Zachary B. Strumpf
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zachary B. Strumpf has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
C. Miller
Pulmonary, Critical Care and Sleep Medicine, University Hospitals Cleveland Medical Center, Cleveland, OH, United States
3 shared publicationsK.Z. Abbas
Internal Medicine, University Hospitals Cleveland Medical Center, Cleveland, OH, United States
3 shared publicationsM. Matta
Pulmonary, Critical Care and Sleep Medicine, University Hospitals Cleveland Medical Center, Cleveland, OH, United States
3 shared publications- Wyatt P. Bensken
Department of Population and Quantitative Health Sciences Case Western Reserve University School of Medicine Cleveland Ohio USA
3 shared publications Kingman P. Strohl
Division of Pulmonary, Critical Care and Sleep Medicine, University Hospitals Cleveland Medical Center, Cleveland, USA
2 shared publications- Ambrose A. Chiang
Sleep Medicine Section, Louis Stokes Cleveland Veterans Administration (VA) Medical Center
1 shared publication
Latest Publications
- Open Access
- 11 June 2026
- Published by Elsevier in Respiratory Medicine
- Vol. 260, 108959
Challenging uniform size criteria for EBUS-TBNA sampling: Comparative analysis by lymph node station
- 11 June 2026
- Published by Elsevier in Respiratory Medicine
- Vol. 260, 108959
Open AccessChallenging uniform size criteria for EBUS-TBNA sampling: Comparative analysis by lymph node station
- Open Access
- 11 February 2026
- Published by Springer Nature in Sleep and Breathing
- Vol. 30 (1) , 41
Spectral analysis of ECG and SpO₂ for machine learning classification of Sleep-Disordered breathing
Purpose: Sleep-disordered breathing (SDB), particularly obstructive sleep apnea (OSA), is prevalent in hospitalized patients, yet remains underdiagnosed due to limited screening tools. This pilot study aimed to develop and validate a machine-learning classifier using electrocardiogram (ECG) and pulse oximetry (SpO₂) waveforms to detect SDB, leveraging routinely collected physiological data to enable non-invasive, scalable screening in hospitalized patients. Methods: We utilized data from the Multi-Ethnic Study of Atherosclerosis (MESA) Sleep cohort, which included full overnight polysomnography (PSG). A total of 122 participants were randomly selected, enriched for severe OSA cases. Spectral analysis of R-R intervals and SpO₂ variability was performed, and a support vector machine (SVM) classifier was trained using a subset of subjects ( n = 30). Performance was evaluated in a validation set ( n = 92) using standard classification metrics with 95% CIs calculated. Results: The first-stage classifier (SVM-1) demonstrated high sensitivity (98.7%) and specificity (99.0%) in identifying respiratory events at the window level. The second-stage classifier (SVM-2) correctly classified OSA presence with 100% accuracy in the training set. When applied to the validation set, the combined model achieved a sensitivity of 72.3%, specificity of 73.3%, and F1-score of 73.1%. Performance was impacted by arrhythmias, and lack of direct respiratory effort measures. Conclusion: A machine-learning model using routinely collected ECG and SpO₂ data shows promise for SDB detection but may require additional cardiopulmonary parameters for clinical decision-making in the ICU. Further validation with data collected in real-world ICU settings is warranted.
- 11 February 2026
- Published by Springer Nature in Sleep and Breathing
- Vol. 30 (1) , 41
Open AccessSpectral analysis of ECG and SpO₂ for machine learning classification of Sleep-Disordered breathing
Purpose: Sleep-disordered breathing (SDB), particularly obstructive sleep apnea (OSA), is prevalent in hospitalized patients, yet remains underdiagnosed due to limited screening tools. This pilot study aimed to develop and validate a machine-learning classifier using electrocardiogram (ECG) and pulse oximetry (SpO₂) waveforms to detect SDB, leveraging routinely collected physiological data to enable non-invasive, scalable screening in hospitalized patients. Methods: We utilized data from the Multi-Ethnic Study of Atherosclerosis (MESA) Sleep cohort, which included full overnight polysomnography (PSG). A total of 122 participants were randomly selected, enriched for severe OSA cases. Spectral analysis of R-R intervals and SpO₂ variability was performed, and a support vector machine (SVM) classifier was trained using a subset of subjects ( n = 30). Performance was evaluated in a validation set ( n = 92) using standard classification metrics with 95% CIs calculated. Results: The first-stage classifier (SVM-1) demonstrated high sensitivity (98.7%) and specificity (99.0%) in identifying respiratory events at the window level. The second-stage classifier (SVM-2) correctly classified OSA presence with 100% accuracy in the training set. When applied to the validation set, the combined model achieved a sensitivity of 72.3%, specificity of 73.3%, and F1-score of 73.1%. Performance was impacted by arrhythmias, and lack of direct respiratory effort measures. Conclusion: A machine-learning model using routinely collected ECG and SpO₂ data shows promise for SDB detection but may require additional cardiopulmonary parameters for clinical decision-making in the ICU. Further validation with data collected in real-world ICU settings is warranted.
- Open Access
- 1 December 2025
- Published by Oxford University Press (OUP) in ATS Scholar
- Vol. 6 (4) , 402-406
Did COVID-19 Curb Residents’ Enthusiasm for Pulmonary Disease and Critical Care Medicine/Critical Care Medicine Fellowships?
- 1 December 2025
- Published by Oxford University Press (OUP) in ATS Scholar
- Vol. 6 (4) , 402-406
Open AccessDid COVID-19 Curb Residents’ Enthusiasm for Pulmonary Disease and Critical Care Medicine/Critical Care Medicine Fellowships?
- Open Access
- 25 January 2024
- Published by Oxford University Press (OUP) in ATS Scholar
- Vol. 5 (1) , 154-161
Trends in Pulmonary Critical Care Fellowship Applications and Match Rates before and after the Onset of the COVID-19 Pandemic
Background: Because of the coronavirus disease (COVID-19) pandemic, fellowship interviews for pulmonary disease and critical care medicine (PCCM) switched from an in-person to virtual interview format. Objective: This study aimed to examine the changes that resulted from this switch (appointment year 2021 and beyond) for both the individual applicants and the match process as a whole. Methods: This cross-sectional study used longitudinal data from the Electronic Residency Application Service and the National Resident Matching Program from appointment years 2017 to 2022. Data from the Electronic Residency Application Service included the number of programs applicants applied to, and National Resident Matching Program data included the number of fellowship positions available, number entering the match, match rate, and the number of applicants who matched within the same region/program as their core residency training program. Descriptive and summary statistics and unadjusted linear models were used to identify if trends appeared in post-COVID-19 appointment years (2021 and beyond). Results: The number of PCCM positions increased by 33 (95% confidence interval, 26.2, 39.8) yearly between 2017 and 2022, with almost twice as many applicants (62.6; 95% CI confidence interval, 37.8, 87.4) entering the PCCM fellowship match during that same period. There was a decrease in the percentage of applicants matched each year, a trend unchanged before and after COVID-19, by an average of −2.15%. Comparing before and after COVID-19 appointment years, there was no significant change in same-region or same-program matches. Conclusion: Our analysis shows steadily rising interest in application rates for PCCM fellowships through the onset of the pandemic. However, a lack of proportionate increase in fellowship positions led to a decrease in overall match rates for applicants. To mitigate this, an increase in PCCM fellowship positions should be considered, and surveillance of these trends should continue.
- 25 January 2024
- Published by Oxford University Press (OUP) in ATS Scholar
- Vol. 5 (1) , 154-161
Open AccessTrends in Pulmonary Critical Care Fellowship Applications and Match Rates before and after the Onset of the COVID-19 Pandemic
Background: Because of the coronavirus disease (COVID-19) pandemic, fellowship interviews for pulmonary disease and critical care medicine (PCCM) switched from an in-person to virtual interview format. Objective: This study aimed to examine the changes that resulted from this switch (appointment year 2021 and beyond) for both the individual applicants and the match process as a whole. Methods: This cross-sectional study used longitudinal data from the Electronic Residency Application Service and the National Resident Matching Program from appointment years 2017 to 2022. Data from the Electronic Residency Application Service included the number of programs applicants applied to, and National Resident Matching Program data included the number of fellowship positions available, number entering the match, match rate, and the number of applicants who matched within the same region/program as their core residency training program. Descriptive and summary statistics and unadjusted linear models were used to identify if trends appeared in post-COVID-19 appointment years (2021 and beyond). Results: The number of PCCM positions increased by 33 (95% confidence interval, 26.2, 39.8) yearly between 2017 and 2022, with almost twice as many applicants (62.6; 95% CI confidence interval, 37.8, 87.4) entering the PCCM fellowship match during that same period. There was a decrease in the percentage of applicants matched each year, a trend unchanged before and after COVID-19, by an average of −2.15%. Comparing before and after COVID-19 appointment years, there was no significant change in same-region or same-program matches. Conclusion: Our analysis shows steadily rising interest in application rates for PCCM fellowships through the onset of the pandemic. However, a lack of proportionate increase in fellowship positions led to a decrease in overall match rates for applicants. To mitigate this, an increase in PCCM fellowship positions should be considered, and surveillance of these trends should continue.
- Open Access
- 26 June 2023
- Published by Elsevier in Sleep Health
- Vol. 9 (4) , 430-440
Belun Ring (Belun Sleep System BLS-100): Deep learning-facilitated wearable enables obstructive sleep apnea detection, apnea severity categorization, and sleep stage classification in patients suspected of obstructive sleep apnea
- 26 June 2023
- Published by Elsevier in Sleep Health
- Vol. 9 (4) , 430-440
Open AccessBelun Ring (Belun Sleep System BLS-100): Deep learning-facilitated wearable enables obstructive sleep apnea detection, apnea severity categorization, and sleep stage classification in patients suspected of obstructive sleep apnea
- 1 May 2023
- Published by Oxford University Press (OUP)
- p. A4285
Are Demographic Factors Predictive of PCCM Application Numbers or Match Rates?
- 1 May 2023
- Published by Oxford University Press (OUP)
- p. A4285
Are Demographic Factors Predictive of PCCM Application Numbers or Match Rates?