Mahmoud Alwakeel
Research Interests
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Articles (10)
Although hypothesized to be the root cause of the pulse oximetry disparities, skin tone and its use for improving medical therapies have yet to be extensively studied. Studies that previously used self-reported race as a proxy variable for skin tone cannot account for skin tone variabilities within race groups. This study aimed to create a unique baseline dataset that included skin tone and electronic health record (EHR) data to better evaluate health disparities associated with pulse oximetry. We collected skin tone data at 16 different body locations using multiple devices, including administered visual scales, colorimetric, spectrophotometric, and photography via mobile phone cameras. All patients’ data were converted into a common data model and de-identified before publication in PhysioNet. We assessed 167 features per skin location on 128 patients linked with their EHR data, such as laboratory data, vital sign recordings, and demographic information. We also include 2,438 images from mobile phones to assist in developing artificial intelligence tools to combat health disparities.
Year:
2026
Year:
2025
Objective Capital budgeting in intensive care units (ICUs) demands rapid, high-stakes investment decisions. We developed an open-source ICU Capital Budgeting Workbench that merges a deterministic finance engine with GPT-based natural-language processing (NLP) to streamline planning. Materials and Methods The web application couples classic valuation metrics (e.g., net present value, internal rate of return, and payback) with an NLP module that converts multi-year free-text scenarios into structured projections. Users describe projects in everyday language; GPT parses these narratives into year-by-year cash flows and discount rates, after which the engine computes financial metrics and produces interactive sensitivity, scenario, and Monte Carlo analyses. Results In illustrative cases the workbench translated narrative ICU expansion proposals into five and ten-year cash-flow tables and NPV calculations within seconds, eliminating manual spreadsheet construction. Interactive dashboards let users test key assumptions, instantly revealing how occupancy, reimbursement, or inflation shifts influence returns. Compared with traditional ad-hoc spreadsheets, the tool demonstrated marked time savings and consistent analytic structure. Discussion This proof-of-concept shows how large language models can reduce transcription errors, standardize methodology, and embed uncertainty modeling in routine capital planning. Limitations include dependence on GPT’s parsing accuracy and the need for real-world validation with authentic hospital data. Conclusion The ICU Capital Budgeting Workbench exemplifies practical AI integration for finance and operations leaders, offering transparent, reproducible, and scalable decision support for ICU equipment and facility investments. By replacing bespoke spreadsheets with a governed, open-source platform, it may improve efficiency and support better-informed, data-driven investment strategy.
Year:
2025
Importance Early identification of fever or hypothermia is crucial for diagnosing sepsis. Despite their increased use across healthcare systems, concerns have been raised about the accuracy of temporal thermometers among Black patients. Objective To study the performance of temporal thermometry across race and ethnicity, and its impact on the initiation of the sepsis management bundle (SEP-1). Design In this retrospective cohort study, records from 2008–2024 in 123 U.S. hospitals were analyzed, including electronic health records from Duke, MIMIC-IV, eICU-CRD-1, and eICU-CRD-2. Patients were included if they had a temporal measurement within one hour of an oral/core measurement (esophageal, bladder, rectal). Main Outcomes and Measures Hidden Fever was defined when the temporal thermometer read ≤ 38°C but oral/core measurement > 38°C and Hidden Hypothermia as temporal temperature ≥ 36°C but oral/core < 36°C. The primary outcome was Hidden Hyper/Hypothermia (HHH) when either Hidden Fever or Hidden Hypothermia happened. Observed Hyper / Hypothermia (OHH) corresponded to an agreement between both measurements, used as a control. To study the impact of temporal thermometry underperformance on SEP-1 bundle initiation, we assessed time to culture ordering, antibiotics administration, and lactate measurement. A composite of these three, whichever happened first, was defined as our secondary outcome. Results 6,921 paired temperature measurements were studied for the primary outcome analysis, corresponding to 4,248 hospitalizations (2.6% Asian; 12.4% Black; 2.6% Hispanic/Latino; 83.4% White; 44.9% female; 7.7% with HHH) from 115 hospitals. After adjusting for confounders, Black [OR (95% CI): 1.760 (1.219, 2.541), p =0.003] and Hispanic/Latino [OR (95% CI): 2.183 (1.226, 3.888), p= 0.008] patients were significantly more likely to present with HHH than White patients. For the study of the secondary outcome, 434 patients had either OHH or HHH. Compared to patients with OHH, patients with HHH had significantly delayed secondary outcomes, with log-rank p-value of 0.002. Conclusions and Relevance Solely relying on temporal thermometry can lead to missed hyper/hypothermia events, especially among Asian, Black, and Hispanic patients. This has been associated with delays in the initiation of the SEP-1 bundle, which may hamper health systems’ compliance with reimbursement programs. Key Points Question Are there racial differences in temporal thermometry that result in missed hyper/hypothermia, and are these associated with delays in sepsis bundle care (SEP-1) initiation? Findings In this multicenter retrospective cohort study of 4,248 hospitalizations, Asian, Black, and Hispanic patients were more likely to have hidden hyper/hypothermia when using temporal thermometers, as compared to oral/core measurements. These missed events were associated with delayed SEP-1 interventions (three out of four were studied: culture orders, antibiotic administration, and lactate measurements). Meaning Reliance on temporal thermometry could exacerbate health disparities and hamper hospital systems’ compliance with reimbursement programs. Temporal thermometers should therefore be routinely validated with contact thermometers.
Year:
2025
Background: The methicillin-resistant Staphylococcus aureus (MRSA) accounts for 20% to 40% of all hospital-acquired pneumonia (HAP) cases with mortality rates up to 55%. Prompt and accurate diagnosis is essential, especially in intensive care unit (ICU) patients. Nasal MRSA polymerase chain reaction (PCR) diagnostic utility evidence is conflicting in the literature for HAP due to a low number of HAP patients included in prior studies or due to the lack of high-yield gold standard cultures defined for comparisons. Methods: This was a retrospective cohort study conducted in a 65-bed medical ICU, and encompassing all adult patients admitted from January 2015 to March 2023 for HAP. Respiratory cultures included were those obtained by bronchoalveolar lavage or endotracheal suction within 7 days of nasal MRSA PCR testing. Results: The study included 412 patients; 56.8% were males and 65% were Whites. The mean age was 60.5 years. Most patients (82.5%) underwent MRSA-PCR before intubation, and the average time between MRSA-PCR and lower respiratory cultures was 2.15 days. The diagnostic performance of nasal MRSA PCR in diagnosing HAP in the ICU yielded a sensitivity (Sen) of 47.83%, specificity (Sp) of 92.29%, positive predictive value (PPV) of 26.83%, and negative predictive value (NPV) of 96.77%. For nonventilator HAP (nv-HAP) cases sensitivity was at 50%, specificity 92.83%, PPV 28.57%, and NPV at 97.00%. In ventilator-acquired pneumonia (VAP-HAP), the corresponding values were 42.86%, 90.91%, 23.08%, and 96.15%, respectively. Conclusion: The nasal MRSA PCR shows a high NPV and low false negative rate, suggesting it is a reliable tool for ruling out MRSA HAP in ICU patients. Care should be taken into account for disease prevalence and clinical context, as these factors may influence test performance. Further validation through prospective large-sample studies utilizing high-yield lower respiratory tract cultures is necessary to confirm our findings.
Year:
2024
Background: Reduction in sedation exposure is an important metric in intensive care unit (ICU) patients. However, challenges arose during the coronavirus disease-2019 (COVID-19) pandemic in adhering to this practice, driven by concerns on transmission and disease severity issues. Accordingly, diverse sedation approaches emerged, although the effect on mortality has not been studied thoroughly. Methods: Retrospective cohort study in the medical ICU of seven hospitals within a major Health System in Northeast Ohio. We included all adult patients admitted with COVID-19 requiring invasive mechanical ventilation (IMV) from March 2020 to December 2021. Results: Study included 2394 COVID-19 patients requiring IMV. Across waves, sample included 55-63% male subjects, with an average age of 61-68 years ( P 0.05] for propofol, ketamine, and midazolam. Dexmedetomidine demonstrated a decrease in the odds of mortality [aOR = 0.96 (95% CI 0.94-0.97); P < 0.001]. Conclusion: Mortality in critical COVID-19 patients was mostly driven by illness severity, and the choice of sedation might have minimal impact when other factors are controlled.
Year:
2024
Background The neutrophil-to-lymphocyte ratio (NLR) proves to be a convenient and cost-effective marker with studies showing that a high NLR can serve as a mortality indicator in burn cases. We conducted a meta-analysis aiming to explore whether on-admission NLR values could serve as predictors of mortality in burn patients. Methods PubMed, Web of Science, Scopus and Embase were searched from inception until January 2024. We included all studies investigating burn patients that contain information on the NLR value at the time of hospital admission and mortality outcomes. The studies were critically appraised using the NIH Quality Assessment Tool. Results Nine studies fulfilled our criteria with a total population of 1837 participants, including 1526 survivor Burn patients and 311 non-survivor Burn patients. The overall mean difference measured by random model showed a significant increase in NLR by 5.06 (95% CI 3.42, 6.68) p ≤ 0.001 for the non-survivor group over the survivors group with heterogeneity I 2 = 67.33%, p ≤ 0.001. A meta-regression was done to investigate the potential source of heterogeneity among studies. The results showed that age ( p = 0.394), gender ( p = 0.164), and sample size ( p = 0.099) did not contribute to the source of heterogeneity, however, the burn surface area contributed significantly ( p = 0.002). A leave-one-out meta-analysis was done, showing that omitting Le Qui et al., leads to significantly decrease the heterogeneity to be I 2 = 2.73%. Meta-regression repeated to assess the burn surface area again to be found noncontributing ( p = 0.404). Conclusions Our findings support that elevated NLR values can serve as a mortality indicator in burn cases. This will have a great clinical impact by aiding in stratifying the burn patients on admission.
Year:
2024
Objectives: Examining the cumulative evidence from randomized controlled trials (RCTs), evaluating the use of pharmacological agents for the treatment of COVID‐19 infections in patients with critical illness. Data Sources: Databases Medline, Embase, Web of Science, Scopus, CINAHL, and Cochrane. Study Selection: Inclusion criteria were RCTs that enrolled patients with confirmed or suspected COVID‐19 infection who are critically ill. Only RCTs that examined therapeutic agents against one another or no intervention, placebo, or standard of care, were included. Data Extraction: Pairs of reviewers extracted data independently. Outcomes of interest included the overall reported mortality defined as either the ICU mortality, hospital mortality, mortality within 28 days or mortality within 90 days. Data Synthesis: A total of 40 studies (11,613 patients) evaluated 50 therapeutic intervention arms divided into five main therapy categories; steroids, antiviral medications, immunomodulators, plasma therapies [intravenous immunoglobulins (IVIG), convalescent plasma and/or, therapeutic plasma exchange], and therapeutic anticoagulation. Immunomodulators was the only group with possible mortality benefit, risk ratio (RR) 0.83 (95% CI 0.73; 0.95), with nonsignificant heterogeneity ( I 2 = 8%, p = 0.36). In contrast, the other therapy groups showed no significant impact on mortality, as indicated by their respective pooled RRs: steroids [RR 0.91 (95% CI 0.82; 1.01), I 2 = 31%], antiviral medications [RR 1.11 (95% CI 0.82; 1.49), I 2 = 57%], plasma therapies [RR 0.77 (95% CI 0.58; 1.01), I 2 = 36%], and anticoagulation [RR 1.06 (95% CI 0.95; 1.18), I 2 = 0%]. Conclusions: This meta‐analysis highlights both the heterogeneity and a lack of benefit from therapies evaluated during the COVID‐19 pandemic. Many of the RCTs were developed based on limited observational data. Future RCTs investigating pharmaceutical interventions in critically ill patients during pandemics need to be designed based on better evidence.
Year:
2024
Year:
2021
Year:
2020
Collaborators (3)
Amr Muhammad Abdo Salem
Lecturer
Ain Shams University
Jared Houghtaling
Assistant Professor
Tufts Medical Center
Chuan Hong
Duke University
Make your next move.
Prepare your application
Review drafts before you send them.