JEJoshua Emakhu

Joshua Emakhu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Joshua Emakhu has a total of 30 co-authors. Here are the top co-authors by number of shared publications:

  • Joseph Miller

    Department of Emergency Medicine, Henry Ford Health + Michigan State University Health Sciences, Detroit, MI, USA

    3 shared publications
  • Christiana David

    Department of Obstetrics and Gynecology, NYC Health + Hospitals South Brooklyn Health, Brooklyn, USA

    2 shared publications
  • Egbe-Etu Etu

    Department of Marketing and Business Analytics, San Jose State University, San Jose, CA, USA

    2 shared publications
  • Imokhai Tenebe

    Booth School of Business, University of Chicago, Chicago, IL, USA

    2 shared publications
  • Sara Masoud

    Department of Industrial and Systems Engineering, Wayne State University, Detroit, MI, USA

    2 shared publications
  • Andrew Bossick

    Department of Public Health Sciences, Henry Ford Health, Detroit, USA

    1 shared publication

Latest Publications

  • Open Access

    Circadian troponin dynamics reveal sex-specific signals for acute coronary syndrome evaluation

    by Joshua Emakhu, Sana Soman, Kegham Hawatian, Jasreen Gill, Bernard Cook, James McCord, Joseph Miller

    High-sensitivity cardiac troponin (hs-cTn) exhibits circadian variation, yet whether these variations differ by sex and influence early risk stratification for suspected acute coronary syndrome (ACS) is uncertain. We performed a secondary analysis of the RACE-IT stepped-wedge randomized trial across nine Michigan emergency departments (July 2020–April 2021). From the 32,609 patients in the primary trial, we analyzed those with available hs-cTnI values, time-stamped, that fell within the indeterminate range (4–18 ng/L) and were performed with the Beckman Coulter assay. We performed cosinor regression models to evaluate diurnal variation and multivariable logistic regression to analyze the association with 30-day major adverse cardiac events (MACE) after adjusting for cardiovascular risk factors. Median age was 57 years; 42% were men. Men showed a higher Midline Estimating Statistic of Rhythm (MESOR) hs-cTnI (6.3 ng/L vs 5.5 ng/L; p < 0.001) and greater diurnal amplitude ( β = 0.21 vs 0.13; p < 0.001). Peak concentrations occurred at 6:06 AM in both sexes. In multivariable analysis, male sex (adjusted odds ratio [aOR] 2.37, 95% CI 1.68–3.34) and earlier presentation time (per 6-h interval closer to midnight: aOR 0.65, 95% CI 0.54–0.79) independently predicted 30-day MACE. Each 1 ng/L increase in hs-cTnI conferred a 7% higher MACE risk (OR 1.07, 95% CI 1.03–1.12). hs-cTnI exhibits sex-specific circadian patterns with independent prognostic significance. These findings support the potential for time- and sex-adjusted hs-cTnI thresholds to improve early risk stratification in emergency care.

  • Open Access

    Disparities in emergency department outcomes by race during the 2022–2023 COVID-influenza twindemic

    by Joshua Emakhu, Christiana David, Egbe-Etu Etu, Sara Masoud, Imokhai Tenebe, Jordan Larot, Kindness Etu, Satheesh Gunaga, Joseph Miller

    The 2022–2023 “twindemic” of COVID-19 and influenza has worsened emergency department (ED) overcrowding, revealing racial/ethnic disparities in emergency care. This study assessed racial differences in ED operational outcomes—specifically, discharge ED length of stay (LOS), boarding time among admitted patients, and left without being seen (LWBS) rates—and characterized disparities concentrated in the upper tails of delay distributions. This retrospective observational study included adult ED encounters with respiratory presentations and/or laboratory-confirmed COVID-19 or influenza across 10 EDs in Michigan between September 2022 and December 2023. The primary outcomes were ED LOS at discharge, boarding of admitted patients, and LWBS. Models adjusted for covariates and ED site (fixed effects) with site-clustered standard errors; for time outcomes, log-minutes (back-transformed). Tail burden was defined as exceeding the pooled 75th percentile and the upper Tukey fence. Multiple imputations (m = 20) were used to address missing data. Of the 6,476 encounters, the unadjusted median LOS to discharge was 193.0 min (mins) (Black), 177.0 min (White), and 172.0 min (‘Other’). Adjusted differences from White were − 1.8 min (95% CI, − 9.5 to 6.2) for Black and + 1.9 min (− 6.5 to 10.6) for ‘Other’; the boarding differences were + 33.8 min (− 16.5 to 91.8) and + 58.1 min (− 26.1 to 164.4), respectively. The LWBS rate was 5.7% (Black) vs. 2.3% (White); the adjusted odds ratio was 0.98 (0.57–1.68) and 0.79 (0.64–1.00) after imputation (AUC 0.81). Median-based metrics obscured disparities in the upper tail of the institutions’ ED delays, specifically boarding time. Tail-aware metrics could augment standard dashboards by flagging uneven exposure to prolonged delays to drive equity-minded operational improvements. The online version contains supplementary material available at 10.1186/s12873-026-01508-9.

  • Open Access

    Racial and sex differences in acute pericarditis among emergency department chest pain patients: a retrospective cohort study

    by Joshua Emakhu, Wan-Ting Su, Jamie Joseph, Indra Adrianto, Christiana David, Egbe-Etu Etu, Imokhai Tenebe, Andrew Bossick, Joseph Miller

    Acute pericarditis is a rare diagnosis among emergency department (ED) patients with chest pain, and how race and sex jointly influence risk remains poorly


  • Open Access

    Machine learning for dissolved oxygen prediction in the Manawatu River catchment, New Zealand

    by Imokhai T. Tenebe, Eunice O. Babatunde, Nkpa M. Ogarekpe, Egbe-Etu Etu, Joshua Emakhu, Kindness E. Etu, Obiora B. Ezeudu, Oluwarotimi S. Oladele

    Uncontrolled anthropogenic activities have increased river pollution, resulting in poor water quality and a growing need for continuous monitoring, which is time-consuming and costly. This study evaluated the accuracy of machine learning (ML) models in predicting dissolved oxygen (DO) levels, aiming to reduce field monitoring efforts and minimize the number of measured parameters. Regression models (Huber, Linear, Ridge), Bagging methods (Extra Trees, Random Forest, Decision Trees), and Boosting techniques (Gradient Boosting, Light Gradient Boosting, AdaBoost) were tested using data from three sites in the Manawatu Catchment, New Zealand. Data spanning 1989–2014 included 12 water quality variables and was split into 70% training and 30% testing sets. Model performance was assessed using Nash–Sutcliffe efficiency, root mean square error, and coefficient of determination (R2). Results showed that fewer water quality indicators, particularly temperature, pH, and nutrients, effectively predict DO. All three regression models offer the best value for predicting DO within the Manawatu catchment over Bagging and Boosting regressors with R2 > 0.95. This study presents a novel, data-driven approach to water quality monitoring, demonstrating that ML can accurately predict DO using a reduced set of indicators, making monitoring efforts more computationally efficient, labor-saving, and cost-effective for water resource managers.


  • Open Access

    Acute coronary syndrome prediction in emergency care: A machine learning approach

    by Joshua Emakhu, Leslie Monplaisir, Celestine Aguwa, Suzan Arslanturk, Sara Masoud, Hashem Nassereddine, Mohamed S. Hamam, Joseph B. Miller