The use of artificial intelligence to detect voided medication orders in oral and maxillofacial surgery inpatients.

OBJECTIVE: The aim of this study is to determine if supervised machine learning algorithms can accurately predict voided computerized physician order entry in oral and maxillofacial surgery inpatients. METHODS: Data from Electronic Medical Record included patient demographics, comorbidities, procedures, vital signs, laboratory values, and medication orders were retrospectively collected. Predictor variables included patient demographics, comorbidities, procedures, vital signs, and laboratory values. Outcome of interest is if a medication order was voided or not. Data was cleaned and processed using Microsoft Excel and Python v3.12. Gradient Boosted Decision Trees, Random Forest, K-Nearest Neighbor, and Naïve Bayes were trained, validated, and tested for accuracy of the prediction of voided medication orders. RESULTS: 37,493 medication orders from 1,204 patient admissions over 5 years were used for this study. 3,892 (10.4%) medication orders were voided. Gradient Boosted Decision Trees, Random Forest, K-Nearest Neighbor, and Naïve Bayes had an Area Under the Receiver Operating Curve of 0.802 with 95% CI [0.787, 0.825], 0.746 with 95% CI [0.722, 0.765], 0.685 with 95% CI [0.667, 0.699], and 0.505 with 95% CI [0.489, 0.539], respectively. Area Under the Precision Recall Curve was 0.684 with 95% CI [0.679, 0.702], 0.647 with 95% CI [0.638, 0.664], 0.429 with 95% CI [0.417, 0.434], and 0.551 with 95% CI [0.551, 0.552], respectively. CONCLUSION: Gradient Boosted Decision Trees was the best performing model of the supervised machine learning algorithms with satisfactory outcomes in the test cohort for predicting voided Computerized Physician Order Entry in Oral and Maxillofacial Surgery inpatients.

Development and validation of a preliminary multivariable diagnostic model for identifying unusual infections in hospitalized patients.

Diagnostic delay leads to poor outcomes in infections, and it occurs more often when the causative agent is unusual. Delays are attributable to failing to consider such diagnoses in a timely fashion. Using routinely collected electronic health record (EHR) data, we built a preliminary multivariable diagnostic model for early identification of unusual fungal infections and tuberculosis in hospitalized patients. We conducted a two-gate case-control study. Cases encompassed adult patients admitted to 19 Mayo Clinic enterprise hospitals between January 2010 and March 2023 diagnosed with blastomycosis, cryptococcosis, histoplasmosis, mucormycosis, pneumocystosis, or tuberculosis. Control groups were drawn from all admitted patients (random controls) and those with community-acquired infections (ID-controls). Development and validation datasets were created using randomization for dividing cases and controls (7:3), with a secondary validation using ID-controls. A logistic regression model was constructed using baseline and laboratory variables, with the unusual infections of interest outcome. The derivation dataset comprised 1043 cases and 7000 random controls, while the 451 cases were compared to 3000 random controls and 1990 ID-controls for validation. Within the derivation dataset, the model achieved an area under the curve (AUC) of 0.88 (95% confidence interval [CI]: 0.87-0.89) with a good calibration accuracy (Hosmer-Lemeshow P = 0.623). Comparable performance was observed in the primary (AUC = 0.88; 95% CI: 0.86-0.9) and secondary validation datasets (AUC = 0.84; 95% CI: 0.82-0.86). In this multicenter study, an EHR-based preliminary diagnostic model accurately identified five unusual fungal infections and tuberculosis in hospitalized patients. With further validation, this model could help decrease time to diagnosis.

Applied Artificial Intelligence in Healthcare: A Review of Computer Vision Technology Application in Hospital Settings.

Computer vision (CV), a type of artificial intelligence (AI) that uses digital videos or a sequence of images to recognize content, has been used extensively across industries in recent years. However, in the healthcare industry, its applications are limited by factors like privacy, safety, and ethical concerns. Despite this, CV has the potential to improve patient monitoring, and system efficiencies, while reducing workload. In contrast to previous reviews, we focus on the end-user applications of CV. First, we briefly review and categorize CV applications in other industries (job enhancement, surveillance and monitoring, automation, and augmented reality). We then review the developments of CV in the hospital setting, outpatient, and community settings. The recent advances in monitoring delirium, pain and sedation, patient deterioration, mechanical ventilation, mobility, patient safety, surgical applications, quantification of workload in the hospital, and monitoring for patient events outside the hospital are highlighted. To identify opportunities for future applications, we also completed journey mapping at different system levels. Lastly, we discuss the privacy, safety, and ethical considerations associated with CV and outline processes in algorithm development and testing that limit CV expansion in healthcare. This comprehensive review highlights CV applications and ideas for its expanded use in healthcare.

Centralized Multipatient Dashboards' Impact on Intensive Care Unit Clinician Performance and Satisfaction: A Systematic Review.

BACKGROUND: Intensive care unit (ICU) clinicians encounter frequent challenges with managing vast amounts of fragmented data while caring for multiple critically ill patients simultaneously. This may lead to increased provider cognitive load that may jeopardize patient safety. OBJECTIVES: This systematic review assesses the impact of centralized multipatient dashboards on ICU clinician performance, perceptions regarding the use of these tools, and patient outcomes. METHODS: A literature search was conducted on February 9, 2023, using the EBSCO CINAHL, Cochrane Central Register of Controlled Trials, Embase, IEEE Xplore, MEDLINE, Scopus, and Web of Science Core Collection databases. Eligible studies that included ICU clinicians as participants and tested the effect of dashboards designed for use by multiple users to manage multiple patients on user performance and/or satisfaction compared with the standard practice. We narratively synthesized eligible studies following the SWiM (Synthesis Without Meta-analysis) guidelines. Studies were grouped based on dashboard type and outcomes assessed. RESULTS: The search yielded a total of 2,407 studies. Five studies met inclusion criteria and were included. Among these, three studies evaluated interactive displays in the ICU, one study assessed two dashboards in the pediatric ICU (PICU), and one study examined centralized monitor in the PICU. Most studies reported several positive outcomes, including reductions in data gathering time before rounds, a decrease in misrepresentations during multidisciplinary rounds, improved daily documentation compliance, faster decision-making, and user satisfaction. One study did not report any significant association. CONCLUSION: The multipatient dashboards were associated with improved ICU clinician performance and were positively perceived in most of the included studies. The risk of bias was high, and the certainty of evidence was very low, due to inconsistencies, imprecision, indirectness in the outcome measure, and methodological limitations. Designing and evaluating multipatient tools using robust research methodologies is an important focus for future research.

Automatic ARDS surveillance with chest X-ray recognition using convolutional neural networks.

OBJECTIVE: This study aims to design, validate and assess the accuracy a deep learning model capable of differentiation Chest X-Rays between pneumonia, acute respiratory distress syndrome (ARDS) and normal lungs. MATERIALS AND METHODS: A diagnostic performance study was conducted using Chest X-Ray images from adult patients admitted to a medical intensive care unit between January 2003 and November 2014. X-ray images from 15,899 patients were assigned one of three prespecified categories: "ARDS", "Pneumonia", or "Normal". RESULTS: A two-step convolutional neural network (CNN) pipeline was developed and tested to distinguish between the three patterns with sensitivity ranging from 91.8% to 97.8% and specificity ranging from 96.6% to 98.8%. The CNN model was validated with a sensitivity of 96.3% and specificity of 96.6% using a previous dataset of patients with Acute Lung Injury (ALI)/ARDS. DISCUSSION: The results suggest that a deep learning model based on chest x-ray pattern recognition can be a useful tool in distinguishing patients with ARDS from patients with normal lungs, providing faster results than digital surveillance tools based on text reports. CONCLUSION: A CNN-based deep learning model showed clinically significant performance, providing potential for faster ARDS identification. Future research should prospectively evaluate these tools in a clinical setting.

PROGNOSTIC PERFORMANCE OF SERIAL DETERMINATION OF THE SOCIETY FOR CARDIOVASCULAR ANGIOGRAPHY AND INTERVENTIONS SHOCK CLASSIFICATION IN ADULTS WITH CRITICAL ILLNESS.

ABSTRACT: Purpose: The aim of the study is to evaluate whether serial assessment of shock severity can improve prognostication in intensive care unit (ICU) patients. Materials and Methods: This is a retrospective cohort of 21,461 ICU patient admissions from 2014 to 2018. We assigned the Society for Cardiovascular Angiography and Interventions (SCAI) Shock Stage in each 4-h block during the first 24 h of ICU admission; shock was defined as SCAI Shock stage C, D, or E. In-hospital mortality was evaluated using logistic regression. Results: The admission SCAI Shock stages were as follows: A, 39.0%; B, 27.0%; C, 28.9%; D, 2.6%; and E, 2.5%. The SCAI Shock stage subsequently increased in 30.6%, and late-onset shock developed in 30.4%. In-hospital mortality was higher in patients who had shock on admission (11.9%) or late-onset shock (7.3%) versus no shock (4.3%). Persistence of shock predicted higher mortality (adjusted OR = 1.09; 95% CI = 1.06-1.13, for each ICU block with shock). The mean SCAI Shock stage had higher discrimination for in-hospital mortality than the admission or maximum SCAI Shock stage. Dynamic modeling of the SCAI Shock classification improved discrimination for in-hospital mortality (C-statistic = 0.64-0.71). Conclusions: Serial application of the SCAI Shock classification provides improved mortality risk stratification compared with a single assessment on admission, facilitating dynamic prognostication.

TCCC Decision Support With Machine Learning Prediction of Hemorrhage Risk, Shock Probability.

INTRODUCTION: Expected future delays in evacuation during near-peer conflicts in remote locales are expected to require extended care including prolonged field care over hours to days. Such delays can increase potential complications, such as insufficient blood flow (shock), bloodstream infection (sepsis), internal bleeding (hemorrhage), and require more complex treatment beyond stabilization. The Trauma Triage Treatment and Training Decision Support (4TDS) system is a real-time decision support system to monitor casualty health and identify such complications. The 4TDS software prototype operates on an Android smart phone or tablet configured for use in the DoD Nett Warrior program. It includes machine learning models to evaluate trends in six vital signs streamed from a sensor placed on a casualty to identify shock probability, internal hemorrhage risk, and need for a massive transfusion. MATERIALS AND METHODS: The project team used a mixed methods approach to create and evaluate the system including literature review, rapid prototyping, design requirements review, agile development, an algorithm "silent test," and usability assessments with novice to expert medics from all three services. RESULTS: Both models, shock (showing an accuracy of 0.83) and hemorrhage/massive transfusion protocol, were successfully validated using externally collected data. All usability assessment participants completed refresher training scenarios and were able to accurately assess a simulated casualty's condition using the phone prototype. Mean responses to statements on evaluation criteria [e.g., fit with Tactical Combat Casualty Care (TCCC), ease of use, and decision confidence] fell at five or above on a 7-point scale, indicating strong support. CONCLUSIONS: Participatory design ensured 4TDS and machine learning models reflect medic and clinician mental models and work processes and built support among potential users should the system transition to operational use. Validation results can support 4TDS readiness for FDA 510k clearance as a Class II medical device.

Machine Learning for Automated Classification of Abnormal Lung Sounds Obtained from Public Databases: A Systematic Review.

Pulmonary auscultation is essential for detecting abnormal lung sounds during physical assessments, but its reliability depends on the operator. Machine learning (ML) models offer an alternative by automatically classifying lung sounds. ML models require substantial data, and public databases aim to address this limitation. This systematic review compares characteristics, diagnostic accuracy, concerns, and data sources of existing models in the literature. Papers published from five major databases between 1990 and 2022 were assessed. Quality assessment was accomplished with a modified QUADAS-2 tool. The review encompassed 62 studies utilizing ML models and public-access databases for lung sound classification. Artificial neural networks (ANN) and support vector machines (SVM) were frequently employed in the ML classifiers. The accuracy ranged from 49.43% to 100% for discriminating abnormal sound types and 69.40% to 99.62% for disease class classification. Seventeen public databases were identified, with the ICBHI 2017 database being the most used (66%). The majority of studies exhibited a high risk of bias and concerns related to patient selection and reference standards. Summarizing, ML models can effectively classify abnormal lung sounds using publicly available data sources. Nevertheless, inconsistent reporting and methodologies pose limitations to advancing the field, and therefore, public databases should adhere to standardized recording and labeling procedures.

Shock Severity Classification and Mortality in Adults With Cardiac, Medical, Surgical, and Neurological Critical Illness.

OBJECTIVE: To evaluate whether the Society for Cardiovascular Angiography and Interventions (SCAI) Shock Classification could perform risk stratification in a mixed cohort of intensive care unit (ICU) patients, similar to its validation in patients with acute cardiac disease. METHODS: We included 21,461 adult Mayo Clinic ICU patient admissions from December 1, 2014, to February 28, 2018, including cardiac ICU (16.7%), medical ICU (37.4%), neurosciences ICU (27.7%), and surgical ICU (18.2%). The SCAI Shock Classification (a 5-stage classification from no shock [A] to refractory shock [E]) was assigned in each 4-hour period during the first 24 hours of ICU admission. RESULTS: The median age was 65 years, and 43.2% were female. In-hospital mortality occurred in 1611 (7.5%) patients, with a stepwise increase in in-hospital mortality in each higher maximum SCAI Shock stage overall: A, 4.0%; B, 4.6%; C, 7.0%; D, 13.9%; and E, 40.2%. The SCAI Shock Classification provided incremental mortality risk stratification in each ICU, with the best performance in the cardiac ICU and the worse performance in the neurosciences ICU. The SCAI Shock Classification was associated with higher adjusted in-hospital mortality (adjusted odds ratio, 1.32 per each stage; 95% CI, 1.24 to 1.41; P<.001); this association was not observed in the neurosciences ICU when considered separately. CONCLUSION: The SCAI Shock Classification provided incremental mortality risk stratification beyond established prognostic markers across the spectrum of medical and surgical critical illness, proving utility outside its original intent.

Validation of automated data abstraction for SCCM discovery VIRUS COVID-19 registry: practical EHR export pathways (VIRUS-PEEP).

Background: The gold standard for gathering data from electronic health records (EHR) has been manual data extraction; however, this requires vast resources and personnel. Automation of this process reduces resource burdens and expands research opportunities. Objective: This study aimed to determine the feasibility and reliability of automated data extraction in a large registry of adult COVID-19 patients. Materials and methods: This observational study included data from sites participating in the SCCM Discovery VIRUS COVID-19 registry. Important demographic, comorbidity, and outcome variables were chosen for manual and automated extraction for the feasibility dataset. We quantified the degree of agreement with Cohen's kappa statistics for categorical variables. The sensitivity and specificity were also assessed. Correlations for continuous variables were assessed with Pearson's correlation coefficient and Bland-Altman plots. The strength of agreement was defined as almost perfect (0.81-1.00), substantial (0.61-0.80), and moderate (0.41-0.60) based on kappa statistics. Pearson correlations were classified as trivial (0.00-0.30), low (0.30-0.50), moderate (0.50-0.70), high (0.70-0.90), and extremely high (0.90-1.00). Measurements and main results: The cohort included 652 patients from 11 sites. The agreement between manual and automated extraction for categorical variables was almost perfect in 13 (72.2%) variables (Race, Ethnicity, Sex, Coronary Artery Disease, Hypertension, Congestive Heart Failure, Asthma, Diabetes Mellitus, ICU admission rate, IMV rate, HFNC rate, ICU and Hospital Discharge Status), and substantial in five (27.8%) (COPD, CKD, Dyslipidemia/Hyperlipidemia, NIMV, and ECMO rate). The correlations were extremely high in three (42.9%) variables (age, weight, and hospital LOS) and high in four (57.1%) of the continuous variables (Height, Days to ICU admission, ICU LOS, and IMV days). The average sensitivity and specificity for the categorical data were 90.7 and 96.9%. Conclusion and relevance: Our study confirms the feasibility and validity of an automated process to gather data from the EHR.

Rates Among Hospitalized Patients With COVID-19 Treated With Convalescent Plasma: A Systematic Review and Meta-Analysis.

Objective: To examine the association of COVID-19 convalescent plasma transfusion with mortality and the differences between subgroups in hospitalized patients with COVID-19. Patients and Methods: On October 26, 2022, a systematic search was performed for clinical studies of COVID-19 convalescent plasma in the literature from January 1, 2020, to October 26, 2022. Randomized clinical trials and matched cohort studies investigating COVID-19 convalescent plasma transfusion compared with standard of care treatment or placebo among hospitalized patients with confirmed COVID-19 were included. The electronic search yielded 3841 unique records, of which 744 were considered for full-text screening. The selection process was performed independently by a panel of 5 reviewers. The study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Data were extracted by 5 independent reviewers in duplicate and pooled using an inverse-variance random effects model. The prespecified end point was all-cause mortality during hospitalization. Results: Thirty-nine randomized clinical trials enrolling 21,529 participants and 70 matched cohort studies enrolling 50,160 participants were included in the systematic review. Separate meta-analyses reported that transfusion of COVID-19 convalescent plasma was associated with a decrease in mortality compared with the control cohort for both randomized clinical trials (odds ratio [OR], 0.87; 95% CI, 0.76-1.00) and matched cohort studies (OR, 0.76; 95% CI, 0.66-0.88). The meta-analysis of subgroups revealed 2 important findings. First, treatment with convalescent plasma containing high antibody levels was associated with a decrease in mortality compared with convalescent plasma containing low antibody levels (OR, 0.85; 95% CI, 0.73 to 0.99). Second, earlier treatment with COVID-19 convalescent plasma was associated with a decrease in mortality compared with the later treatment cohort (OR, 0.63; 95% CI, 0.48 to 0.82). Conclusion: During COVID-19 convalescent plasma use was associated with a 13% reduced risk of mortality, implying a mortality benefit for hospitalized patients with COVID-19, particularly those treated with convalescent plasma containing high antibody levels treated earlier in the disease course.

Predicting sepsis onset using a machine learned causal probabilistic network algorithm based on electronic health records data.

Sepsis is a leading cause of mortality and early identification improves survival. With increasing digitalization of health care data automated sepsis prediction models hold promise to aid in prompt recognition. Most previous studies have focused on the intensive care unit (ICU) setting. Yet only a small proportion of sepsis develops in the ICU and there is an apparent clinical benefit to identify patients earlier in the disease trajectory. In this cohort of 82,852 hospital admissions and 8038 sepsis episodes classified according to the Sepsis-3 criteria, we demonstrate that a machine learned score can predict sepsis onset within 48 h using sparse routine electronic health record data outside the ICU. Our score was based on a causal probabilistic network model-SepsisFinder-which has similarities with clinical reasoning. A prediction was generated hourly on all admissions, providing a new variable was registered. Compared to the National Early Warning Score (NEWS2), which is an established method to identify sepsis, the SepsisFinder triggered earlier and had a higher area under receiver operating characteristic curve (AUROC) (0.950 vs. 0.872), as well as area under precision-recall curve (APR) (0.189 vs. 0.149). A machine learning comparator based on a gradient-boosting decision tree model had similar AUROC (0.949) and higher APR (0.239) than SepsisFinder but triggered later than both NEWS2 and SepsisFinder. The precision of SepsisFinder increased if screening was restricted to the earlier admission period and in episodes with bloodstream infection. Furthermore, the SepsisFinder signaled median 5.5 h prior to antibiotic administration. Identifying a high-risk population with this method could be used to tailor clinical interventions and improve patient care.

Who needs clinician attention first? A qualitative study of critical care clinicians' needs that enable the prioritization of care for populations of acutely ill patients.

BACKGROUND: To adequately care for groups of acutely ill patients, clinicians maintain situational awareness to identify the most acute needs within the entire intensive care unit (ICU) population through constant reappraisal of patient data from electronic medical record and other information sources. Our objective was to understand the information and process requirements of clinicians caring for multiple ICU patients and how this information is used to support their prioritization of care among populations of acutely ill patients. Additionally, we wanted to gather insights on the organization of an Acute care multi-patient viewer (AMP) dashboard. METHODS: We conducted and audio-recorded semi-structured interviews of ICU clinicians who had worked with the AMP in three quaternary care hospitals. The transcripts were analyzed with open, axial, and selective coding. Data was managed using NVivo 12 software. RESULTS: We interviewed 20 clinicians and identified 5 main themes following data analysis: (1) strategies used to enable patient prioritization, (2) strategies used for optimizing task organization, (3) information and factors helpful for situational awareness within the ICU, (4) unrecognized or missed critical events and information, and (5) suggestions for AMP organization and content. Prioritization of critical care was largely determined by severity of illness and trajectory of patient clinical status. Important sources of information were communication with colleagues from the previous shift, bedside nurses, and patients, data from the electronic medical record and AMP, and physical presence and availability in the ICU. CONCLUSIONS: This qualitative study explored ICU clinicians' information and process requirements to enable the prioritization of care among populations of acutely ill patients. Timely recognition of patients who need priority attention and intervention provides opportunities for improvement of critical care and for preventing catastrophic events in the ICU.

Evaluation of Digital Health Strategy to Support Clinician-Led Critically Ill Patient Population Management: A Randomized Crossover Study.

To investigate whether a novel acute care multipatient viewer (AMP), created with an understanding of clinician information and process requirements, could reduce time to clinical decision-making among clinicians caring for populations of acutely ill patients compared with a widely used commercial electronic medical record (EMR). DESIGN: Single center randomized crossover study. SETTING: Quaternary care academic hospital. SUBJECTS: Attending and in-training critical care physicians, and advanced practice providers. INTERVENTIONS: AMP. MEASUREMENTS AND MAIN RESULTS: We compared ICU clinician performance in structured clinical task completion using two electronic environments-the standard commercial EMR (Epic) versus the novel AMP in addition to Epic. Twenty subjects (10 pairs of clinicians) participated in the study. During the study session, each participant completed the tasks on two ICUs (7-10 beds each) and eight individual patients. The adjusted time for assessment of the entire ICU and the adjusted total time to task completion were significantly lower using AMP versus standard commercial EMR (-6.11; 95% CI, -7.91 to -4.30 min and -5.38; 95% CI, -7.56 to -3.20 min, respectively; p < 0.001). The adjusted time for assessment of individual patients was similar using both the EMR and AMP (0.73; 95% CI, -0.09 to 1.54 min; p = 0.078). AMP was associated with a significantly lower adjusted task load (National Aeronautics and Space Administration-Task Load Index) among clinicians performing the task versus the standard EMR (22.6; 95% CI, -32.7 to -12.4 points; p < 0.001). There was no statistically significant difference in adjusted total errors when comparing the two environments (0.68; 95% CI, 0.36-1.30; p = 0.078). CONCLUSIONS: When compared with the standard EMR, AMP significantly reduced time to assessment of an entire ICU, total time to clinical task completion, and clinician task load. Additional research is needed to assess the clinicians' performance while using AMP in the live ICU setting.

Time to diagnostic certainty for saddle pulmonary embolism in hospitalized patients.

There is a lack of diagnostic performance measures associated with pulmonary embolism (PE). We aimed to explore the concept of the time to diagnostic certainty, which we defined as the time interval that elapses between first presentation of a patient to a confirmed PE diagnosis with computed tomography pulmonary angiogram (CT PA). This approach could be used to highlight variability in health system diagnostic performance, and to select patient outliers for structured chart review in order to identify underlying contributors to diagnostic error or delay. We performed a retrospective observational study at academic medical centers and associated community-based hospitals in one health system, examining randomly selected adult patients admitted to study sites with a diagnosis of acute saddle PE. One hundred patients were randomly selected from 340 patients discharged with saddle PE. Twenty-four patients were excluded. Among the 76 included patients, time to diagnostic certainty ranged from 1.5 to 310 hours. We found that 73/76 patients were considered to have PE present on admission (CT PA ≤ 48 hours). The proportion of patients with PE present on admission with time to diagnostic certainty of > 6 hours was 26% (19/73). The median (IQR) time to treatment (thrombolytics/anticoagulants) was 3.5 (2.5-5.1) hours among the 73 patients. The proportion of patients with PE present on admission with treatment delays of > 6 hours was 16% (12/73). Three patients acquired PE during hospitalization (CT PA > 48 hours). In this study, we developed and successfully tested the concept of time to diagnostic certainty for saddle PE.

Effect of an Artificial Intelligence Decision Support Tool on Palliative Care Referral in Hospitalized Patients: A Randomized Clinical Trial.

CONTEXT: Palliative care services are commonly provided to hospitalized patients, but accurately predicting who needs them remains a challenge. OBJECTIVES: To assess the effectiveness on clinical outcomes of an artificial intelligence (AI)/machine learning (ML) decision support tool for predicting patient need for palliative care services in the hospital. METHODS: The study design was a pragmatic, cluster-randomized, stepped-wedge clinical trial in 12 nursing units at two hospitals over a 15-month period between August 19, 2019, and November 17, 2020. Eligible patients were randomly assigned to either a medical service consultation recommendation triggered by an AI/ML tool predicting the need for palliative care services or usual care. The primary outcome was palliative care consultation note. Secondary outcomes included: hospital readmissions, length of stay, transfer to intensive care and palliative care consultation note by unit. RESULTS: A total of 3183 patient hospitalizations were enrolled. Of eligible patients, A total of 2544 patients were randomized to the decision support tool (1212; 48%) and usual care (1332; 52%). Of these, 1717 patients (67%) were retained for analyses. Patients randomized to the intervention had a statistically significant higher incidence rate of palliative care consultation compared to the control group (IRR, 1.44 [95% CI, 1.11-1.92]). Exploratory evidence suggested that the decision support tool group reduced 60-day and 90-day hospital readmissions (OR, 0.75 [95% CI, 0.57, 0.97]) and (OR, 0.72 [95% CI, 0.55-0.93]) respectively. CONCLUSION: A decision support tool integrated into palliative care practice and leveraging AI/ML demonstrated an increased palliative care consultation rate among hospitalized patients and reductions in hospitalizations.

Diagnostic delay in pulmonary blastomycosis: a case series reflecting a referral center experience.

PURPOSE: The diagnosis of pulmonary blastomycosis is usually delayed because of its non-specific presentation. We aimed to assess the extent of diagnostic delay in hospitalized patients and detect the step in the diagnostic process that requires the most improvement. METHODS: Adult patients diagnosed with pulmonary blastomycosis during a hospital admission between January 2010 through November 2021 were eligible for inclusion. Patients who did not have pulmonary involvement and who were diagnosed before admission were excluded. Demographics and comorbid conditions, specifics of disease presentation, and interventions were evaluated. The timing of the diagnosis, antifungal treatment, and patient outcomes were noted. Descriptive analytical tests were performed. RESULTS: A total of 43 patients were diagnosed with pulmonary blastomycosis during their admissions. The median age was 47 years, with 13 (30%) females. Of all patients, 29 (67%) had isolated pulmonary infection, while 14 (33%) had disseminated disease, affecting mostly skin and musculoskeletal system. The median duration between the initial symptoms and health care encounters was 4 days, and the time to hospital admission was 9 days. The median duration from the initial symptoms to the diagnosis was 20 days. Forty patients (93%) were treated with empirical antibacterials before a definitive diagnosis was made. In addition, corticosteroid treatment was empirically administered to 15 patients (35%) before the diagnosis, with indications such as suspicion of inflammatory processes or symptom relief. In 38 patients (88%), the first performed fungal diagnostic test was positive. Nineteen patients (44%) required admission to the intensive care unit, and 11 patients (26%) died during their hospital stay. CONCLUSION: There was a delay in diagnosis of patients with pulmonary blastomycosis, largely attributable to the lack of consideration of the etiological agent. Novel approaches to assist providers in recognizing the illness earlier and trigger evaluation are needed.

Association of Blood Pressure Variability with Delirium in Patients with Critical Illness.

BACKGROUND: The objective was to examine the association of blood pressure variability (BPV) during the first 24 h after intensive care unit admission with the likelihood of delirium and depressed alertness without delirium ("depressed alertness"). METHODS: This retrospective, observational, cohort study included all consecutive adult patients admitted to an intensive care unit at Mayo Clinic, Rochester, Minnesota, from July 1, 2004, through October 31, 2015. The primary outcomes were delirium and delirium-free days, and the secondary outcomes included depressed alertness and depressed alertness-free days. Logistic regression was performed to determine the association of BPV with delirium and depressed alertness. Proportional odds regression was used to assess the association of BPV with delirium-free days and depressed alertness-free days. RESULTS: Among 66,549 intensive care unit admissions, delirium was documented in 20.2% and depressed alertness was documented in 24.4%. Preserved cognition was documented in 55.4% of intensive care unit admissions. Increased systolic and diastolic BPV was associated with an increased odds of delirium and depressed alertness. The magnitude of the association per 5-mm Hg increase in systolic average real variability (the average of absolute value of changes between consecutive systolic blood pressure readings) was greater for delirium (odds ratio 1.34; 95% confidence interval 1.29-1.40; P < 0.001) than for depressed alertness (odds ratio 1.06; 95% confidence interval 1.02-1.10; P = 0.004). Increased systolic and diastolic BPV was associated with fewer delirium-free days but not with depressed alertness-free days. CONCLUSIONS: BPV in the first 24 h after intensive care unit admission is associated with an increased likelihood of delirium and fewer delirium-free days.

Effects of Image Quality on the Accuracy Human Pose Estimation and Detection of Eye Lid Opening/Closing Using Openpose and DLib.

OBJECTIVE: The application of computer models in continuous patient activity monitoring using video cameras is complicated by the capture of images of varying qualities due to poor lighting conditions and lower image resolutions. Insufficient literature has assessed the effects of image resolution, color depth, noise level, and low light on the inference of eye opening and closing and body landmarks from digital images. METHOD: This study systematically assessed the effects of varying image resolutions (from 100 × 100 pixels to 20 × 20 pixels at an interval of 10 pixels), lighting conditions (from 42 to 2 lux with an interval of 2 lux), color-depths (from 16.7 M colors to 8 M, 1 M, 512 K, 216 K, 64 K, 8 K, 1 K, 729, 512, 343, 216, 125, 64, 27, and 8 colors), and noise levels on the accuracy and model performance in eye dimension estimation and body keypoint localization using the Dlib library and OpenPose with images from the Closed Eyes in the Wild and the COCO datasets, as well as photographs of the face captured at different light intensities. RESULTS: The model accuracy and rate of model failure remained acceptable at an image resolution of 60 × 60 pixels, a color depth of 343 colors, a light intensity of 14 lux, and a Gaussian noise level of 4% (i.e., 4% of pixels replaced by Gaussian noise). CONCLUSIONS: The Dlib and OpenPose models failed to detect eye dimensions and body keypoints only at low image resolutions, lighting conditions, and color depths. CLINICAL IMPACT: Our established baseline threshold values will be useful for future work in the application of computer vision in continuous patient monitoring.

Information and Data Visualization Needs among Direct Care Nurses in the Intensive Care Unit.

OBJECTIVES: Intensive care unit (ICU) direct care nurses spend 22% of their shift completing tasks within the electronic health record (EHR). Miscommunications and inefficiencies occur, particularly during patient hand-off, placing patient safety at risk. Redesigning how direct care nurses visualize and interact with patient information during hand-off is one opportunity to improve EHR use. A web-based survey was deployed to better understand the information and visualization needs at patient hand-off to inform redesign. METHODS: A multicenter anonymous web-based survey of direct care ICU nurses was conducted (9-12/2021). Semi-structured interviews with stakeholders informed survey development. The primary outcome was identifying primary EHR data needs at patient hand-off for inclusion in future EHR visualization and interface development. Secondary outcomes included current use of the EHR at patient hand-off, EHR satisfaction, and visualization preferences. Frequencies, means, and medians were calculated for each data item then ranked in descending order to generate proportional quarters using SAS v9.4. RESULTS: In total, 107 direct care ICU nurses completed the survey. The majority (46%, n = 49/107) use the EHR at patient hand-off to verify exchanged verbal information. Sixty-four percent (n = 68/107) indicated that current EHR visualization was insufficient. At the start of an ICU shift, primary EHR data needs included hemodynamics (mean 4.89 ± 0.37, 98%, n = 105), continuous IV medications (4.55 ± 0.73, 93%, n = 99), laboratory results (4.60 ± 0.56, 96%, n = 103), mechanical circulatory support devices (4.62 ± 0.72, 90%, n = 97), code status (4.40 ± 0.85, 59%, n = 108), and ventilation status (4.35 + 0.79, 51%, n = 108). Secondary outcomes included mean EHR satisfaction of 65 (0-100 scale, standard deviation = ± 21) and preferred future EHR user-interfaces to be organized by organ system (53%, n = 57/107) and visualized by tasks/schedule (61%, n = 65/107). CONCLUSION: We identified information and visualization needs of direct care ICU nurses. The study findings could serve as a baseline toward redesigning an EHR interface.