mortality. The RF model exhibited unparalleled performance, boasting an area under the receiver operating characteristic curve (AUROC) of 0.87 (95% confidence interval [CI] 0.84-0.89), an area under the precision-recall curve (AUPRC) of 0.67 (95% CI 0.61-0.73), and an accuracy of 0.83 (95% CI 0.81-0.86) in the internal validation cohort, paralleled by an AUROC of 0.98 (95% CI 0.97-0.99), an AUPRC of 0.88 (95% CI 0.83-0.93), and an accuracy of 0.97 (95% CI 0.96-0.98) in the external validation cohort. It provided the highest net benefit in the decision curve analysis in relation to the other models. The outcomes of the sensitivity examinations were congruent with those inferred from SHAP and LIME.ConclusionsThe RF model exhibited the best performance in predicting 72 h mortality in adult polytrauma patients and has the potential to aid clinicians in identifying high-risk patients and guiding clinical decision-making.

Project description:BackgroundPatients with rheumatoid arthritis (RA) have an increased risk of developing serious infections (SIs) vs. individuals without RA; efforts to predict SIs in this patient group are ongoing. We assessed the ability of different machine learning modeling approaches to predict SIs using baseline data from the tofacitinib RA clinical trials program.MethodsThis analysis included data from 19 clinical trials (phase 2, n = 10; phase 3, n = 6; phase 3b/4, n = 3). Patients with RA receiving tofacitinib 5 or 10 mg twice daily (BID) were included in the analysis; patients receiving tofacitinib 11 mg once daily were considered as tofacitinib 5 mg BID. All available patient-level baseline variables were extracted. Statistical and machine learning methods (logistic regression, support vector machines with linear kernel, random forest, extreme gradient boosting trees, and boosted trees) were implemented to assess the association of baseline variables with SI (logistic regression only), and to predict SI using selected baseline variables using 5-fold cross-validation. Missing values were handled individually per prediction model.ResultsA total of 8404 patients with RA treated with tofacitinib were eligible for inclusion (15,310 patient-years of total follow-up) of which 473 patients reported SIs. Amongst other baseline factors, age, previous infection, and corticosteroid use were significantly associated with SI. When applying prediction modeling for SI across data from all studies, the area under the receiver operating characteristic (AUROC) curve ranged from 0.656 to 0.739. AUROC values ranged from 0.599 to 0.730 in data from phase 3 and 3b/4 studies, and from 0.563 to 0.643 in data from ORAL Surveillance only.ConclusionsBaseline factors associated with SIs in the tofacitinib RA clinical trial program were similar to established SI risk factors associated with advanced treatments for RA. Furthermore, while model performance in predicting SI was similar to other published models, this did not meet the threshold for accurate prediction (AUROC > 0.85). Thus, predicting the occurrence of SIs at baseline remains challenging and may be complicated by the changing disease course of RA over time. Inclusion of other patient-associated and healthcare delivery-related factors and harmonization of the duration of studies included in the models may be required to improve prediction.Trial registrationClinicalTrials.gov: NCT00147498; NCT00413660; NCT00550446; NCT00603512; NCT00687193; NCT01164579; NCT00976599; NCT01059864; NCT01359150; NCT02147587; NCT00960440; NCT00847613; NCT00814307; NCT00856544; NCT00853385; NCT01039688; NCT02187055; NCT02831855; NCT02092467.