Ziyuan Guan

The manuscript offers a timely, high‑level vision of Personal Health Data Spaces (PHDS) that will be useful for policymakers and researchers seeking a big‑picture view of patient‑centred data ecosystems. However, the work remains largely descriptive:...

Key Points: The developed dynamic model for predicting progression to stage 2 or higher AKI using multicenter data had robust performance. Clinical decision support implementation of the developed model could help prevent AKI progression. Kinetic eGFR, nephrotoxic drug burden, and BUN were the top features and remained the same across the models and sites. Background: AKI is an abrupt decline in kidney function that occurs in about 20% of hospitalized admissions and may lead to irreversible kidney damage. Methods: We developed and externally validated deep learning models to dynamically predict progression to stage 2 or higher AKI defined by Kidney Disease Improving Global Outcomes serum creatinine criteria within the next 48 hours. We used an extensive set of predictors including demographics, admission source, comorbidities, medications, laboratory, and vitals measurements. Results: Our retrospective study includes adult noncritical care patients at the University of Pittsburgh Medical Center (UPMC; 2018–2022; n =39,755) and the University of Florida Health (UFH; 2012–2019; n =122,324). In the UFH and UPMC development cohort, the mean age was 55 and 71 and 55% ( n =47,350) and 54% ( n =15,128) were female, respectively. Stage 2 or higher AKI occurred in 3% ( n =3257) and 8% ( n =2296) of UFH and UPMC patients, respectively. Area under the receiver operating characteristic curve values with 95% confidence interval (CI) ranged between 0.77 (95% CI, 0.75 to 0.78; UPMC Model—model trained on UPMC patients) and 0.81 (95% CI, 0.79 to 0.82; UFH Model—model trained on University of Florida patients) for the UFH test cohort and between 0.79 (95% CI, 0.78 to 0.8; UFH Model) and 0.83 (95% CI, 0.82 to 0.84; UPMC Model) for the UPMC test cohort. UFH-UPMC Model achieved an area under the receiver operating characteristic curve of 0.81 (95% CI, 0.80 to 0.83) for UFH and 0.82 (95% CI, 0.81 to 0.84) for UPMC test cohorts. Kinetic eGFR, nephrotoxic drug burden, and BUN remained the features with the highest influence across the models and institutions. Conclusions: The model developed using multicenter data had robust performance, suggesting that implementation could help prevent AKI progression.

Intensive care unit (ICU) patients often experience rapid changes in clinical status, requiring timely identification of deterioration to guide life-sustaining interventions. Current artificial intelligence (AI) models for acuity assessment rely on mortality as a proxy and lack direct prediction of clinical instability or treatment needs. Here we present APRICOT-M, a state-space model to predict real-time ICU acuity outcomes and transitions, and the need for life-sustaining therapies within the next four hours. The model integrates vital signs, laboratory results, medications, assessment scores, and patient characteristics, to make predictions, handling sparse, irregular data efficiently. Our model is trained on over 140,000 ICU admissions across 55 hospitals and validated on external and real-time data, outperforming clinical scores in predicting mortality and instability. The model demonstrates clinical relevance, with physicians reporting alerts as actionable and timely in a substantial portion of cases. These results highlight APRICOT-M's potential to support earlier, more informed ICU interventions.

Background: Electronic health records (EHRs) have an enormous potential to advance medical research and practice through easily accessible and interpretable EHR-derived databases. Attainability of this potential is limited by issues with data quality (DQ) and performance assessment. Objective: This review aims to streamline the current best practices on EHR DQ and performance assessments as a replicable standard for researchers in the field. Methods: PubMed was systematically searched for original research articles assessing EHR DQ and performance from inception until May 7, 2023. Results: Our search yielded 26 original research articles. Most articles had 1 or more significant limitations, including incomplete or inconsistent reporting (n=6, 30%), poor replicability (n=5, 25%), and limited generalizability of results (n=5, 25%). Completeness (n=21, 81%), conformance (n=18, 69%), and plausibility (n=16, 62%) were the most cited indicators of DQ, while correctness or accuracy (n=14, 54%) was most cited for data performance, with context-specific supplementation by recency (n=7, 27%), fairness (n=6, 23%), stability (n=4, 15%), and shareability (n=2, 8%) assessments. Artificial intelligence–based techniques, including natural language data extraction, data imputation, and fairness algorithms, were demonstrated to play a rising role in improving both dataset quality and performance. Conclusions: This review highlights the need for incentivizing DQ and performance assessments and their standardization. The results suggest the usefulness of artificial intelligence–based techniques for enhancing DQ and performance to unlock the full potential of EHRs to improve medical research and practice.

On average, more than 5 million patients are admitted to intensive care units (ICUs) in the US, with mortality rates ranging from 10 to 29%. The acuity state of patients in the ICU can quickly change from stable to unstable, sometimes leading to life-threatening conditions. Early detection of deteriorating conditions can assist in more timely interventions and improved survival rates. While Artificial Intelligence (AI)-based models show potential for assessing acuity in a more granular and automated manner, they typically use mortality as a proxy of acuity in the ICU. Furthermore, these methods do not determine the acuity state of a patient (i.e., stable or unstable), the transition between acuity states, or the need for life-sustaining therapies. In this study, we propose APRICOT-M (Acuity Prediction in Intensive Care Unit-Mamba), a 1M-parameter state space-based neural network to predict acuity state, transitions, and the need for life-sustaining therapies in real-time among ICU patients. The model integrates ICU data in the preceding four hours (including vital signs, laboratory results, assessment scores, and medications) and patient characteristics (age, sex, race, and comorbidities) to predict the acuity outcomes in the next four hours. Our state space-based model can process sparse and irregularly sampled data without manual imputation, thus reducing the noise in input data and increasing inference speed. The model was trained on data from 107,473 patients (142,062 ICU admissions) from 55 hospitals between 2014-2017 and validated externally on data from 74,901 patients (101,356 ICU admissions) from 143 hospitals. Additionally, it was validated temporally on data from 12,927 patients (15,940 ICU admissions) from one hospital in 2018-2019 and prospectively on data from 215 patients (369 ICU admissions) from one hospital in 2021-2023. Three datasets were used for training and evaluation: the University of Florida Health (UFH) dataset, the electronic ICU Collaborative Research Database (eICU), and the Medical Information Mart for Intensive Care (MIMIC)-IV dataset. APRICOT-M significantly outperforms the baseline acuity assessment, Sequential Organ Failure Assessment (SOFA), for mortality prediction in both external (AUROC 0.95 CI: 0.94-0.95 compared to 0.78 CI: 0.78-0.79) and prospective (AUROC 0.99 CI: 0.97-1.00 compared to 0.80 CI: 0.65-0.92) cohorts, as well as for instability prediction (external AUROC 0.75 CI: 0.74-0.75 compared to 0.51 CI: 0.51-0.51, and prospective AUROC 0.69 CI: 0.64-0.74 compared to 0.53 CI: 0.50-0.57). This tool has the potential to help clinicians make timely interventions by predicting the transition between acuity states and decision-making on life-sustaining within the next four hours in the ICU.

Modern electronic health records (EHRs) hold immense promise in tracking personalized patient health trajectories through sequential deep learning, owing to their extensive breadth, scale, and temporal granularity. Nonetheless, how to effectively leverage multiple modalities from EHRs poses significant challenges, given its complex characteristics such as high dimensionality, multimodality, sparsity, varied recording frequencies, and temporal irregularities. To this end, this paper introduces a novel multimodal contrastive learning framework, specifically focusing on medical time series and clinical notes. To tackle the challenge of sparsity and irregular time intervals in medical time series, the framework integrates temporal cross-attention transformers with a dynamic embedding and tokenization scheme for learning multimodal feature representations. To harness the interconnected relationships between medical time series and clinical notes, the framework equips a global contrastive loss, aligning a patient's multimodal feature representations with the corresponding discharge summaries. Since discharge summaries uniquely pertain to individual patients and represent a holistic view of the patient's hospital stay, machine learning models are led to learn discriminative multimodal features via global contrasting. Extensive experiments with a real-world EHR dataset demonstrated that our framework outperformed state-of-the-art approaches on the exemplar task of predicting the occurrence of nine postoperative complications for more than 120,000 major inpatient surgeries using multimodal data from UF health system split among three hospitals (UF Health Gainesville, UF Health Jacksonville, and UF Health Jacksonville-North).

The breadth, scale, and temporal granularity of modern electronic health records (EHR) systems offers great potential for estimating personalized and contextual patient health trajectories using sequential deep learning. However, learning useful representations of EHR data is challenging due to its high dimensionality, sparsity, multimodality, irregular and variable-specific recording frequency, and timestamp duplication when multiple measurements are recorded simultaneously. Although recent efforts to fuse structured EHR and unstructured clinical notes suggest the potential for more accurate prediction of clinical outcomes, less focus has been placed on EHR embedding approaches that directly address temporal EHR challenges by learning time-aware representations from multimodal patient time series. In this paper, we introduce a dynamic embedding and tokenization framework for precise representation of multimodal clinical time series that combines novel methods for encoding time and sequential position with temporal cross-attention. Our embedding and tokenization framework, when integrated into a multitask transformer classifier with sliding window attention, outperformed baseline approaches on the exemplar task of predicting the occurrence of nine postoperative complications of more than 120,000 major inpatient surgeries using multimodal data from three hospitals and two academic health centers in the United States.

BACKGROUND Electronic Health Records (EHRs) have an enormous potential to advance medical research and practice through easily accessible and interpretable EHR-derived databases. Attainability of this potential is limited by issues with data quality and performance assessment. OBJECTIVE This review aims to streamline the current best practices on EHR Data Quality and Performance assessments as a replicable standard for researchers in the field. METHODS PubMed was systematically searched for original research articles assessing EHR data quality and/or performance from inception until May 7, 2023. RESULTS Our search yielded 26 original research articles. Most articles suffered from one or more significant limitations, including incomplete or inconsistent reporting (30%), poor replicability (25%), and lacking generalizability of results (25%). Completeness (81%), Conformance (69%), and Plausibility (62%) were the most cited indicators of Data Quality, while Correctness/Accuracy (54%) was most cited for Data Performance, with context-specific supplementation by Recency (27%), Fairness (23%), Stability (15%), and Shareability (8%) assessments. Artificial Intelligence (AI)-based techniques including natural language data extraction, data imputation, and fairness algorithms were demonstrated to play a rising role in improving both dataset quality and performance. CONCLUSIONS This review highlights the need for incentivizing data quality and performance assessments and their standardization. The results suggest utility of the adoption of AI-based techniques for enhancing data quality and performance to unlock the full potential of EHRs to improve medical research and practice.

Background: Machine learning–enabled clinical information systems (ML-CISs) have the potential to drive health care delivery and research. The Fast Healthcare Interoperability Resources (FHIR) data standard has been increasingly applied in developing these systems. However, methods for applying FHIR to ML-CISs are variable. Objective: This study evaluates and compares the functionalities, strengths, and weaknesses of existing systems and proposes guidelines for optimizing future work with ML-CISs. Methods: Embase, PubMed, and Web of Science were searched for articles describing machine learning systems that were used for clinical data analytics or decision support in compliance with FHIR standards. Information regarding each system’s functionality, data sources, formats, security, performance, resource requirements, scalability, strengths, and limitations was compared across systems. Results: A total of 39 articles describing FHIR-based ML-CISs were divided into the following three categories according to their primary focus: clinical decision support systems (n=18), data management and analytic platforms (n=10), or auxiliary modules and application programming interfaces (n=11). Model strengths included novel use of cloud systems, Bayesian networks, visualization strategies, and techniques for translating unstructured or free-text data to FHIR frameworks. Many intelligent systems lacked electronic health record interoperability and externally validated evidence of clinical efficacy. Conclusions: Shortcomings in current ML-CISs can be addressed by incorporating modular and interoperable data management, analytic platforms, secure interinstitutional data exchange, and application programming interfaces with adequate scalability to support both real-time and prospective clinical applications that use electronic health record platforms with diverse implementations.