Using Trajectories of Bedside Vital Signs to Identify COVID-19 Subphenotypes

BACKGROUND

Trajectories of bedside vital signs have been used to identify sepsis subphenotypes with distinct outcomes and treatment responses. The objective of this study was to validate the vitals trajectory model in a multicenter cohort of patients hospitalized with COVID-19 and to evaluate the clinical characteristics and outcomes of the resulting subphenotypes.

RESEARCH QUESTION

Can the trajectory of routine bedside vital signs identify COVID-19 subphenotypes with distinct clinical characteristics and outcomes?

STUDY DESIGN AND METHODS

The study included adult patients admitted with COVID-19 to four academic hospitals in the Emory Healthcare system between March 1, 2020, and May 31, 2022. Using a validated group-based trajectory model, we classified patients into previously defined vital sign trajectories using oral temperature, heart rate, respiratory rate, and systolic and diastolic BP measured in the first 8 h of hospitalization. Clinical characteristics, biomarkers, and outcomes were compared between subphenotypes. Heterogeneity of treatment effect to tocilizumab was evaluated.

RESULTS

The 7,065 patients with hospitalized COVID-19 were classified into four subphenotypes: group A (n = 1,429, 20%)-high temperature, heart rate, respiratory rate, and hypotensive; group B (1,454, 21%)-high temperature, heart rate, respiratory rate, and hypertensive; group C (2,996, 42%)-low temperature, heart rate, respiratory rate, and normotensive; and group D (1,186, 17%)-low temperature, heart rate, respiratory rate, and hypotensive. Groups A and D had higher ORs of mechanical ventilation, vasopressors, and 30-day inpatient mortality (P < .001). On comparing patients receiving tocilizumab (n = 55) with those who met criteria for tocilizumab but were admitted before its use (n = 461), there was significant heterogeneity of treatment effect across subphenotypes in the association of tocilizumab with 30-day mortality (P = .001).

INTERPRETATION

By using bedside vital signs available in even low-resource settings, we found novel subphenotypes associated with distinct manifestations of COVID-19, which could lead to preemptive and targeted treatments.

HIRA: Heart Rate Interval based Rapid Alert score to characterize autonomic dysfunction among patients with sepsis-related acute respiratory failure (ARF)

Objective. To examine whether heart rate interval based rapid alert (HIRA) score derived from a combination model of heart rate variability (HRV) and modified early warning score (MEWS) is a surrogate for the detection of acute respiratory failure (ARF) in critically ill sepsis patients.Approach. Retrospective HRV analysis of sepsis patients admitted to Emory healthcare intensive care unit (ICU) was performed between sepsis-related ARF and sepsis controls without ARF. HRV measures such as time domain, frequency domain, and nonlinear measures were analyzed up to 24 h after patient admission, 1 h before the onset of ARF, and a random event time in the sepsis controls. Statistical significance was computed by the Wilcoxon Rank Sum test. Machine learning algorithms such as eXtreme Gradient Boosting and logistic regression were developed to validate the HIRA score model. The performance of HIRA and early warning score models were evaluated using the area under the receiver operating characteristic (AUROC).Main Results. A total of 89 (ICU) patients with sepsis were included in this retrospective cohort study, of whom 31 (34%) developed sepsis-related ARF and 58 (65%) were sepsis controls without ARF. Time-domain HRV for Electrocardiogram (ECG) Beat-to-Beat RR intervals strongly distinguished ARF patients from controls. HRV measures for nonlinear and frequency domains were significantly altered (p< 0.05) among ARF compared to controls. The HIRA score AUC: 0.93; 95% confidence interval (CI): 0.88-0.98) showed a higher predictive ability to detect ARF when compared to MEWS (AUC: 0.71; 95% CI: 0.50-0.90).Significance. HRV was significantly impaired across patients who developed ARF when compared to controls. The HIRA score uses non-invasively derived HRV and may be used to inform diagnostic and therapeutic decisions regarding the severity of sepsis and earlier identification of the need for mechanical ventilation.

Leveraging Data Science and Novel Technologies to Develop and Implement Precision Medicine Strategies in Critical Care

Precision medicine aims to identify treatments that are most likely to result in favorable outcomes for subgroups of patients with similar clinical and biological characteristics. The gaps for the development and implementation of precision medicine strategies in the critical care setting are many, but the advent of data science and multi-omics approaches, combined with the rich data ecosystem in the intensive care unit, offer unprecedented opportunities to realize the promise of precision critical care. In this article, the authors review the data-driven and technology-based approaches being leveraged to discover and implement precision medicine strategies in the critical care setting.

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

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.

Temperature Trajectory Subphenotypes in Oncology Patients with Neutropenia and Suspected Infection

Rationale: Despite etiologic and severity heterogeneity in neutropenic sepsis, management is often uniform. Understanding host response clinical subphenotypes might inform treatment strategies for neutropenic sepsis. Objectives: In this retrospective two-hospital study, we analyzed whether temperature trajectory modeling could identify distinct, clinically relevant subphenotypes among oncology patients with neutropenia and suspected infection. Methods: Among adult oncologic admissions with neutropenia and blood cultures within 24 hours, a previously validated model classified patients' initial 72-hour temperature trajectories into one of four subphenotypes. We analyzed subphenotypes' independent relationships with hospital mortality and bloodstream infection using multivariable models. Measurements and Main Results: Patients (primary cohort n = 1,145, validation cohort n = 6,564) fit into one of four temperature subphenotypes. "Hyperthermic slow resolvers" (pooled n = 1,140 [14.8%], mortality n = 104 [9.1%]) and "hypothermic" encounters (n = 1,612 [20.9%], mortality n = 138 [8.6%]) had higher mortality than "hyperthermic fast resolvers" (n = 1,314 [17.0%], mortality n = 47 [3.6%]) and "normothermic" (n = 3,643 [47.3%], mortality n = 196 [5.4%]) encounters (P < 0.001). Bloodstream infections were more common among hyperthermic slow resolvers (n = 248 [21.8%]) and hyperthermic fast resolvers (n = 240 [18.3%]) than among hypothermic (n = 188 [11.7%]) or normothermic (n = 418 [11.5%]) encounters (P < 0.001). Adjusted for confounders, hyperthermic slow resolvers had increased adjusted odds for mortality (primary cohort odds ratio, 1.91 [P = 0.03]; validation cohort odds ratio, 2.19 [P < 0.001]) and bloodstream infection (primary odds ratio, 1.54 [P = 0.04]; validation cohort odds ratio, 2.15 [P < 0.001]). Conclusions: Temperature trajectory subphenotypes were independently associated with important outcomes among hospitalized patients with neutropenia in two independent cohorts.

Development and validation of novel sepsis subphenotypes using trajectories of vital signs

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.

Hospital trajectories and early predictors of clinical outcomes differ between SARS-CoV-2 and influenza pneumonia

BACKGROUND

A comparison of pneumonias due to SARS-CoV-2 and influenza, in terms of clinical course and predictors of outcomes, might inform prognosis and resource management. We aimed to compare clinical course and outcome predictors in SARS-CoV-2 and influenza pneumonia using multi-state modelling and supervised machine learning on clinical data among hospitalised patients.

METHODS

This multicenter retrospective cohort study of patients hospitalised with SARS-CoV-2 (March-December 2020) or influenza (Jan 2015-March 2020) pneumonia had the composite of hospital mortality and hospice discharge as the primary outcome. Multi-state models compared differences in oxygenation/ventilatory utilisation between pneumonias longitudinally throughout hospitalisation. Differences in predictors of outcome were modelled using supervised machine learning classifiers.

FINDINGS

Among 2,529 hospitalisations with SARS-CoV-2 and 2,256 with influenza pneumonia, the primary outcome occurred in 21% and 9%, respectively. Multi-state models differentiated oxygen requirement progression between viruses, with SARS-CoV-2 manifesting rapidly-escalating early hypoxemia. Highly contributory classifier variables for the primary outcome differed substantially between viruses.

INTERPRETATION

SARS-CoV-2 and influenza pneumonia differ in presentation, hospital course, and outcome predictors. These pathogen-specific differential responses in viral pneumonias suggest distinct management approaches should be investigated.

FUNDING

This project was supported by NIH/NCATS UL1 TR002345, NIH/NCATS KL2 TR002346 (PGL), the Doris Duke Charitable Foundation grant 2015215 (PGL), NIH/NHLBI R35 HL140026 (CSC), and a Big Ideas Award from the BJC HealthCare and Washington University School of Medicine Healthcare Innovation Lab and NIH/NIGMS R35 GM142992 (PS).

Identifying infected patients using semi-supervised and transfer learning

Objectives

Early identification of infection improves outcomes, but developing models for early identification requires determining infection status with manual chart review, limiting sample size. Therefore, we aimed to compare semi-supervised and transfer learning algorithms with algorithms based solely on manual chart review for identifying infection in hospitalized patients.

Materials and Methods

This multicenter retrospective study of admissions to 6 hospitals included “gold-standard” labels of infection from manual chart review and “silver-standard” labels from nonchart-reviewed patients using the Sepsis-3 infection criteria based on antibiotic and culture orders. “Gold-standard” labeled admissions were randomly allocated to training (70%) and testing (30%) datasets. Using patient characteristics, vital signs, and laboratory data from the first 24 hours of admission, we derived deep learning and non-deep learning models using transfer learning and semi-supervised methods. Performance was compared in the gold-standard test set using discrimination and calibration metrics.

Results

The study comprised 432 965 admissions, of which 2724 underwent chart review. In the test set, deep learning and non-deep learning approaches had similar discrimination (area under the receiver operating characteristic curve of 0.82). Semi-supervised and transfer learning approaches did not improve discrimination over models fit using only silver- or gold-standard data. Transfer learning had the best calibration (unreliability index P value: .997, Brier score: 0.173), followed by self-learning gradient boosted machine (P value: .67, Brier score: 0.170).

Discussion

Deep learning and non-deep learning models performed similarly for identifying infection, as did models developed using Sepsis-3 and manual chart review labels.

Conclusion

In a multicenter study of almost 3000 chart-reviewed patients, semi-supervised and transfer learning models showed similar performance for model discrimination as baseline XGBoost, while transfer learning improved calibration.

Factors Associated with Diagnostic Accuracy of Robotic Bronchoscopy with 12-month Follow-up

BACKGROUND

Robotic Bronchoscopy (RB) aims to increase the diagnostic yield of guided bronchoscopy by providing improved navigation, farther reach, and stability during lesion sampling.

METHODS

We reviewed data on consecutive cases in which robotic bronchoscopy was used to diagnose lung lesions from June 15^th, 2018 to December 15^th, 2019 at the University of Chicago Medical Center.

RESULTS

The median lesion size was 20.5 mm. All patients had at least 12 months of follow-up. The overall diagnostic accuracy was 77% (95/124). The diagnostic accuracy was 85%, 84% and 38% for concentric, eccentric and absent r-EBUS views, respectively (p < 0.001). A positive r-EBUS view and lesions size of 20-30 mm had higher odds of achieving a diagnosis on multivariate analysis. The 12-month diagnostic accuracy, sensitivity, specificity, positive and negative predictive value for malignancy was 77%, 69%, 100%, 100% and 58%, respectively. Pneumothorax was noted in 1.6% (2) cases with bleeding reported in 3.2% (4) cases. No post-procedure respiratory failure was noted.

CONCLUSIONS

The overall diagnostic accuracy using RB for pulmonary lesion sampling in our cohort with 12-month follow-up compared favorably to established guided bronchoscopy technologies. Lesion size ≥20 mm and confirmation by r-EBUS predicted higher accuracy independent of concentric or eccentric r-EBUS patterns.

Longitudinal respiratory subphenotypes in patients with COVID-19-related acute respiratory distress syndrome: results from three observational cohorts

BACKGROUND

Patients with COVID-19-related acute respiratory distress syndrome (ARDS) have been postulated to present with distinct respiratory subphenotypes. However, most phenotyping schema have been limited by sample size, disregard for temporal dynamics, and insufficient validation. We aimed to identify respiratory subphenotypes of COVID-19-related ARDS using unbiased data-driven approaches.

METHODS

PRoVENT-COVID was an investigator-initiated, national, multicentre, prospective, observational cohort study at 22 intensive care units (ICUs) in the Netherlands. Consecutive patients who had received invasive mechanical ventilation for COVID-19 (aged 18 years or older) served as the derivation cohort, and similar patients from two ICUs in the USA served as the replication cohorts. COVID-19 was confirmed by positive RT-PCR. We used latent class analysis to identify subphenotypes using clinically available respiratory data cross-sectionally at baseline, and longitudinally using 8-hourly data from the first 4 days of invasive ventilation. We used group-based trajectory modelling to evaluate trajectories of individual variables and to facilitate potential clinical translation. The PRoVENT-COVID study is registered with ClinicalTrials.gov, NCT04346342.

FINDINGS

Between March 1, 2020, and May 15, 2020, 1007 patients were admitted to participating ICUs in the Netherlands, and included in the derivation cohort. Data for 288 patients were included in replication cohort 1 and 326 in replication cohort 2. Cross-sectional latent class analysis did not identify any underlying subphenotypes. Longitudinal latent class analysis identified two distinct subphenotypes. Subphenotype 2 was characterised by higher mechanical power, minute ventilation, and ventilatory ratio over the first 4 days of invasive mechanical ventilation than subphenotype 1, but PaO₂/FiO₂, pH, and compliance of the respiratory system did not differ between the two subphenotypes. 185 (28%) of 671 patients with subphenotype 1 and 109 (32%) of 336 patients with subphenotype 2 had died at day 28 (p=0·10). However, patients with subphenotype 2 had fewer ventilator-free days at day 28 (median 0, IQR 0-15 vs 5, 0-17; p=0·016) and more frequent venous thrombotic events (109 [32%] of 336 patients vs 176 [26%] of 671 patients; p=0·048) compared with subphenotype 1. Group-based trajectory modelling revealed trajectories of ventilatory ratio and mechanical power with similar dynamics to those observed in latent class analysis-derived trajectory subphenotypes. The two trajectories were: a stable value for ventilatory ratio or mechanical power over the first 4 days of invasive mechanical ventilation (trajectory A) or an upward trajectory (trajectory B). However, upward trajectories were better independent prognosticators for 28-day mortality (OR 1·64, 95% CI 1·17-2·29 for ventilatory ratio; 1·82, 1·24-2·66 for mechanical power). The association between upward ventilatory ratio trajectories (trajectory B) and 28-day mortality was confirmed in the replication cohorts (OR 4·65, 95% CI 1·87-11·6 for ventilatory ratio in replication cohort 1; 1·89, 1·05-3·37 for ventilatory ratio in replication cohort 2).

INTERPRETATION

At baseline, COVID-19-related ARDS has no consistent respiratory subphenotype. Patients diverged from a fairly homogenous to a more heterogeneous population, with trajectories of ventilatory ratio and mechanical power being the most discriminatory. Modelling these parameters alone provided prognostic value for duration of mechanical ventilation and mortality.

FUNDING

Amsterdam UMC.

Temperature Trajectory Subphenotypes Correlate With Immune Responses in Patients With Sepsis

OBJECTIVES

We recently found that distinct body temperature trajectories of infected patients correlated with survival. Understanding the relationship between the temperature trajectories and the host immune response to infection could allow us to immunophenotype patients at the bedside using temperature. The objective was to identify whether temperature trajectories have consistent associations with specific cytokine responses in two distinct cohorts of infected patients.

DESIGN

Prospective observational study.

SETTING

Large academic medical center between 2013 and 2019.

SUBJECTS

Two cohorts of infected patients: 1) patients in the ICU with septic shock and 2) hospitalized patients with Staphylococcus aureus bacteremia.

INTERVENTIONS

Clinical data (including body temperature) and plasma cytokine concentrations were measured. Patients were classified into four temperature trajectory subphenotypes using their temperature measurements in the first 72 hours from the onset of infection. Log-transformed cytokine levels were standardized to the mean and compared with the subphenotypes in both cohorts.

MEASUREMENTS AND MAIN RESULTS

The cohorts consisted of 120 patients with septic shock (cohort 1) and 88 patients with S. aureus bacteremia (cohort 2). Patients from both cohorts were classified into one of four previously validated temperature subphenotypes: "hyperthermic, slow resolvers" (n = 19 cohort 1; n = 13 cohort 2), "hyperthermic, fast resolvers" (n = 18 C1; n = 24 C2), "normothermic" (n = 54 C1; n = 31 C2), and "hypothermic" (n = 29 C1; n = 20 C2). Both "hyperthermic, slow resolvers" and "hyperthermic, fast resolvers" had high levels of G-CSF, CCL2, and interleukin-10 compared with the "hypothermic" group when controlling for cohort and timing of cytokine measurement (p < 0.05). In contrast to the "hyperthermic, slow resolvers," the "hyperthermic, fast resolvers" showed significant decreases in the levels of several cytokines over a 24-hour period, including interleukin-1RA, interleukin-6, interleukin-8, G-CSF, and M-CSF (p < 0.001).

CONCLUSIONS

Temperature trajectory subphenotypes are associated with consistent cytokine profiles in two distinct cohorts of infected patients. These subphenotypes could play a role in the bedside identification of cytokine profiles in patients with sepsis.

Thoracic ultrasound as a predictor of pleurodesis success at the time of indwelling pleural catheter removal

BACKGROUND AND OBJECTIVE

IPC in patients with MPE are removed within 3 months in 30-58% of cases, usually due to decreased pleural fluid output as a result of pleurodesis. Disease control can also account for the lack of fluid output, potentially explaining why 4-14% of patients undergo repeat pleural intervention for fluid re-accumulation (at the time of disease recurrence or progression). The aim of our pilot study is to determine the accuracy of thoracic ultrasound (TUS) in predicting pleurodesis success in patients with MPE at the time of IPC removal.

METHODS

This is a single-centre, prospective observational cohort study that enrolled consecutive patients with confirmed MPE treated with IPC at the time of IPC removal. TUS was performed to calculate a PAS. Patients were followed up for a minimum of 3 months. Failure was defined as pleural fluid recurrence within 3 months.

RESULTS

Twenty-seven patients were screened and 25 were included in the final analysis. Pleurodesis success was observed in 88% (n = 22) and failure in 12% (n = 3) of patients. The mean PAS was higher in patients with pleurodesis success (22.0 vs 9.3, P = 0.01). A PAS greater than 10 predicted pleurodesis success with a sensitivity of 100% and specificity of 86%.

CONCLUSION

This pilot study suggests that TUS at the time of IPC removal accurately identifies patients who have achieved pleurodesis and therefore will not have re-accumulation of pleural effusion or require an ipsilateral pleural intervention for at least 3 months post-IPC removal.

Robot-assisted bronchoscopy for pulmonary lesion diagnosis: results from the initial multicenter experience

Background

The Robotic Endoscopic System (Auris Health, Inc., Redwood City, CA) has the potential to overcome several limitations of contemporary guided-bronchoscopic technologies for the diagnosis of lung lesions. Our objective is to report on the initial post-marketing feasibility, safety and diagnostic yield of this technology.

Methods

We retrospectively reviewed data on consecutive cases in which robot-assisted bronchoscopy was used to sample lung lesions at four centers in the US (academic and community) from June 15th, 2018 to December 15th, 2018.

Results

One hundred and sixty-seven lesions in 165 patients were included in the analysis, with an average follow-up of 185 ± 55 days. The average size of target lesions was 25.0 ± 15.0 mm. Seventy-one percent were located in the peripheral third of the lung. Pneumothorax and airway bleeding occurred in 3.6 and 2.4% cases, respectively. Navigation was successful in 88.6% of cases. Tissue samples were successfully obtained in 98.8%. The diagnostic yield estimates ranged from 69.1 to 77% assuming the cases of biopsy-proven inflammation without any follow-up information (N = 13) were non-diagnostic and diagnostic, respectively. The yield was 81.5, 71.7 and 26.9% for concentric, eccentric and absent r-EBUS views, respectively. Diagnostic yield was not affected by lesion size, density, lobar location or centrality.

Conclusions

RAB implementation in community and academic centers is safe and feasible, with an initial diagnostic yield of 69.1–77% in patients with lung lesions that require diagnostic bronchoscopy. Comparative trials with the existing bronchoscopic technologies are needed to determine cost-effectiveness of this technology.

Identifying Novel Sepsis Subphenotypes Using Temperature Trajectories

Rationale: Sepsis is a heterogeneous syndrome, and identifying clinically relevant subphenotypes is essential.Objectives: To identify novel subphenotypes in hospitalized patients with infection using longitudinal temperature trajectories.Methods: In the model development cohort, inpatient admissions meeting criteria for infection in the emergency department and receiving antibiotics within 24 hours of presentation were included. Temperature measurements within the first 72 hours were compared between survivors and nonsurvivors. Group-based trajectory modeling was performed to identify temperature trajectory groups, and patient characteristics and outcomes were compared between the groups. The model was then externally validated at a second hospital using the same inclusion criteria.Measurements and Main Results: A total of 12,413 admissions were included in the development cohort, and 19,053 were included in the validation cohort. In the development cohort, four temperature trajectory groups were identified: "hyperthermic, slow resolvers" (n = 1,855; 14.9% of the cohort); "hyperthermic, fast resolvers" (n = 2,877; 23.2%); "normothermic" (n = 4,067; 32.8%); and "hypothermic" (n = 3,614; 29.1%). The hypothermic subjects were the oldest and had the most comorbidities, the lowest levels of inflammatory markers, and the highest in-hospital mortality rate (9.5%). The hyperthermic, slow resolvers were the youngest and had the fewest comorbidities, the highest levels of inflammatory markers, and a mortality rate of 5.1%. The hyperthermic, fast resolvers had the lowest mortality rate (2.9%). Similar trajectory groups, patient characteristics, and outcomes were found in the validation cohort.Conclusions: We identified and validated four novel subphenotypes of patients with infection, with significant variability in inflammatory markers and outcomes.