An official website of the United States government
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.
more »
« less
Clustering and classification of vertical movement profiles for ecological inference of behavior
Abstract Vertical movements can expose individuals to rapid changes in physical and trophic environments—for aquatic fauna, dive profiles from biotelemetry data can be used to quantify and categorize vertical movements. Inferences on classes of vertical movement profiles typically rely on subjective summaries of parameters or statistical clustering techniques that utilize Euclidean matching of vertical movement profiles with vertical observation points. These approaches are prone to subjectivity, error, and bias. We used machine learning approaches on a large dataset of vertical time series (N = 28,217 dives) for 31 post‐nesting leatherback turtles (Dermochelys coriacea). We applied dynamic time warp (DTW) clustering to group vertical movement (dive) time series by their metrics (depth and duration) into an optimal number of clusters. We then identified environmental covariates associated with each cluster using a generalized additive mixed‐effects model (GAMM). A convolutional neural network (CNN) model, trained on standard dive shape types from the literature, was used to classify dives within each DTW cluster by their shape. Two clusters were identified with the DTW approach—these varied in their spatial and temporal distributions, with dependence on environmental covariates, sea surface temperature, bathymetry, sea surface height anomaly, and time‐lagged surface chlorophyllaconcentrations. CNN classification accuracy of the five standard dive profiles was 95%. Subsequent analyses revealed that the two clusters differed in their composition of standard dive shapes, with each cluster dominated by shapes indicative of distinct behaviors (pelagic foraging and exploration, respectively). The use of these two machine learning approaches allowed for discrete behaviors to be identified from vertical time series data, first by clustering vertical movements by their movement metrics (DTW) and second by classifying dive profiles within each cluster by their shapes (CNN). Statistical inference for the identified clusters found distinct relationships with environmental covariates, supporting hypotheses of vertical niche switching and vertically structured foraging behavior. This approach could be similarly applied to the time series of other animals utilizing the vertical dimension in their movements, including aerial, arboreal, and other aquatic species, to efficiently identify different movement behaviors and inform habitat models.
more »
« less
- Award ID(s):
- 1915347
- PAR ID:
- 10443404
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Ecosphere
- Volume:
- 14
- Issue:
- 1
- ISSN:
- 2150-8925
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The data-driven characterization of discretionary lane-changing behaviors has traditionally been hindered by the scarcity of high-resolution data that can precisely record lateral movements. In this study, we conducted an exploratory investigation leveraging the Third Generation Simulation (TGSIM) dataset to advance our understanding of discretionary lane-changing behaviors. In this paper, we developed a discretionary lane-changing extraction pipeline and scrutinized crucial factors such as gaps and relative speeds in leading and following directions. A dynamic time warping (DTW) analysis was performed to quantify the difference between any pair of lane-changing behaviors, and an affinity propagation (AP) clustering, evaluated on normalized DTW distance, was conducted. Our results yielded five clusters based on lead and lag gaps, enabling us to categorize lane-changing behaviors into aggressive, neutral, and cautious for both leading and following directions. Clustering based on relative speeds revealed two distinct groups of lane-changing behaviors, one representing overtaking and the other indicative of transitioning into a lane with stable and homogenous speed. The proposed DTW analysis, in conjunction with AP clustering, demonstrated promising potential in categorizing and characterizing lane-changing behaviors. Additionally, this approach can be readily adapted to analyze any driving behavior.more » « less
-
Abstract Quantifying food intake in wild animals is crucial to many ecological and evolutionary questions, yet it can be very challenging, especially in the marine environment. Because foraging behavior can be inferred from dive recordings in many marine creatures, we hypothesized that specific behavioral dive variables can indicate food intake. To test this hypothesis, we attached time-depth recorders to breeding Adélie penguins also implanted with RFID tags that crossed a weighbridge as they traveled to and from the ocean to feed their chicks. The weighbridge reported how much mass the penguin had gained during a foraging trip. The variables that explained a significant amount of the change in body mass while at sea were the number of foraging dives per hour (46%) and the number of undulations per hour (12%). Most importantly, every increment of 1 in the rate of foraging dives per hour equated to a penguin gaining an average 170 g of mass, over the course of a 6–60 h foraging trip. These results add to a growing understanding that different metrics of foraging success are likely appropriate for different species, and that assessing the types and frequencies of dives using time-depth recorders can yield valuable insights.more » « less
-
Animals that display plasticity in behavioral, ecological, and morphological traits are better poised to cope with environmental disturbances. Here, we examined individual plasticity and intraspecific variation in the morphometrics, movement patterns, and dive behavior of an enigmatic apex predator, the leopard seal ( Hydrurga leptonyx ). Satellite/GPS tags and time-depth recorders were deployed on 22 leopard seals off the Western Antarctic Peninsula. Adult female leopard seals were significantly larger (454±59 kg) and longer (302±11 cm) than adult males (302±22 kg, 276±11 cm). As females were 50% larger than their male counterparts, leopard seals are therefore one of the most extreme examples of female-biased sexual size dimorphism in marine mammals. Female leopard seals also spent more time hauled-out on land and ice than males. In the austral spring/summer, three adult female leopard seals hauled-out on ice for 10+ days, which likely represent the first satellite tracks of parturition and lactation for the species. While we found sex-based differences in morphometrics and haul-out durations, other variables, including maximum distance traveled and dive parameters, did not vary by sex. Regardless of sex, some leopard seals remained in near-shore habitats, traveling less than 50 kilometers, while other leopard seals traveled up to 1,700 kilometers away from the tagging location. Overall, leopard seals were short (3.0±0.7 min) and shallow (29±8 m) divers. However, within this general pattern, some individual leopard seals primarily used short, shallow dives, while others switched between short, shallow dives and long, deep dives. We also recorded the single deepest and longest dive made by any leopard seal—1, 256 meters for 25 minutes. Together, our results showcased high plasticity among leopard seals tagged in a single location. These flexible behaviors and traits may offer leopard seals, an ice-associated apex predator, resilience to the rapidly changing Southern Ocean.more » « less
-
Birol, Inanc (Ed.)Abstract Motivation Gene clustering is a widely-used technique that has enabled computational prediction of unknown gene functions within a species. However, it remains a challenge to refine gene function prediction by leveraging evolutionarily conserved genes in another species. This challenge calls for a new computational algorithm to identify gene co-clusters in two species, so that genes in each co-cluster exhibit similar expression levels in each species and strong conservation between the species. Results Here we develop the bipartite tight spectral clustering (BiTSC) algorithm, which identifies gene co-clusters in two species based on gene orthology information and gene expression data. BiTSC novelly implements a formulation that encodes gene orthology as a bipartite network and gene expression data as node covariates. This formulation allows BiTSC to adopt and combine the advantages of multiple unsupervised learning techniques: kernel enhancement, bipartite spectral clustering, consensus clustering, tight clustering, and hierarchical clustering. As a result, BiTSC is a flexible and robust algorithm capable of identifying informative gene co-clusters without forcing all genes into co-clusters. Another advantage of BiTSC is that it does not rely on any distributional assumptions. Beyond cross-species gene co-clustering, BiTSC also has wide applications as a general algorithm for identifying tight node co-clusters in any bipartite network with node covariates. We demonstrate the accuracy and robustness of BiTSC through comprehensive simulation studies. In a real data example, we use BiTSC to identify conserved gene co-clusters of D. melanogaster and C. elegans, and we perform a series of downstream analysis to both validate BiTSC and verify the biological significance of the identified co-clusters. Availability and implementation The Python package BiTSC is open-access and available at https://github.com/edensunyidan/BiTSC.more » « less
