DADeveendra Amin

Deveendra Amin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Deveendra Amin has a total of 49 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multicenter Development and Prospective Validation of eCARTv5: A Gradient-Boosted Machine-Learning Early Warning Score

    by Matthew M. MD Churpek, Kyle A. Carey, Ashley Snyder, Christopher J Winslow, Emily Gilbert, Nirav S Shah, Brian W. Patterson, Majid Md Afshar, Alan Md Weiss, Devendra N. Amin, et al.

    BACKGROUND: Early detection of clinical deterioration using machine-learning early warning scores may improve outcomes. However, most implemented scores were developed using logistic regression, only underwent retrospective validation, and were not tested in important subgroups. OBJECTIVE: The objective of our multicenter retrospective and prospective observational study was to develop and prospectively validate a gradient-boosted machine model (eCARTv5) for identifying clinical deterioration on the wards. DERIVATION COHORT: All adult patients admitted to the inpatient medical-surgical wards at seven hospitals in three health systems for model development (2006–2022). VALIDATION COHORT: All adult patients admitted to the inpatient medical-surgical wards and at 21 hospitals from three health systems for retrospective (2009–2023) and prospective (2023–2024) external validation. PREDICTION MODEL: Predictor variables (demographics, vital signs, documentation, and laboratory values) were used in a gradient-boosted trees algorithm to predict ICU transfer or death in the next 24 hours. The developed model (eCARTv5) was compared with the Modified Early Warning Score (MEWS), the National Early Warning Score (NEWS), and eCARTv2 using the area under the receiver operating characteristic curve (AUROC). RESULTS: The development cohort included 901,491 admissions, the retrospective validation cohort included 1,769,461 admissions, and the prospective validation cohort included 205,946 admissions. In retrospective validation, eCARTv5 had the highest AUROC (0.834; 95% CI, 0.834–0.835), followed by eCARTv2 (0.775 [95% CI, 0.775–0.776]), NEWS (0.766 [95% CI, 0.766–0.767]), and MEWS (0.704 [95% CI, 0.703–0.704]). eCARTv5’s performance remained high (AUROC ≥0.80) across a range of patient demographics, clinical conditions, and during prospective validation. CONCLUSION: We developed eCARTv5, which performed better than eCARTv2, NEWS, and MEWS retrospectively, prospectively, and across a range of subgroups. These results served as the foundation for Food and Drug Administration clearance for its use in identifying deterioration in hospitalized ward patients.


  • Development and Validation of a Machine Learning COVID-19 Veteran (COVet) Deterioration Risk Score

    by Sushant Md Govindan, Alexandra Spicer, Matthew Mps Bearce, Richard S. Schaefer, Andrea Ba Uhl, Gil Alterovitz, Michael J. Kim, Kyle A. Carey, Nirav S. Shah, Christopher Winslow, et al.

    BACKGROUND AND OBJECTIVE: To develop the COVid Veteran (COVet) score for clinical deterioration in Veterans hospitalized with COVID-19 and further validate this model in both Veteran and non-Veteran samples. No such score has been derived and validated while incorporating a Veteran sample. DERIVATION COHORT: Adults (age ≥ 18 yr) hospitalized outside the ICU with a diagnosis of COVID-19 for model development to the Veterans Health Administration (VHA) (n = 80 hospitals). VALIDATION COHORT: External validation occurred in a VHA cohort of 34 hospitals, as well as six non-Veteran health systems for further external validation (n = 21 hospitals) between 2020 and 2023. PREDICTION MODEL: eXtreme Gradient Boosting machine learning methods were used, and performance was assessed using the area under the receiver operating characteristic curve and compared with the National Early Warning Score (NEWS). The primary outcome was transfer to the ICU or death within 24 hours of each new variable observation. Model predictor variables included demographics, vital signs, structured flowsheet data, and laboratory values. RESULTS: A total of 96,908 admissions occurred during the study period, of which 59,897 were in the Veteran sample and 37,011 were in the non-Veteran sample. During external validation in the Veteran sample, the model demonstrated excellent discrimination, with an area under the receiver operating characteristic curve of 0.88. This was significantly higher than NEWS (0.79; p < 0.01). In the non-Veteran sample, the model also demonstrated excellent discrimination (0.86 vs. 0.79 for NEWS; p < 0.01). The top three variables of importance were eosinophil percentage, mean oxygen saturation in the prior 24-hour period, and worst mental status in the prior 24-hour period. CONCLUSIONS: We used machine learning methods to develop and validate a highly accurate early warning score in both Veterans and non-Veterans hospitalized with COVID-19. The model could lead to earlier identification and therapy, which may improve outcomes.


  • Open Access

    The early identification of disease progression in patients with suspected infection presenting to the emergency department: a multi-centre derivation and validation study

    by Kordo Saeed, Darius Cameron Wilson, Frank Bloos, Philipp Schuetz, Yuri van der Does, Olle Melander, Pierre Hausfater, Jacopo M. Legramante, Yann-Erick Claessens, Deveendra Amin, et al.

    There is a lack of validated tools to assess potential disease progression and hospitalisation decisions in patients presenting to the emergency department (ED) with a suspected infection. This study aimed to identify suitable blood biomarkers (MR-proADM, PCT, lactate and CRP) or clinical scores (SIRS, SOFA, qSOFA, NEWS and CRB-65) to fulfil this unmet clinical need. An observational derivation patient cohort validated by an independent secondary analysis across nine EDs. Logistic and Cox regression, area under the receiver operating characteristic (AUROC) and Kaplan-Meier curves were used to assess performance. Disease progression was identified using a composite endpoint of 28-day mortality, ICU admission and hospitalisation > 10 days. One thousand one hundred seventy-five derivation and 896 validation patients were analysed with respective 28-day mortality rates of 7.1% and 5.0%, and hospitalisation rates of 77.9% and 76.2%. MR-proADM showed greatest accuracy in predicting 28-day mortality and hospitalisation requirement across both cohorts. Patient subgroups with high MR-proADM concentrations (≥ 1.54 nmol/L) and low biomarker (PCT < 0.25 ng/mL, lactate < 2.0 mmol/L or CRP < 67 mg/L) or clinical score (SOFA < 2 points, qSOFA < 2 points, NEWS < 4 points or CRB-65 < 2 points) values were characterised by a significantly longer length of hospitalisation (p < 0.001), rate of ICU admission (p < 0.001), elevated mortality risk (e.g. SOFA, qSOFA and NEWS HR [95%CI], 45.5 [10.0–207.6], 23.4 [11.1–49.3] and 32.6 [9.4–113.6], respectively) and a greater number of disease progression events (p < 0.001), compared to similar subgroups with low MR-proADM concentrations (< 1.54 nmol/L). Increased out-patient treatment across both cohorts could be facilitated using a derivation-derived MR-proADM cut-off of < 0.87 nmol/L (15.0% and 16.6%), with decreased readmission rates and no mortalities. In patients presenting to the ED with a suspected infection, the blood biomarker MR-proADM could most accurately identify the likelihood of further disease progression. Incorporation into an early sepsis management protocol may therefore aid rapid decision-making in order to either initiate, escalate or intensify early treatment strategies, or identify patients suitable for safe out-patient treatment.