Mansoor Hayat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mansoor Hayat has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Frederick Adam Zeiler
Graduate Program in Biomedical Engineering, Price Faculty of Engineering, University of Manitoba, Winnipeg, Canada
17 shared publications - Tobias Bergmann
Department of Biomedical Engineering, Price Faculty of Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada
17 shared publications - Amanjyot Singh Sainbhi
Department of Biomedical Engineering, Price Faculty of Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada
16 shared publications - Kevin Y. Stein
Department of Biomedical Engineering, Price Faculty of Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada
15 shared publications - Noah Silvaggio
Department of Human Anatomy and Cell Science, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, MB R3E 0J9, Canada
15 shared publications - Nuray Vakitbilir
Department of Biomedical Engineering, Price Faculty of Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada
15 shared publications
Latest Publications
- Open Access
- 3 November 2026
- Published by MDPI AG in Bioengineering
- Vol. 13 (11) , 1303
Defining the Operating Envelope of Camera-Based Optical Character Recognition for Structured Data Capture from Non-Interoperable ICU Bedside Device Displays: A Controlled Technical Validation Study
Many intensive care unit bedside devices lack interoperable digital outputs, so clinically important readings are transferred into records by intermittent manual charting. Camera-based optical character recognition (OCR) offers an interface-independent alternative, but its value depends on identifying acquisition conditions under which structured extraction remains reliable and conditions under which output should be withheld. We evaluated a frame-sampled pipeline comprising display localisation, segmentation, pre-processing, OCR, clinical dictionary-based normalisation, and layered quality-control gating. A total of 151,763 usable frames were included in the primary evaluation across seven bedside instruments, three camera platforms, distances of 36 to 390 inches, viewing angles of 0 to 80 degrees, five lighting conditions, and two layouts. Per-stratum performance intervals are binomial Wilson and Clopper–Pearson intervals; the sampling-density transition estimates include bootstrap uncertainty. In an independently double-annotated stratified subset of 750 frames, Cohen’s kappa ranged from 0.89 to 0.97 across categorical annotations. Exact agreement was 96.4% for numeric values (95% CI 94.8–97.6%) and 94.8% for strings and labels (95% CI 93.0–96.3%); pooled exact agreement was 95.1% (95% CI 93.4–96.5%) and pooled kappa was 0.93 (95% CI 0.90–0.95). At 36 inches and near-frontal orientation, device-level sensitivity and precision were 0.990 and 0.997, 0.931 and 0.937, and 0.782 and 0.787 for the mirrorless, Raspberry Pi, and consumer webcam platforms, respectively. By 74 inches at near-frontal orientation, device-level sensitivity had fallen to 0.617, 0.515, and 0.309, respectively, showing that physical distance alone does not define a stable bedside operating range. Effective display sampling density described extraction performance more consistently across cameras than physical distance alone; the 0.90 complete device-level extraction transition was approximately 9.8 px/cm (bootstrap 95% CI 8.7–11.4 px/cm), a workflow-specific provisional empirical estimate rather than a validated operational threshold. Precision remained comparatively high as sensitivity declined; this is reported as observed system-level behaviour rather than causal evidence for any individual pipeline stage.
- 3 November 2026
- Published by MDPI AG in Bioengineering
- Vol. 13 (11) , 1303
Open AccessDefining the Operating Envelope of Camera-Based Optical Character Recognition for Structured Data Capture from Non-Interoperable ICU Bedside Device Displays: A Controlled Technical Validation Study
Many intensive care unit bedside devices lack interoperable digital outputs, so clinically important readings are transferred into records by intermittent manual charting. Camera-based optical character recognition (OCR) offers an interface-independent alternative, but its value depends on identifying acquisition conditions under which structured extraction remains reliable and conditions under which output should be withheld. We evaluated a frame-sampled pipeline comprising display localisation, segmentation, pre-processing, OCR, clinical dictionary-based normalisation, and layered quality-control gating. A total of 151,763 usable frames were included in the primary evaluation across seven bedside instruments, three camera platforms, distances of 36 to 390 inches, viewing angles of 0 to 80 degrees, five lighting conditions, and two layouts. Per-stratum performance intervals are binomial Wilson and Clopper–Pearson intervals; the sampling-density transition estimates include bootstrap uncertainty. In an independently double-annotated stratified subset of 750 frames, Cohen’s kappa ranged from 0.89 to 0.97 across categorical annotations. Exact agreement was 96.4% for numeric values (95% CI 94.8–97.6%) and 94.8% for strings and labels (95% CI 93.0–96.3%); pooled exact agreement was 95.1% (95% CI 93.4–96.5%) and pooled kappa was 0.93 (95% CI 0.90–0.95). At 36 inches and near-frontal orientation, device-level sensitivity and precision were 0.990 and 0.997, 0.931 and 0.937, and 0.782 and 0.787 for the mirrorless, Raspberry Pi, and consumer webcam platforms, respectively. By 74 inches at near-frontal orientation, device-level sensitivity had fallen to 0.617, 0.515, and 0.309, respectively, showing that physical distance alone does not define a stable bedside operating range. Effective display sampling density described extraction performance more consistently across cameras than physical distance alone; the 0.90 complete device-level extraction transition was approximately 9.8 px/cm (bootstrap 95% CI 8.7–11.4 px/cm), a workflow-specific provisional empirical estimate rather than a validated operational threshold. Precision remained comparatively high as sensitivity declined; this is reported as observed system-level behaviour rather than causal evidence for any individual pipeline stage.
- Open Access
- 27 August 2026
- Published by Springer Nature in Intensive Care Medicine Experimental
- Vol. 14 (1) , 114
Exploring the temporal statistical relationship between commercial cerebral near-infrared spectroscopy signals and intracranial pressure in traumatic brain injury
Background: Monitoring of intracranial pressure (ICP) is important for not only assessing neurological status of patients following traumatic brain injury (TBI), but also for guiding therapeutic interventions for the prevention of secondary neurological injury. Although current ICP monitoring techniques are highly temporally accurate, they come with some significant limitations. These limitations include the invasive nature, expertise required for placement of these devices, high cost associated with maintenance, and poor spatial resolution. Cerebral near-infrared spectroscopy (NIRS) offers a non-invasive alternative technique for cerebral physiological monitoring. This modality eliminates the need for surgical expertise, as well as decreasing the financial cost associated with monitoring cerebral physiology. Preliminary evidence has pointed to a potential link between the NIRS variable, regional oxygen saturation (rSO 2 ), and invasively obtained ICP. Despite this, there are very few studies that exist that investigate the direct statistical relationship between NIRS variables, such as rSO 2 , and invasively obtained ICP. As such, this study set out to characterize and compare the temporal statistical properties of commercial NIRS-based rSO 2 , ICP, and mean arterial pressure (MAP) signals. Results: Utilizing retrospective high-frequency physiologic data from a population of 118 TBI patients across different temporal resolutions and data window sizes, we evaluated independent statistical signal structure of rSO 2 and ICP using variance analysis and ARIMA modelling. Following normalization, variance metrics remained significantly different between all physiologic variable comparison groups, across all temporal resolutions and window sizes examined. In contrast, median optimal ARIMA model orders converged, with no significant differences observed between any of the included physiological variables. Next, Pearson correlation, cross-correlation, Granger causality, and VARIMA IRF analysis continued to show increasing temporal similarity between ICP and rSO 2 as temporal resolution decreased and window size increased. In contrast, throughout the majority of the analyses, the relationship between AMP and rSO 2 remained not only consistently weaker, but also more inconsistent across the majority of the analyses. Conclusion: Findings from this study demonstrate convergence in the temporal statistical behaviour of ICP and rSO 2 at lower temporal resolutions, providing a foundation for future predictive non-invasive ICP monitoring approaches. Further investigation into direct statistical relationships and development of reliable non-invasive ICP prediction models using NIRS-derived data remains necessary for clinical utility.
- 27 August 2026
- Published by Springer Nature in Intensive Care Medicine Experimental
- Vol. 14 (1) , 114
Open AccessExploring the temporal statistical relationship between commercial cerebral near-infrared spectroscopy signals and intracranial pressure in traumatic brain injury
Background: Monitoring of intracranial pressure (ICP) is important for not only assessing neurological status of patients following traumatic brain injury (TBI), but also for guiding therapeutic interventions for the prevention of secondary neurological injury. Although current ICP monitoring techniques are highly temporally accurate, they come with some significant limitations. These limitations include the invasive nature, expertise required for placement of these devices, high cost associated with maintenance, and poor spatial resolution. Cerebral near-infrared spectroscopy (NIRS) offers a non-invasive alternative technique for cerebral physiological monitoring. This modality eliminates the need for surgical expertise, as well as decreasing the financial cost associated with monitoring cerebral physiology. Preliminary evidence has pointed to a potential link between the NIRS variable, regional oxygen saturation (rSO 2 ), and invasively obtained ICP. Despite this, there are very few studies that exist that investigate the direct statistical relationship between NIRS variables, such as rSO 2 , and invasively obtained ICP. As such, this study set out to characterize and compare the temporal statistical properties of commercial NIRS-based rSO 2 , ICP, and mean arterial pressure (MAP) signals. Results: Utilizing retrospective high-frequency physiologic data from a population of 118 TBI patients across different temporal resolutions and data window sizes, we evaluated independent statistical signal structure of rSO 2 and ICP using variance analysis and ARIMA modelling. Following normalization, variance metrics remained significantly different between all physiologic variable comparison groups, across all temporal resolutions and window sizes examined. In contrast, median optimal ARIMA model orders converged, with no significant differences observed between any of the included physiological variables. Next, Pearson correlation, cross-correlation, Granger causality, and VARIMA IRF analysis continued to show increasing temporal similarity between ICP and rSO 2 as temporal resolution decreased and window size increased. In contrast, throughout the majority of the analyses, the relationship between AMP and rSO 2 remained not only consistently weaker, but also more inconsistent across the majority of the analyses. Conclusion: Findings from this study demonstrate convergence in the temporal statistical behaviour of ICP and rSO 2 at lower temporal resolutions, providing a foundation for future predictive non-invasive ICP monitoring approaches. Further investigation into direct statistical relationships and development of reliable non-invasive ICP prediction models using NIRS-derived data remains necessary for clinical utility.
- Open Access
- 9 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (14) , 6910
Few-Shot Hyperspectral Representation Learning for Multi-Task Forensic Document Analysis Using Episodic Prototypical Networks
Hyperspectral imaging has emerged as a promising modality for forensic document analysis due to its ability to capture spectral and material information beyond conventional RGB representations. However, existing hyperspectral forensic studies typically focus on individual tasks and provide limited insight into the transferability of learned representations across different forensic applications. This study investigates episodic hyperspectral representation learning for forensic document analysis using a shared spectral–spatial embedding space learned through prototypical optimization. The proposed framework is evaluated on the complete UWA WIHSI and iVision HHID hyperspectral datasets across multiple forensic applications, namely writer identification, writer verification, ink mismatch detection, forgery detection, gender prediction, and age prediction.The proposed method achieved high performance on the controlled UWA WIHSI dataset across multiple forensic tasks. On the more challenging iVision HHID dataset, it attained a writer identification accuracy of 90.74%, together with writer verification and ink mismatch detection ROC–AUC scores of 0.9936 and 0.9915, respectively. Cross-dataset experiments further highlighted both the potential and the challenges of transferring learned hyperspectral representations across different acquisition conditions and writer populations, while extensive ablation studies confirmed the importance of spectral information, embedding design, and optimization strategy in learning effective hyperspectral representations. Overall, the results show that shared hyperspectral representations can support diverse forensic document analysis applications within a common embedding space while providing insight into the opportunities and challenges of developing transferable hyperspectral representations for forensic settings.
- 9 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (14) , 6910
Open AccessFew-Shot Hyperspectral Representation Learning for Multi-Task Forensic Document Analysis Using Episodic Prototypical Networks
Hyperspectral imaging has emerged as a promising modality for forensic document analysis due to its ability to capture spectral and material information beyond conventional RGB representations. However, existing hyperspectral forensic studies typically focus on individual tasks and provide limited insight into the transferability of learned representations across different forensic applications. This study investigates episodic hyperspectral representation learning for forensic document analysis using a shared spectral–spatial embedding space learned through prototypical optimization. The proposed framework is evaluated on the complete UWA WIHSI and iVision HHID hyperspectral datasets across multiple forensic applications, namely writer identification, writer verification, ink mismatch detection, forgery detection, gender prediction, and age prediction.The proposed method achieved high performance on the controlled UWA WIHSI dataset across multiple forensic tasks. On the more challenging iVision HHID dataset, it attained a writer identification accuracy of 90.74%, together with writer verification and ink mismatch detection ROC–AUC scores of 0.9936 and 0.9915, respectively. Cross-dataset experiments further highlighted both the potential and the challenges of transferring learned hyperspectral representations across different acquisition conditions and writer populations, while extensive ablation studies confirmed the importance of spectral information, embedding design, and optimization strategy in learning effective hyperspectral representations. Overall, the results show that shared hyperspectral representations can support diverse forensic document analysis applications within a common embedding space while providing insight into the opportunities and challenges of developing transferable hyperspectral representations for forensic settings.
- Open Access
Interpolation and Imputation Strategies for Missing Segments in Continuous Pressure-Flow Cerebral Bio-Signals: A Systematic Scoping Review
Objective: Continuous pressure-flow cerebral bio-signals are critical for monitoring cerebrovascular dynamics but are often disrupted by missing data segments caused by artifacts from a variety of sources. These missing segments refer to segments of the signal that do not contain any valid physiological data. Such interruptions fragment the signals, resulting in discontinuities that compromise their overall integrity. Therefore, reconstructing missing values and preserving signal continuity are essential for ensuring the stable computation of signal trajectories and the accuracy of derived cerebrovascular indices. Methods: To address this issue, this systematic scoping review aimed to identify and synthesize existing interpolation and imputation strategies for handling missing segments in continuous pressure-flow cerebral bio-signals. Following the Cochrane and Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines, a comprehensive search of five electronic databases was conducted from their inception to 24 September 2024, and updated on 16 June 2025, using a detailed search string. Results: The initial searches yielded 19,403 results, and 8 studies were filtered and included in the review. All included studies employed interpolation techniques, such as linear and spline interpolation algorithms, to correct distorted signal segments. However, none of the included studies directly utilized interpolation or imputation strategies to reconstruct or completely fill missing data segments. Conclusions: This reveals a critical knowledge gap, as no study has systematically addressed the utilization of interpolation or imputation strategies for missing segments in pressure-flow cerebral bio-signals. Therefore, this systematic review emphasizes the need for specialized methodologies and standardized frameworks to enable reliable recovery of missing data segments in pressure-flow cerebral bio-signals, which is critical for advancing real-time neurocritical care monitoring and experimental neuroscience/psychological research. Significance: This systematic review lays the groundwork for future research into physiologically informed interpolation and imputation strategies for pressure-flow cerebral bio-signals in clinical and research applications.
Open AccessInterpolation and Imputation Strategies for Missing Segments in Continuous Pressure-Flow Cerebral Bio-Signals: A Systematic Scoping Review
Objective: Continuous pressure-flow cerebral bio-signals are critical for monitoring cerebrovascular dynamics but are often disrupted by missing data segments caused by artifacts from a variety of sources. These missing segments refer to segments of the signal that do not contain any valid physiological data. Such interruptions fragment the signals, resulting in discontinuities that compromise their overall integrity. Therefore, reconstructing missing values and preserving signal continuity are essential for ensuring the stable computation of signal trajectories and the accuracy of derived cerebrovascular indices. Methods: To address this issue, this systematic scoping review aimed to identify and synthesize existing interpolation and imputation strategies for handling missing segments in continuous pressure-flow cerebral bio-signals. Following the Cochrane and Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines, a comprehensive search of five electronic databases was conducted from their inception to 24 September 2024, and updated on 16 June 2025, using a detailed search string. Results: The initial searches yielded 19,403 results, and 8 studies were filtered and included in the review. All included studies employed interpolation techniques, such as linear and spline interpolation algorithms, to correct distorted signal segments. However, none of the included studies directly utilized interpolation or imputation strategies to reconstruct or completely fill missing data segments. Conclusions: This reveals a critical knowledge gap, as no study has systematically addressed the utilization of interpolation or imputation strategies for missing segments in pressure-flow cerebral bio-signals. Therefore, this systematic review emphasizes the need for specialized methodologies and standardized frameworks to enable reliable recovery of missing data segments in pressure-flow cerebral bio-signals, which is critical for advancing real-time neurocritical care monitoring and experimental neuroscience/psychological research. Significance: This systematic review lays the groundwork for future research into physiologically informed interpolation and imputation strategies for pressure-flow cerebral bio-signals in clinical and research applications.
- Open Access
- 7 May 2026
- Published by Springer Nature in BMC Biomedical Engineering
- Vol. 8 (1)
Comparative analysis of processed EEG indices and entropy-based metrics for assessing anesthetic depth: a scoping review - PRISMA-ScR
Processed electroencephalography (EEG) monitors such as the bispectral index (BIS) and patient state index (PSI), are used clinically to estimate anesthetic depth, yet their algorithmic design obscures how closely these indices reflect underlying neural complexity. Entropy-based analyses, grounded in information theory, provide a quantitative framework for characterizing EEG signal irregularity and have been proposed as physiologically interpretable alternatives. However, the relationship between these commercial indices and theoretical entropy measures remains unclear. This systematic review aimed to (1) synthesize existing evidence on the relationship between commercially available processed EEG metrics and entropy-based EEG analyses, and (2) identify factors influencing their comparability, including algorithmic, demographic, and anesthetic variables. A comprehensive literature search identified experimental and clinical studies comparing BIS, PSI, and related commercial indices with theoretical entropy measures (e.g., approximate entropy, sample entropy, and permutation entropy, state entropy and response entropy) across various anesthetic agents and clinical populations. Data were extracted on study design, patient demographics, EEG metrics, analytical methods, and reported correlations or prediction probabilities. Ninety-four studies were included, encompassing participants across diverse anesthetic modalities. Overall, BIS exhibited moderate-to-strong correlations with entropy-derived measures and comparable prediction probabilities for distinguishing anesthetic depth. Entropy indices demonstrated greater resistance to certain artifacts but higher susceptibility to electromyographic contamination. Age, anesthetic type, and the use of neuromuscular blocking agents significantly influenced the relationship between indices. Across studies, heterogeneity in preprocessing, entropy algorithms, and patient selection limited direct comparability. Commercially processed EEG indices and theoretical entropy measures capture overlapping but distinct dimensions of cortical dynamics during anesthesia. While both reliably track transitions in consciousness, discrepancies arise from differences in signal filtering, algorithm design, and physiological variability. Future research should prioritize transparent algorithmic frameworks and standardized entropy computation to enhance the interpretability and cross-device comparability of EEG-derived anesthesia monitors.
- 7 May 2026
- Published by Springer Nature in BMC Biomedical Engineering
- Vol. 8 (1)
Open AccessComparative analysis of processed EEG indices and entropy-based metrics for assessing anesthetic depth: a scoping review - PRISMA-ScR
Processed electroencephalography (EEG) monitors such as the bispectral index (BIS) and patient state index (PSI), are used clinically to estimate anesthetic depth, yet their algorithmic design obscures how closely these indices reflect underlying neural complexity. Entropy-based analyses, grounded in information theory, provide a quantitative framework for characterizing EEG signal irregularity and have been proposed as physiologically interpretable alternatives. However, the relationship between these commercial indices and theoretical entropy measures remains unclear. This systematic review aimed to (1) synthesize existing evidence on the relationship between commercially available processed EEG metrics and entropy-based EEG analyses, and (2) identify factors influencing their comparability, including algorithmic, demographic, and anesthetic variables. A comprehensive literature search identified experimental and clinical studies comparing BIS, PSI, and related commercial indices with theoretical entropy measures (e.g., approximate entropy, sample entropy, and permutation entropy, state entropy and response entropy) across various anesthetic agents and clinical populations. Data were extracted on study design, patient demographics, EEG metrics, analytical methods, and reported correlations or prediction probabilities. Ninety-four studies were included, encompassing participants across diverse anesthetic modalities. Overall, BIS exhibited moderate-to-strong correlations with entropy-derived measures and comparable prediction probabilities for distinguishing anesthetic depth. Entropy indices demonstrated greater resistance to certain artifacts but higher susceptibility to electromyographic contamination. Age, anesthetic type, and the use of neuromuscular blocking agents significantly influenced the relationship between indices. Across studies, heterogeneity in preprocessing, entropy algorithms, and patient selection limited direct comparability. Commercially processed EEG indices and theoretical entropy measures capture overlapping but distinct dimensions of cortical dynamics during anesthesia. While both reliably track transitions in consciousness, discrepancies arise from differences in signal filtering, algorithm design, and physiological variability. Future research should prioritize transparent algorithmic frameworks and standardized entropy computation to enhance the interpretability and cross-device comparability of EEG-derived anesthesia monitors.
- Open Access
- 23 April 2026
- Published by Elsevier in SSRN Electronic Journal
Device-Agnostic Camera-Based System for Real-Time Extraction of ICU Bedside Device Data
Manual transcription of bedside medical device data in intensive care units remains a significant source of documentation error and workflow inefficiency, particularly where legacy devices lack interoperable digital outputs. We developed a device-agnostic, camera-based system for automated extraction of physiological and pharmacological information directly from bedside displays. The system integrates multi-device screen detection, image pre-processing, optical character recognition, and domain-specific normalisation within a unified pipeline.The approach was evaluated on approximately 150,000 annotated frames acquired across multiple camera platforms under systematically varied distances, viewing angles, and lighting conditions. Under clinically relevant conditions (36 inches, near-frontal view), device detection sensitivity reached 0.995 and OCR sensitivity reached 0.990, with field-level transcription exceeding 0.96. Performance remained stable at extended bedside distances (approximately 72 inches), but declined progressively beyond this range, primarily due to reduced effective pixel density on the display surface.These findings demonstrate that camera-based digitisation enables scalable and reliable extraction of structured data from heterogeneous ICU devices without requiring direct device integration, supporting improved clinical documentation and research data capture.Funding: This work was directly supported by the Endowed Manitoba Public Insurance (MPI) Chair in Neuroscience, Research Manitoba (Grant # 5429), and the Natural Sciences and Engineering Research Council of Canada Alliance Advantage program (NSERC; RGPIN-2022-0362, I2IPJ-586104–23, I2IPJ-598125-24). FAZ is supported through the Endowed Manitoba Public Insurance (MPI) Chair in Neuroscience/TBI Research Endowment, NSERC (DGECR-2022-00260, RGPIN-2022-03621, ALLRP-578524-22, I2IPJ-586104–23, ALLRP-597708-24, I2IPJ-598125-24), the Canadian Institutes of Health Research (CIHR; Grant # 530549), the MPI Neuroscience Research Operating Fund, the Health Sciences Centre Foundation Winnipeg, the Canada Foundation for Innovation (CFI; Project # 38583), Research Manitoba (Grant # 5429, 6554, 7312), and the Pan Am Clinic Foundation of Winnipeg. MH is supported by Research Manitoba (Grant # 5429) and the Research Manitoba Post-Doctoral Fellowship. VR is supported by the University of Manitoba Undergraduate Research Award (URA) and NSERC (I2IPJ-598125-24). MM is supported by NSERC (I2IPJ-598125-24). IH is supported by CIHR (Grant # 530549), the University of Manitoba Grad- uate Enhancement of Tri-Agency Stipends (GETS) program, and the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering. RH is supported by NSERC (ALLRP-597708-24), the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program, and the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering. ASS is supported by NSERC (RGPIN-2022-03621, I2IPJ-598125-24) and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. KYS is supported through the NSERC CGS-D program (CGS D-579021-2023), the University of Manitoba R.G. and E.M. Graduate Fellowship (Doctoral) in Biomedical Engineering, and the University of Manitoba MD/PhD program. NV is supported by the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering, NSERC (RGPIN-2022-03621), and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. NS is supported by the University of Manitoba Graduate Fellowship (UMGF) in Human Anatomy and Cell Sciences and NSERC (ALLRP-578524-22, ALLRP-597708- 24). TB is supported through the NSERC CGS-M program, the NSERC PGS-D pro- gram (PGS D-600443–2025), NSERC (ALLRP-578524-22), and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. JM is supported by CIHR (Grant # 530549) and the Lab2Market program (IT49045). LF is supported through the NSERC Post-Doctoral Fellowship (PDF) program and the Swedish Brain Foundation (#FO2023-0124). VR is supported by the University of Manitoba Undergraduate Research Award (URA) and NSERC (I2IPJ-598125-24). MM is supported by NSERC (I2IPJ-598125-24). IH is supported by CIHR (Grant # 530549), the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program, and the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering. RH is supported by NSERC (ALLRP-597708-24), the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program, and the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering. ASS is supported by NSERC (RGPIN-2022-03621, I2IPJ-598125-24) and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. KYS is supported through the NSERC CGS-D program (CGS D-579021-2023), the University of Manitoba R.G. and E.M. Graduate Fellowship (Doctoral) in Biomedical Engineering, and the University of Manitoba MD/PhD program. NV is supported by the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering, NSERC (RGPIN-2022-03621), and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. NS is supported by the University of Manitoba Graduate Fellowship (UMGF) in Human Anatomy and Cell Sciences and NSERC (ALLRP-578524-22, ALLRP-597708-TB is supported through the NSERC CGS-M program, the NSERC PGS-D program (PGS D-600443–2025), NSERC (ALLRP-578524-22), and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. JM is supported by CIHR (Grant # 530549) and the Lab2Market program (IT49045). LF is supported through the NSERC Post-Doctoral Fellowship (PDF) program and the Swedish Brain Foundation (#FO2023-0124).Declaration of Interest: FAZ and LF, in combination with the University of Manitoba, have formal intellectual property filings (Provisional Patent:...
- 23 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDevice-Agnostic Camera-Based System for Real-Time Extraction of ICU Bedside Device Data
Manual transcription of bedside medical device data in intensive care units remains a significant source of documentation error and workflow inefficiency, particularly where legacy devices lack interoperable digital outputs. We developed a device-agnostic, camera-based system for automated extraction of physiological and pharmacological information directly from bedside displays. The system integrates multi-device screen detection, image pre-processing, optical character recognition, and domain-specific normalisation within a unified pipeline.The approach was evaluated on approximately 150,000 annotated frames acquired across multiple camera platforms under systematically varied distances, viewing angles, and lighting conditions. Under clinically relevant conditions (36 inches, near-frontal view), device detection sensitivity reached 0.995 and OCR sensitivity reached 0.990, with field-level transcription exceeding 0.96. Performance remained stable at extended bedside distances (approximately 72 inches), but declined progressively beyond this range, primarily due to reduced effective pixel density on the display surface.These findings demonstrate that camera-based digitisation enables scalable and reliable extraction of structured data from heterogeneous ICU devices without requiring direct device integration, supporting improved clinical documentation and research data capture.Funding: This work was directly supported by the Endowed Manitoba Public Insurance (MPI) Chair in Neuroscience, Research Manitoba (Grant # 5429), and the Natural Sciences and Engineering Research Council of Canada Alliance Advantage program (NSERC; RGPIN-2022-0362, I2IPJ-586104–23, I2IPJ-598125-24). FAZ is supported through the Endowed Manitoba Public Insurance (MPI) Chair in Neuroscience/TBI Research Endowment, NSERC (DGECR-2022-00260, RGPIN-2022-03621, ALLRP-578524-22, I2IPJ-586104–23, ALLRP-597708-24, I2IPJ-598125-24), the Canadian Institutes of Health Research (CIHR; Grant # 530549), the MPI Neuroscience Research Operating Fund, the Health Sciences Centre Foundation Winnipeg, the Canada Foundation for Innovation (CFI; Project # 38583), Research Manitoba (Grant # 5429, 6554, 7312), and the Pan Am Clinic Foundation of Winnipeg. MH is supported by Research Manitoba (Grant # 5429) and the Research Manitoba Post-Doctoral Fellowship. VR is supported by the University of Manitoba Undergraduate Research Award (URA) and NSERC (I2IPJ-598125-24). MM is supported by NSERC (I2IPJ-598125-24). IH is supported by CIHR (Grant # 530549), the University of Manitoba Grad- uate Enhancement of Tri-Agency Stipends (GETS) program, and the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering. RH is supported by NSERC (ALLRP-597708-24), the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program, and the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering. ASS is supported by NSERC (RGPIN-2022-03621, I2IPJ-598125-24) and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. KYS is supported through the NSERC CGS-D program (CGS D-579021-2023), the University of Manitoba R.G. and E.M. Graduate Fellowship (Doctoral) in Biomedical Engineering, and the University of Manitoba MD/PhD program. NV is supported by the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering, NSERC (RGPIN-2022-03621), and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. NS is supported by the University of Manitoba Graduate Fellowship (UMGF) in Human Anatomy and Cell Sciences and NSERC (ALLRP-578524-22, ALLRP-597708- 24). TB is supported through the NSERC CGS-M program, the NSERC PGS-D pro- gram (PGS D-600443–2025), NSERC (ALLRP-578524-22), and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. JM is supported by CIHR (Grant # 530549) and the Lab2Market program (IT49045). LF is supported through the NSERC Post-Doctoral Fellowship (PDF) program and the Swedish Brain Foundation (#FO2023-0124). VR is supported by the University of Manitoba Undergraduate Research Award (URA) and NSERC (I2IPJ-598125-24). MM is supported by NSERC (I2IPJ-598125-24). IH is supported by CIHR (Grant # 530549), the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program, and the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering. RH is supported by NSERC (ALLRP-597708-24), the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program, and the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering. ASS is supported by NSERC (RGPIN-2022-03621, I2IPJ-598125-24) and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. KYS is supported through the NSERC CGS-D program (CGS D-579021-2023), the University of Manitoba R.G. and E.M. Graduate Fellowship (Doctoral) in Biomedical Engineering, and the University of Manitoba MD/PhD program. NV is supported by the University of Manitoba Graduate Fellowship (UMGF) in Biomedical Engineering, NSERC (RGPIN-2022-03621), and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. NS is supported by the University of Manitoba Graduate Fellowship (UMGF) in Human Anatomy and Cell Sciences and NSERC (ALLRP-578524-22, ALLRP-597708-TB is supported through the NSERC CGS-M program, the NSERC PGS-D program (PGS D-600443–2025), NSERC (ALLRP-578524-22), and the University of Manitoba Graduate Enhancement of Tri-Agency Stipends (GETS) program. JM is supported by CIHR (Grant # 530549) and the Lab2Market program (IT49045). LF is supported through the NSERC Post-Doctoral Fellowship (PDF) program and the Swedish Brain Foundation (#FO2023-0124).Declaration of Interest: FAZ and LF, in combination with the University of Manitoba, have formal intellectual property filings (Provisional Patent:...
- Open Access
- 7 April 2026
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 26 (1)
A novel algorithm for the continuous determination of individualized intracranial pressure (iICP) thresholds using a multi-window weighted approach
Individualized intracranial pressure (iICP) thresholds, defined as the function intersectionality between intracranial pressure (ICP) and cerebrovascular r
- 7 April 2026
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 26 (1)
Open AccessA novel algorithm for the continuous determination of individualized intracranial pressure (iICP) thresholds using a multi-window weighted approach
Individualized intracranial pressure (iICP) thresholds, defined as the function intersectionality between intracranial pressure (ICP) and cerebrovascular r
- Open Access
- 31 March 2026
- Published by IOP Publishing in Physiological Measurement
- Vol. 47 (3) , 035014
Algorithmic derivation of optimal CPP, MAP, and BIS targets from cerebrovascular reactivity indices: a systematic scoping review
Objective. Autoregulation-guided physiological targeting, using metrics such as optimal cerebral perfusion pressure (CPPopt), optimal mean arterial pressure (MAPopt), and optimal bispectral index (BISopt), has emerged as a promising strategy for improving patient outcomes in critical care and neuromonitoring. These targets, derived from the continuous assessment of cerebrovascular reactivity (CVR) indices, are increasingly being studied for their potential to individualize patient management. This review aimed to identify and characterize existing literature detailing the derivation algorithms of CPPopt, MAPopt, and BISopt, focusing on key computational parameters, methodological consistencies, and quantitative algorithm performance metrics. Approach. Following preferred reporting items for systematic reviews and meta-analyses extension for scoping reviews guidelines, studies were included if they reported algorithmic details of CPPopt, MAPopt, or BISopt derivation and provided at least six of seven core technical parameters (raw data sampling frequency, CVR index preprocessing, binning, data window size for optimality curve fitting, curve fitting method, update frequency, and yield), which were extracted during data extraction. Additional data captured included patient cohort characteristics, study objective, and CVR assessment technology. Main results. 20 studies met the inclusion criteria: 13 described CPPopt, 6 described MAPopt, and 2 described BISopt derivation algorithms. CPPopt algorithms predominantly used the pressure reactivity index (PRx) as the CVR index, 5 mmHg binning, and second-order polynomial curve fitting, with frequent minute-by-minute updates and multi-window averaging. MAPopt algorithms primarily used near-infrared spectroscopy-derived indices such as hemoglobin volume index and cerebral oximetry index (COx), while BISopt studies combined electroencephalogram monitoring with PRx or COx. Algorithmic yield ranged from 45.6% to 100%, depending on the preprocessing strategy and curve-fitting quality. Based on the existing literature, we found CPPopt derivation remains the most mature and widely studied algorithm, while MAPopt and BISopt are emerging modalities with growing interest. Significance. Despite high feasibility across studies, significant methodological variability limits the comparability of the found algorithms. Standardized algorithm reporting is needed to support widespread clinical adoption of autoregulation-guided physiological targets.
- 31 March 2026
- Published by IOP Publishing in Physiological Measurement
- Vol. 47 (3) , 035014
Open AccessAlgorithmic derivation of optimal CPP, MAP, and BIS targets from cerebrovascular reactivity indices: a systematic scoping review
Objective. Autoregulation-guided physiological targeting, using metrics such as optimal cerebral perfusion pressure (CPPopt), optimal mean arterial pressure (MAPopt), and optimal bispectral index (BISopt), has emerged as a promising strategy for improving patient outcomes in critical care and neuromonitoring. These targets, derived from the continuous assessment of cerebrovascular reactivity (CVR) indices, are increasingly being studied for their potential to individualize patient management. This review aimed to identify and characterize existing literature detailing the derivation algorithms of CPPopt, MAPopt, and BISopt, focusing on key computational parameters, methodological consistencies, and quantitative algorithm performance metrics. Approach. Following preferred reporting items for systematic reviews and meta-analyses extension for scoping reviews guidelines, studies were included if they reported algorithmic details of CPPopt, MAPopt, or BISopt derivation and provided at least six of seven core technical parameters (raw data sampling frequency, CVR index preprocessing, binning, data window size for optimality curve fitting, curve fitting method, update frequency, and yield), which were extracted during data extraction. Additional data captured included patient cohort characteristics, study objective, and CVR assessment technology. Main results. 20 studies met the inclusion criteria: 13 described CPPopt, 6 described MAPopt, and 2 described BISopt derivation algorithms. CPPopt algorithms predominantly used the pressure reactivity index (PRx) as the CVR index, 5 mmHg binning, and second-order polynomial curve fitting, with frequent minute-by-minute updates and multi-window averaging. MAPopt algorithms primarily used near-infrared spectroscopy-derived indices such as hemoglobin volume index and cerebral oximetry index (COx), while BISopt studies combined electroencephalogram monitoring with PRx or COx. Algorithmic yield ranged from 45.6% to 100%, depending on the preprocessing strategy and curve-fitting quality. Based on the existing literature, we found CPPopt derivation remains the most mature and widely studied algorithm, while MAPopt and BISopt are emerging modalities with growing interest. Significance. Despite high feasibility across studies, significant methodological variability limits the comparability of the found algorithms. Standardized algorithm reporting is needed to support widespread clinical adoption of autoregulation-guided physiological targets.