Dataset Information

Comparison of time series clustering methods for identifying novel subphenotypes of patients with infection.

ABSTRACT:

Objective

Severe infection can lead to organ dysfunction and sepsis. Identifying subphenotypes of infected patients is essential for personalized management. It is unknown how different time series clustering algorithms compare in identifying these subphenotypes.

Materials and methods

Patients with suspected infection admitted between 2014 and 2019 to 4 hospitals in Emory healthcare were included, split into separate training and validation cohorts. Dynamic time warping (DTW) was applied to vital signs from the first 8 h of hospitalization, and hierarchical clustering (DTW-HC) and partition around medoids (DTW-PAM) were used to cluster patients into subphenotypes. DTW-HC, DTW-PAM, and a previously published group-based trajectory model (GBTM) were evaluated for agreement in subphenotype clusters, trajectory patterns, and subphenotype associations with clinical outcomes and treatment responses.

Results

There were 12 473 patients in training and 8256 patients in validation cohorts. DTW-HC, DTW-PAM, and GBTM models resulted in 4 consistent vitals trajectory patterns with significant agreement in clustering (71-80% agreement, P < .001): group A was hyperthermic, tachycardic, tachypneic, and hypotensive. Group B was hyperthermic, tachycardic, tachypneic, and hypertensive. Groups C and D had lower temperatures, heart rates, and respiratory rates, with group C normotensive and group D hypotensive. Group A had higher odds ratio of 30-day inpatient mortality (P < .01) and group D had significant mortality benefit from balanced crystalloids compared to saline (P < .01) in all 3 models.

Discussion

DTW- and GBTM-based clustering algorithms applied to vital signs in infected patients identified consistent subphenotypes with distinct clinical outcomes and treatment responses.

Conclusion

Time series clustering with distinct computational approaches demonstrate similar performance and significant agreement in the resulting subphenotypes.

SUBMITTER: Bhavani SV

PROVIDER: S-EPMC10198539 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of time series clustering methods for identifying novel subphenotypes of patients with infection.

Bhavani Sivasubramanium V SV Xiong Li L Pius Abish A Semler Matthew M Qian Edward T ET Verhoef Philip A PA Robichaux Chad C Coopersmith Craig M CM Churpek Matthew M MM

Journal of the American Medical Informatics Association : JAMIA 20230501 6

<h4>Objective</h4>Severe infection can lead to organ dysfunction and sepsis. Identifying subphenotypes of infected patients is essential for personalized management. It is unknown how different time series clustering algorithms compare in identifying these subphenotypes.<h4>Materials and methods</h4>Patients with suspected infection admitted between 2014 and 2019 to 4 hospitals in Emory healthcare were included, split into separate training and validation cohorts. Dynamic time warping (DTW) was ...[more]

PMID: 37043759

Similar Datasets

Project description:BackgroundBarth syndrome (BTHS) is a rare genetic disease that is characterized by cardiomyopathy, skeletal myopathy, neutropenia, and growth abnormalities and often leads to death in childhood. Recently, elamipretide has been tested as a potential first disease-modifying drug. This study aimed to identify patients with BTHS who may respond to elamipretide, based on continuous physiological measurements acquired through wearable devices.ResultsData from a randomized, double-blind, placebo-controlled crossover trial of 12 patients with BTHS were used, including physiological time series data measured using a wearable device (heart rate, respiratory rate, activity, and posture) and functional scores. The latter included the 6-minute walk test (6MWT), Patient-Reported Outcomes Measurement Information System (PROMIS) fatigue score, SWAY Balance Mobile Application score (SWAY balance score), BTHS Symptom Assessment (BTHS-SA) Total Fatigue score, muscle strength by handheld dynamometry, 5 times sit-and-stand test (5XSST), and monolysocardiolipin to cardiolipin ratio (MLCL:CL). Groups were created through median split of the functional scores into "highest score" and "lowest score", and "best response to elamipretide" and "worst response to elamipretide". Agglomerative hierarchical clustering (AHC) models were implemented to assess whether physiological data could classify patients according to functional status and distinguish non-responders from responders to elamipretide. AHC models clustered patients according to their functional status with accuracies of 60-93%, with the greatest accuracies for 6MWT (93%), PROMIS (87%), and SWAY balance score (80%). Another set of AHC models clustered patients with respect to their response to treatment with elamipretide with perfect accuracy (all 100%).ConclusionsIn this proof-of-concept study, we demonstrated that continuously acquired physiological measurements from wearable devices can be used to predict functional status and response to treatment among patients with BTHS.

Project description:While genome-wide gene expression data are generated at an increasing rate, the repertoire of approaches for pattern discovery in these data is still limited. Identifying subtle patterns of interest in large amounts of data (tens of thousands of profiles) associated with a certain level of noise remains a challenge. A microarray time series was recently generated to study the transcriptional program of the mouse segmentation clock, a biological oscillator associated with the periodic formation of the segments of the body axis. A method related to Fourier analysis, the Lomb-Scargle periodogram, was used to detect periodic profiles in the dataset, leading to the identification of a novel set of cyclic genes associated with the segmentation clock. Here, we applied to the same microarray time series dataset four distinct mathematical methods to identify significant patterns in gene expression profiles. These methods are called: Phase consistency, Address reduction, Cyclohedron test and Stable persistence, and are based on different conceptual frameworks that are either hypothesis- or data-driven. Some of the methods, unlike Fourier transforms, are not dependent on the assumption of periodicity of the pattern of interest. Remarkably, these methods identified blindly the expression profiles of known cyclic genes as the most significant patterns in the dataset. Many candidate genes predicted by more than one approach appeared to be true positive cyclic genes and will be of particular interest for future research. In addition, these methods predicted novel candidate cyclic genes that were consistent with previous biological knowledge and experimental validation in mouse embryos. Our results demonstrate the utility of these novel pattern detection strategies, notably for detection of periodic profiles, and suggest that combining several distinct mathematical approaches to analyze microarray datasets is a valuable strategy for identifying genes that exhibit novel, interesting transcriptional patterns.

Project description:BackgroundPreventive interventions with post-exposure prophylaxis (PEP) are needed in leprosy high-endemic areas to interrupt the transmission of Mycobacterium leprae. Program managers intend to use Geographic Information Systems (GIS) to target preventive interventions considering efficient use of public health resources. Statistical GIS analyses are commonly used to identify clusters of disease without accounting for the local context. Therefore, we propose a contextualized spatial approach that includes expert consultation to identify clusters and compare it with a standard statistical approach.Methodology/principal findingsWe included all leprosy patients registered from 2014 to 2020 at the Health Centers in Fatehpur and Chandauli districts, Uttar Pradesh State, India (n = 3,855). Our contextualized spatial approach included expert consultation determining criteria and definition for the identification of clusters using Density Based Spatial Clustering Algorithm with Noise, followed by creating cluster maps considering natural boundaries and the local context. We compared this approach with the commonly used Anselin Local Moran's I statistic to identify high-risk villages. In the contextualized approach, 374 clusters were identified in Chandauli and 512 in Fatehpur. In total, 75% and 57% of all cases were captured by the identified clusters in Chandauli and Fatehpur, respectively. If 100 individuals per case were targeted for PEP, 33% and 11% of the total cluster population would receive PEP, respectively. In the statistical approach, more clusters in Chandauli and fewer clusters in Fatehpur (508 and 193) and lower proportions of cases in clusters (66% and 43%) were identified, and lower proportions of population targeted for PEP was calculated compared to the contextualized approach (11% and 11%).ConclusionA contextualized spatial approach could identify clusters in high-endemic districts more precisely than a standard statistical approach. Therefore, it can be a useful alternative to detect preventive intervention targets in high-endemic areas.

Dataset Information

Comparison of time series clustering methods for identifying novel subphenotypes of patients with infection.

Objective

Materials and methods

Results

Discussion

Conclusion

Publications

Comparison of time series clustering methods for identifying novel subphenotypes of patients with infection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets