Learning Phenotypic Associations for Parkinson's Disease with Longitudinal Clinical Records.

Parkinson's disease (PD) is associated with multiple clinical motor and non-motor manifestations. Understanding of PD etiologies has been informed by a growing number of genetic mutations and various fluid-based and brain imaging biomarkers. However, the mechanisms underlying its varied phenotypic features remain elusive. The present work introduces a data-driven approach for generating phenotypic association graphs for PD cohorts. Data collected by the Parkinson's Progression Markers Initiative (PPMI), the Parkinson's Disease Biomarkers Program (PDBP), and the Fox Investigation for New Discovery of Biomarkers (BioFIND) were analyzed by this approach to identify heterogeneous and longitudinal phenotypic associations that may provide insight into the pathology of this complex disease. Findings based on the phenotypic association graphs could improve understanding of longitudinal PD pathologies and how these relate to patient symptomology.

Corticosteroids for infectious critical illness: A multicenter target trial emulation stratified by predicted organ dysfunction trajectory.

Corticosteroids decrease the duration of organ dysfunction in a range of infectious critical illnesses, but their risk and benefit are not fully defined using this construct. This retrospective multicenter study aimed to evaluate the association between usage of corticosteroids and mortality of patients with infectious critical illness by emulating a target trial framework. The study employed a novel stratification method with predictive machine learning (ML) subphenotyping based on organ dysfunction trajectory. Our analysis revealed that corticosteroids' effectiveness varied depending on the stratification method. The ML-based approach identified four distinct subphenotypes, two of which had a large enough sample size in our patient cohorts for further evaluation: "Rapidly Improving" (RI) and "Rapidly Worsening," (RW) which showed divergent responses to corticosteroid treatment. Specifically, the RW group either benefited or were not harmed from corticosteroids, whereas the RI group appeared to derive harm. In the development cohort, which comprised of a combination of patients from the eICU and MIMIC-IV datasets, hazard ratio estimates for the primary outcome, 28-day mortality, in the RW group was 1.05 (95% CI: 0.96 - 1.04) whereas for the RW group, it was 1.40 (95% CI: 1.28 - 1.54). For the validation cohort, which comprised of patients from the Critical carE Database for Advanced Research, estimates for 28-day mortality for the RW and RI groups were 1.24 (95% CI: 1.05 - 1.46) and 1.34 (95% CI: 1.14 - 1.59), respectively. For secondary outcomes, the RW group had a shorter time to ICU discharge and time to cessation of mechanical ventilation with corticosteroid treatment, where the RI group again demonstrated harm. The findings support matching treatment strategies to empirically observed pathobiology and offer a more nuanced understanding of corticosteroid utility. Our results have implications for the design and interpretation of both observational studies and randomized controlled trials (RCTs), suggesting the need for stratification methods that account for the differential response to standard of care.

Learning across diverse biomedical data modalities and cohorts: Challenges and opportunities for innovation.

In healthcare, machine learning (ML) shows significant potential to augment patient care, improve population health, and streamline healthcare workflows. Realizing its full potential is, however, often hampered by concerns about data privacy, diversity in data sources, and suboptimal utilization of different data modalities. This review studies the utility of cross-cohort cross-category (C4) integration in such contexts: the process of combining information from diverse datasets distributed across distinct, secure sites. We argue that C4 approaches could pave the way for ML models that are both holistic and widely applicable. This paper provides a comprehensive overview of C4 in health care, including its present stage, potential opportunities, and associated challenges.

An adaptive federated learning framework for clinical risk prediction with electronic health records from multiple hospitals.

Clinical risk prediction with electronic health records (EHR) using machine learning has attracted lots of attentions in recent years, where one of the key challenges is how to protect data privacy. Federated learning (FL) provides a promising framework for building predictive models by leveraging the data from multiple institutions without sharing them. However, data distribution drift across different institutions greatly impacts the performance of FL. In this paper, an adaptive FL framework was proposed to address this challenge. Our framework separated the input features into stable, domain-specific, and conditional-irrelevant parts according to their relationships to clinical outcomes. We evaluate this framework on the tasks of predicting the onset risk of sepsis and acute kidney injury (AKI) for patients in the intensive care unit (ICU) from multiple clinical institutions. The results showed that our framework can achieve better prediction performance compared with existing FL baselines and provide reasonable feature interpretations.

Bipartite Ranking Fairness Through a Model Agnostic Ordering Adjustment.

Recently, with the applications of algorithms in various risky scenarios, algorithmic fairness has been a serious concern and received lots of interest in machine learning community. In this article, we focus on the bipartite ranking scenario, where the instances come from either the positive or negative class and the goal is to learn a ranking function that ranks positive instances higher than negative ones. We are interested in whether the learned ranking function can cause systematic disparity across different protected groups defined by sensitive attributes. While there could be a trade-off between fairness and performance, we propose a model agnostic post-processing framework xOrder for achieving fairness in bipartite ranking and maintaining the algorithm classification performance. In particular, we optimize a weighted sum of the utility as identifying an optimal warping path across different protected groups and solve it through a dynamic programming process. xOrder is compatible with various classification models and ranking fairness metrics, including supervised and unsupervised fairness metrics. In addition to binary groups, xOrder can be applied to multiple protected groups. We evaluate our proposed algorithm on four benchmark data sets and two real-world patient electronic health record repositories. xOrder consistently achieves a better balance between the algorithm utility and ranking fairness on a variety of datasets with different metrics. From the visualization of the calibrated ranking scores, xOrder mitigates the score distribution shifts of different groups compared with baselines. Moreover, additional analytical results verify that xOrder achieves a robust performance when faced with fewer samples and a bigger difference between training and testing ranking score distributions.

Generalizability of a Machine Learning Model for Improving Utilization of Parathyroid Hormone-Related Peptide Testing across Multiple Clinical Centers.

BACKGROUND: Measuring parathyroid hormone-related peptide (PTHrP) helps diagnose the humoral hypercalcemia of malignancy, but is often ordered for patients with low pretest probability, resulting in poor test utilization. Manual review of results to identify inappropriate PTHrP orders is a cumbersome process. METHODS: Using a dataset of 1330 patients from a single institute, we developed a machine learning (ML) model to predict abnormal PTHrP results. We then evaluated the performance of the model on two external datasets. Different strategies (model transporting, retraining, rebuilding, and fine-tuning) were investigated to improve model generalizability. Maximum mean discrepancy (MMD) was adopted to quantify the shift of data distributions across different datasets. RESULTS: The model achieved an area under the receiver operating characteristic curve (AUROC) of 0.936, and a specificity of 0.842 at 0.900 sensitivity in the development cohort. Directly transporting this model to two external datasets resulted in a deterioration of AUROC to 0.838 and 0.737, with the latter having a larger MMD corresponding to a greater data shift compared to the original dataset. Model rebuilding using site-specific data improved AUROC to 0.891 and 0.837 on the two sites, respectively. When external data is insufficient for retraining, a fine-tuning strategy also improved model utility. CONCLUSIONS: ML offers promise to improve PTHrP test utilization while relieving the burden of manual review. Transporting a ready-made model to external datasets may lead to performance deterioration due to data distribution shift. Model retraining or rebuilding could improve generalizability when there are enough data, and model fine-tuning may be favorable when site-specific data is limited.

Data heterogeneity in federated learning with Electronic Health Records: Case studies of risk prediction for acute kidney injury and sepsis diseases in critical care.

With the wider availability of healthcare data such as Electronic Health Records (EHR), more and more data-driven based approaches have been proposed to improve the quality-of-care delivery. Predictive modeling, which aims at building computational models for predicting clinical risk, is a popular research topic in healthcare analytics. However, concerns about privacy of healthcare data may hinder the development of effective predictive models that are generalizable because this often requires rich diverse data from multiple clinical institutions. Recently, federated learning (FL) has demonstrated promise in addressing this concern. However, data heterogeneity from different local participating sites may affect prediction performance of federated models. Due to acute kidney injury (AKI) and sepsis' high prevalence among patients admitted to intensive care units (ICU), the early prediction of these conditions based on AI is an important topic in critical care medicine. In this study, we take AKI and sepsis onset risk prediction in ICU as two examples to explore the impact of data heterogeneity in the FL framework as well as compare performances across frameworks. We built predictive models based on local, pooled, and FL frameworks using EHR data across multiple hospitals. The local framework only used data from each site itself. The pooled framework combined data from all sites. In the FL framework, each local site did not have access to other sites' data. A model was updated locally, and its parameters were shared to a central aggregator, which was used to update the federated model's parameters and then subsequently, shared with each site. We found models built within a FL framework outperformed local counterparts. Then, we analyzed variable importance discrepancies across sites and frameworks. Finally, we explored potential sources of the heterogeneity within the EHR data. The different distributions of demographic profiles, medication use, and site information contributed to data heterogeneity.