Search

BackgroundHeterogeneity in Acute Respiratory Distress Syndrome (ARDS), as a consequence of its non-specific definition, has led to a multitude of negative randomised controlled trials (RCTs). Investigators have sought to identify heterogeneity of treatment effect (HTE) in RCTs using clustering algorithms. We evaluated the proficiency of several commonly-used machine-learning algorithms to identify clusters where HTE may be detected.MethodsFive unsupervised: Latent class analysis (LCA), K-means, partition around medoids, hierarchical, and spectral clustering; and four supervised algorithms: model-based recursive partitioning, Causal Forest (CF), and X-learner with Random Forest (XL-RF) and Bayesian Additive Regression Trees were individually applied to three prior ARDS RCTs. Clinical data and research protein biomarkers were used as partitioning variables, with the latter excluded for secondary analyses. For a clustering schema, HTE was evaluated based on the interaction term of treatment group and cluster with day-90 mortality as the dependent variable.FindingsNo single algorithm identified clusters with significant HTE in all three trials. LCA, XL-RF, and CF identified HTE most frequently (2/3 RCTs). Important partitioning variables in the unsupervised approaches were consistent across algorithms and RCTs. In supervised models, important partitioning variables varied between algorithms and across RCTs. In algorithms where clusters demonstrated HTE in the same trial, patients frequently interchanged clusters from treatment-benefit to treatment-harm clusters across algorithms. LCA aside, results from all other algorithms were subject to significant alteration in cluster composition and HTE with random seed change. Removing research biomarkers as partitioning variables greatly reduced the chances of detecting HTE across all algorithms.InterpretationMachine-learning algorithms were inconsistent in their abilities to identify clusters with significant HTE. Protein biomarkers were essential in identifying clusters with HTE. Investigations using machine-learning approaches to identify clusters to seek HTE require cautious interpretation.FundingNIGMS R35 GM142992 (PS), NHLBI R35 HL140026 (CSC); NIGMS R01 GM123193, Department of Defense W81XWH-21-1-0009, NIA R21 AG068720, NIDA R01 DA051464 (MMC).

Purpose Sepsis is a heterogeneous syndrome and identification of sub-phenotypes is essential. This study used trajectories of vital signs to develop and validate sub-phenotypes and investigated the interaction of sub-phenotypes with treatment using randomized controlled trial data. Methods All patients with suspected infection admitted to four academic hospitals in Emory Healthcare between 2014-2017 (training cohort) and 2018-2019 (validation cohort) were included. Group-based trajectory modeling was applied to vital signs from the first 8 h of hospitalization to develop and validate vitals trajectory sub-phenotypes. The associations between sub-phenotypes and outcomes were evaluated in patients with sepsis. The interaction between sub-phenotype and treatment with balanced crystalloids versus saline was tested in a secondary analysis of SMART (Isotonic Solutions and Major Adverse Renal Events Trial). Results There were 12,473 patients with suspected infection in training and 8256 patients in validation cohorts, and 4 vitals trajectory sub-phenotypes were found. Group A (N = 3483, 28%) were hyperthermic, tachycardic, tachypneic, and hypotensive. Group B (N = 1578, 13%) were hyperthermic, tachycardic, tachypneic (not as pronounced as Group A) and hypertensive. Groups C (N = 4044, 32%) and D (N = 3368, 27%) had lower temperatures, heart rates, and respiratory rates, with Group C normotensive and Group D hypotensive. In the 6,919 patients with sepsis, Groups A and B were younger while Groups C and D were older. Group A had the lowest prevalence of congestive heart failure, hypertension, diabetes mellitus, and chronic kidney disease, while Group B had the highest prevalence. Groups A and D had the highest vasopressor use (p < 0.001 for all analyses above). In logistic regression, 30-day mortality was significantly higher in Groups A and D (p < 0.001 and p = 0.03, respectively). In the SMART trial, sub-phenotype significantly modified treatment effect (p = 0.03). Group D had significantly lower odds of mortality with balanced crystalloids compared to saline (odds ratio (OR) 0.39, 95% confidence interval (CI) 0.23-0.67, p < 0.001). Conclusion Sepsis sub-phenotypes based on vital sign trajectory were consistent across cohorts, had distinct outcomes, and different responses to treatment with balanced crystalloids versus saline., Author(s): Sivasubramanium V. Bhavani [sup.1] [sup.2] [sup.10], Matthew Semler [sup.3], Edward T. Qian [sup.3], Philip A. Verhoef [sup.4] [sup.5], Chad Robichaux [sup.6], Matthew M. Churpek [sup.7] [sup.8], Craig M. Coopersmith [...]

Background: Identifying COPD patients at high risk for mortality or healthcare utilization remains a challenge. A robust system for identifying high-risk COPD patients using Electronic Health Record (EHR) data would empower targeting interventions aimed at ensuring guideline compliance and multimorbidity management. The purpose of this study was to empirically derive, validate, and characterize subgroups of COPD patients based on routinely collected clinical data widely available within the EHR. Methods: Cluster analysis was used in 5,006 patients with COPD at Intermountain to identify clusters based on a large collection of clinical variables. Recursive Partitioning (RP) was then used to determine a preferred tree that assigned patients to clusters based on a parsimonious variable subset. The mortality, COPD exacerbations, and comorbidity profile of the identified groups were examined. The findings were validated in an independent Intermountain cohort and in external cohorts from the United States Veterans Affairs (VA) and University of Chicago Medicine systems. Measurements and Main Results: The RP algorithm identified five LIVE Scores based on laboratory values: albumin, creatinine, chloride, potassium, and hemoglobin. The groups were characterized by increasing risk of mortality. The lowest risk, LIVE Score 5 had 8% 4-year mortality vs. 56% in the highest risk LIVE Score 1 (p < 0.001). These findings were validated in the VA cohort (n = 83,134), an expanded Intermountain cohort (n = 48,871) and in the University of Chicago system (n = 3,236). Higher mortality groups also had higher COPD exacerbation rates and comorbidity rates. Conclusions: In large clinical datasets across different organizations, the LIVE Score utilizes existing laboratory data for COPD patients, and may be used to stratify risk for mortality and COPD exacerbations.

Rationale: Although chronic obstructive pulmonary disease (COPD) exacerbation frequency is stable in research cohorts, whether severe COPD exacerbation frequency can be used to identify patients at high risk for future severe COPD exacerbations and/or mortality is unknown. Methods: Severe COPD exacerbation frequency stability was determined in 3 distinct clinical cohorts. A total of 17,450 patients with COPD in Intermountain Healthcare were categorized based on the number of severe COPD exacerbations per year. We determined whether exacerbation frequency was stable and whether it predicted mortality. These findings were validated in 83,134 patients from the U.S. Veterans Affairs (VA) nationwide health care system and 3326 patients from the University of Chicago Medicine health system. Results: In the Intermountain Healthcare cohort, the majority (84%, 14,706 patients) had no exacerbations in 2009 and were likely to remain non-exacerbators with a significantly lower 6-year mortality compared with frequent exacerbators (2 or more exacerbations per year) (25% versus 57%, p

Objective The timely stratification of trauma injury severity can enhance the quality of trauma care but it requires intense manual annotation from certified trauma coders. The objective of this study is to develop machine learning models for the stratification of trauma injury severity across various body regions using clinical text and structured electronic health records (EHRs) data. Materials and Methods Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create 2 machine learning models with different approaches to representing text. The first one fuses concept unique identifiers (CUIs) extracted from free text with structured EHR variables, while the second one integrates free text with structured EHR variables. Temporal validation was undertaken to ensure the models' temporal generalizability. Additionally, analyses to assess the variable importance were conducted. Results Both models demonstrated impressive performance in categorizing leg injuries, achieving high accuracy with macro-F1 scores of over 0.8. Additionally, they showed considerable accuracy, with macro-F1 scores exceeding or near 0.7, in assessing injuries in the areas of the chest and head. We showed in our variable importance analysis that the most important features in the model have strong face validity in determining clinically relevant trauma injuries. Discussion The CUI-based model achieves comparable performance, if not higher, compared to the free-text-based model, with reduced complexity. Furthermore, integrating structured EHR data improves performance, particularly when the text modalities are insufficiently indicative. Conclusions Our multi-modal, multiclass models can provide accurate stratification of trauma injury severity and clinically relevant interpretations. [ABSTRACT FROM AUTHOR]

Key Points: Question: Among critically ill adults, do the effects of peripheral oxygen-saturation (Spo2) targets on outcomes differ based on an individual's characteristics? Findings: A machine learning model derived in one randomized trial and validated in another found that the predicted effect of lower vs higher Spo2 targets ranged from a 27% absolute reduction to a 34% absolute increase in 28-day mortality and differed significantly based on an individual's characteristics. Meaning: The effect of oxygen-saturation targets on mortality varied by patients' individual characteristics. Importance: Among critically ill adults, randomized trials have not found oxygenation targets to affect outcomes overall. Whether the effects of oxygenation targets differ based on an individual's characteristics is unknown. Objective: To determine whether an individual's characteristics modify the effect of lower vs higher peripheral oxygenation-saturation (Spo2) targets on mortality. Design, Setting, and Participants: A machine learning model to predict the effect of treatment with a lower vs higher Spo2 target on mortality for individual patients was derived in the Pragmatic Investigation of Optimal Oxygen Targets (PILOT) trial and externally validated in the Intensive Care Unit Randomized Trial Comparing Two Approaches to Oxygen Therapy (ICU-ROX) trial. Critically ill adults received invasive mechanical ventilation in an intensive care unit (ICU) in the United States between July 2018 and August 2021 for PILOT (n = 1682) and in 21 ICUs in Australia and New Zealand between September 2015 and May 2018 for ICU-ROX (n = 965). Exposures: Randomization to a lower vs higher Spo2 target group. Main Outcome and Measure: 28-Day mortality. Results: In the ICU-ROX validation cohort, the predicted effect of treatment with a lower vs higher Spo2 target for individual patients ranged from a 27.2% absolute reduction to a 34.4% absolute increase in 28-day mortality. For example, patients predicted to benefit from a lower Spo2 target had a higher prevalence of acute brain injury, whereas patients predicted to benefit from a higher Spo2 target had a higher prevalence of sepsis and abnormally elevated vital signs. Patients predicted to benefit from a lower Spo2 target experienced lower mortality when randomized to the lower Spo2 group, whereas patients predicted to benefit from a higher Spo2 target experienced lower mortality when randomized to the higher Spo2 group (likelihood ratio test for effect modification P =.02). The use of a Spo2 target predicted to be best for each patient, instead of the randomized Spo2 target, would have reduced the absolute overall mortality by 6.4% (95% CI, 1.9%-10.9%). Conclusion and relevance: Oxygenation targets that are individualized using machine learning analyses of randomized trials may reduce mortality for critically ill adults. A prospective trial evaluating the use of individualized oxygenation targets is needed. This cohort study examines whether peripheral oxygenation-saturation targets on mortality would differ by individual patient characteristics among 2 temporally and geographically distinct randomized trials of lower vs higher Spo2 targets in critically ill patients receiving mechanical ventilation [ABSTRACT FROM AUTHOR]