Postoperative Overtriage to an Intensive Care Unit Is Associated With Low Value of Care.

OBJECTIVE: We test the hypothesis that for low-acuity surgical patients, postoperative intensive care unit (ICU) admission is associated with lower value of care compared with ward admission. BACKGROUND: Overtriaging low-acuity patients to ICU consumes valuable resources and may not confer better patient outcomes. Associations among postoperative overtriage, patient outcomes, costs, and value of care have not been previously reported. METHODS: In this longitudinal cohort study, postoperative ICU admissions were classified as overtriaged or appropriately triaged according to machine learning-based patient acuity assessments and requirements for immediate postoperative mechanical ventilation or vasopressor support. The nearest neighbors algorithm identified risk-matched control ward admissions. The primary outcome was value of care, calculated as inverse observed-to-expected mortality ratios divided by total costs. RESULTS: Acuity assessments had an area under the receiver operating characteristic curve of 0.92 in generating predictions for triage classifications. Of 8592 postoperative ICU admissions, 423 (4.9%) were overtriaged. These were matched with 2155 control ward admissions with similar comorbidities, incidence of emergent surgery, immediate postoperative vital signs, and do not resuscitate order placement and rescindment patterns. Compared with controls, overtraiged admissions did not have a lower incidence of any measured complications. Total costs for admission were $16.4K for overtriage and $15.9K for controls ( P =0.03). Value of care was lower for overtriaged admissions [2.9 (2.0-4.0)] compared with controls [24.2 (14.1-34.5), P <0.001]. CONCLUSIONS: Low-acuity postoperative patients who were overtriaged to ICUs had increased total costs, no improvements in outcomes, and received low-value care.

Aligning Patient Acuity With Resource Intensity After Major Surgery: A Scoping Review.

OBJECTIVE: Develop unifying definitions and paradigms for data-driven methods to augment postoperative resource intensity decisions. SUMMARY BACKGROUND DATA: Postoperative level-of-care assignments and frequency of vital sign and laboratory measurements (ie, resource intensity) should align with patient acuity. Effective, data-driven decision-support platforms could improve value of care for millions of patients annually, but their development is hindered by the lack of salient definitions and paradigms. METHODS: Embase, PubMed, and Web of Science were searched for articles describing patient acuity and resource intensity after inpatient surgery. Study quality was assessed using validated tools. Thirty-five studies were included and assimilated according to PRISMA guidelines. RESULTS: Perioperative patient acuity is accurately represented by combinations of demographic, physiologic, and hospital-system variables as input features in models that capture complex, non-linear relationships. Intraoperative physiologic data enriche these representations. Triaging high-acuity patients to low-intensity care is associated with increased risk for mortality; triaging low-acuity patients to intensive care units (ICUs) has low value and imparts harm when other, valid requests for ICU admission are denied due to resource limitations, increasing their risk for unrecognized decompensation and failure-to-rescue. Providing high-intensity care for low-acuity patients may also confer harm through unnecessary testing and subsequent treatment of incidental findings, but there is insufficient evidence to evaluate this hypothesis. Compared with data-driven models, clinicians exhibit volatile performance in predicting complications and making postoperative resource intensity decisions. CONCLUSION: To optimize value, postoperative resource intensity decisions should align with precise, data-driven patient acuity assessments augmented by models that accurately represent complex, non-linear relationships among risk factors.

Early Biomarker Signatures in Surgical Sepsis.

INTRODUCTION: Sepsis has complex, time-sensitive pathophysiology and important phenotypic subgroups. The objective of this study was to use machine learning analyses of blood and urine biomarker profiles to elucidate the pathophysiologic signatures of subgroups of surgical sepsis patients. METHODS: This prospective cohort study included 243 surgical sepsis patients admitted to a quaternary care center between January 2015 and June 2017. We applied hierarchical clustering to clinical variables and 42 blood and urine biomarkers to identify phenotypic subgroups in a development cohort. Clinical characteristics and short-term and long-term outcomes were compared between clusters. A naïve Bayes classifier predicted cluster labels in a validation cohort. RESULTS: The development cohort contained one cluster characterized by early organ dysfunction (cluster I, n = 18) and one cluster characterized by recovery (cluster II, n = 139). Cluster I was associated with higher Acute Physiologic Assessment and Chronic Health Evaluation II (30 versus 16, P < 0.001) and SOFA scores (13 versus 5, P < 0.001), greater prevalence of chronic cardiovascular and renal disease (P < 0.001) and septic shock (78% versus 17%, P < 0.001). Cluster I had higher mortality within 14 d of sepsis onset (11% versus 1.5%, P = 0.001) and within 1 y (44% versus 20%, P = 0.032), and higher incidence of chronic critical illness (61% versus 30%, P = 0.001). The Bayes classifier achieved 95% accuracy and identified two clusters that were similar to development cohort clusters. CONCLUSIONS: Machine learning analyses of clinical and biomarker variables identified an early organ dysfunction sepsis phenotype characterized by inflammation, renal dysfunction, endotheliopathy, and immunosuppression, as well as poor short-term and long-term clinical outcomes.

Patient and Procedural Determinants of Postoperative Pain Trajectories.

BACKGROUND: The primary goal of this study was to evaluate patterns in acute postoperative pain in a mixed surgical patient cohort with the hypothesis that there would be heterogeneity in these patterns. METHODS: This study included 360 patients from a mixed surgical cohort whose pain was measured across postoperative days 1 through 7. Pain was characterized using the Brief Pain Inventory. Primary analysis used group-based trajectory modeling to estimate trajectories/patterns of postoperative pain. Secondary analysis examined associations between sociodemographic, clinical, and behavioral patient factors and pain trajectories. RESULTS: Five distinct postoperative pain trajectories were identified. Many patients (167 of 360, 46%) were in the moderate-to-high pain group, followed by the moderate-to-low (88 of 360, 24%), high (58 of 360, 17%), low (25 of 360, 7%), and decreasing (21 of 360, 6%) pain groups. Lower age (odds ratio, 0.94; 95% CI, 0.91 to 0.99), female sex (odds ratio, 6.5; 95% CI, 1.49 to 15.6), higher anxiety (odds ratio, 1.08; 95% CI, 1.01 to 1.14), and more pain behaviors (odds ratio, 1.10; 95% CI, 1.02 to 1.18) were related to increased likelihood of being in the high pain trajectory in multivariable analysis. Preoperative and intraoperative opioids were not associated with postoperative pain trajectories. Pain trajectory group was, however, associated with postoperative opioid use (P < 0.001), with the high pain group (249.5 oral morphine milligram equivalents) requiring four times more opioids than the low pain group (60.0 oral morphine milligram equivalents). CONCLUSIONS: There are multiple distinct acute postoperative pain intensity trajectories, with 63% of patients reporting stable and sustained high or moderate-to-high pain over the first 7 days after surgery. These postoperative pain trajectories were predominantly defined by patient factors and not surgical factors.

Slow Dynamics of Acute Postoperative Pain Intensity Time Series Determined via Wavelet Analysis Are Associated With the Risk of Severe Postoperative Day 30 Pain.

BACKGROUND: Evidence suggests that increased early postoperative pain (POP) intensities are associated with increased pain in the weeks following surgery. However, it remains unclear which temporal aspects of this early POP relate to later pain experience. In this prospective cohort study, we used wavelet analysis of clinically captured POP intensity data on postoperative days 1 and 2 to characterize slow/fast dynamics of POP intensities and predict pain outcomes on postoperative day 30. METHODS: The study used clinical POP time series from the first 48 hours following surgery from 218 patients to predict their mean POP on postoperative day 30. We first used wavelet analysis to approximate the POP series and to represent the series at different time scales to characterize the early temporal profile of acute POP in the first 2 postoperative days. We then used the wavelet coefficients alongside demographic parameters as inputs to a neural network to predict the risk of severe pain 30 days after surgery. RESULTS: Slow dynamic approximation components, but not fast dynamic detailed components, were linked to pain intensity on postoperative day 30. Despite imbalanced outcome rates, using wavelet decomposition along with a neural network for classification, the model achieved an F score of 0.79 and area under the receiver operating characteristic curve of 0.74 on test-set data for classifying pain intensities on postoperative day 30. The wavelet-based approach outperformed logistic regression (F score of 0.31) and neural network (F score of 0.22) classifiers that were restricted to sociodemographic variables and linear trajectories of pain intensities. CONCLUSIONS: These findings identify latent mechanistic information within the temporal domain of clinically documented acute POP intensity ratings, which are accessible via wavelet analysis, and demonstrate that such temporal patterns inform pain outcomes at postoperative day 30.

Intelligent, Autonomous Machines in Surgery.

Surgeons perform two primary tasks: operating and engaging patients and caregivers in shared decision-making. Human dexterity and decision-making are biologically limited. Intelligent, autonomous machines have the potential to augment or replace surgeons. Rather than regarding this possibility with denial, ire, or indifference, surgeons should understand and steer these technologies. Closer examination of surgical innovations and lessons learned from the automotive industry can inform this process. Innovations in minimally invasive surgery and surgical decision-making follow classic S-shaped curves with three phases: (1) introduction of a new technology, (2) achievement of a performance advantage relative to existing standards, and (3) arrival at a performance plateau, followed by replacement with an innovation featuring greater machine autonomy and less human influence. There is currently no level I evidence demonstrating improved patient outcomes using intelligent, autonomous machines for performing operations or surgical decision-making tasks. History suggests that if such evidence emerges and if the machines are cost effective, then they will augment or replace humans, initially for simple, common, rote tasks under close human supervision and later for complex tasks with minimal human supervision. This process poses ethical challenges in assigning liability for errors, matching decisions to patient values, and displacing human workers, but may allow surgeons to spend less time gathering and analyzing data and more time interacting with patients and tending to urgent, critical-and potentially more valuable-aspects of patient care. Surgeons should steer these technologies toward optimal patient care and net social benefit using the uniquely human traits of creativity, altruism, and moral deliberation.

Added Value of Intraoperative Data for Predicting Postoperative Complications: The MySurgeryRisk PostOp Extension.

BACKGROUND: Models that predict postoperative complications often ignore important intraoperative events and physiological changes. This study tested the hypothesis that accuracy, discrimination, and precision in predicting postoperative complications would improve when using both preoperative and intraoperative data input data compared with preoperative data alone. METHODS: This retrospective cohort analysis included 43,943 adults undergoing 52,529 inpatient surgeries at a single institution during a 5-y period. Random forest machine learning models in the validated MySurgeryRisk platform made patient-level predictions for seven postoperative complications and mortality occurring during hospital admission using electronic health record data and patient neighborhood characteristics. For each outcome, one model trained with preoperative data alone; one model trained with both preoperative and intraoperative data. Models were compared by accuracy, discrimination (expressed as area under the receiver operating characteristic curve), precision (expressed as area under the precision-recall curve), and reclassification indices. RESULTS: Machine learning models incorporating both preoperative and intraoperative data had greater accuracy, discrimination, and precision than models using preoperative data alone for predicting all seven postoperative complications (intensive care unit length of stay >48 h, mechanical ventilation >48 h, neurologic complications including delirium, cardiovascular complications, acute kidney injury, venous thromboembolism, and wound complications), and in-hospital mortality (accuracy: 88% versus 77%; area under the receiver operating characteristic curve: 0.93 versus 0.87; area under the precision-recall curve: 0.21 versus 0.15). Overall reclassification improvement was 2.4%-10.0% for complications and 11.2% for in-hospital mortality. CONCLUSIONS: Incorporating both preoperative and intraoperative data significantly increased the accuracy, discrimination, and precision of machine learning models predicting postoperative complications and mortality.

Forty-two Million Ways to Describe Pain: Topic Modeling of 200,000 PubMed Pain-Related Abstracts Using Natural Language Processing and Deep Learning-Based Text Generation.

OBJECTIVE: Recent efforts to update the definitions and taxonomic structure of concepts related to pain have revealed opportunities to better quantify topics of existing pain research subject areas. METHODS: Here, we apply basic natural language processing (NLP) analyses on a corpus of >200,000 abstracts published on PubMed under the medical subject heading (MeSH) of "pain" to quantify the topics, content, and themes on pain-related research dating back to the 1940s. RESULTS: The most common stemmed terms included "pain" (601,122 occurrences), "patient" (508,064 occurrences), and "studi-" (208,839 occurrences). Contrarily, terms with the highest term frequency-inverse document frequency included "tmd" (6.21), "qol" (6.01), and "endometriosis" (5.94). Using the vector-embedded model of term definitions available via the "word2vec" technique, the most similar terms to "pain" included "discomfort," "symptom," and "pain-related." For the term "acute," the most similar terms in the word2vec vector space included "nonspecific," "vaso-occlusive," and "subacute"; for the term "chronic," the most similar terms included "persistent," "longstanding," and "long-standing." Topic modeling via Latent Dirichlet analysis identified peak coherence (0.49) at 40 topics. Network analysis of these topic models identified three topics that were outliers from the core cluster, two of which pertained to women's health and obstetrics and were closely connected to one another, yet considered distant from the third outlier pertaining to age. A deep learning-based gated recurrent units abstract generation model successfully synthesized several unique abstracts with varying levels of believability, with special attention and some confusion at lower temperatures to the roles of placebo in randomized controlled trials. CONCLUSIONS: Quantitative NLP models of published abstracts pertaining to pain may point to trends and gaps within pain research communities.

MySurgeryRisk: Development and Validation of a Machine-learning Risk Algorithm for Major Complications and Death After Surgery.

OBJECTIVE: To accurately calculate the risk for postoperative complications and death after surgery in the preoperative period using machine-learning modeling of clinical data. BACKGROUND: Postoperative complications cause a 2-fold increase in the 30-day mortality and cost, and are associated with long-term consequences. The ability to precisely forecast the risk for major complications before surgery is limited. METHODS: In a single-center cohort of 51,457 surgical patients undergoing major inpatient surgery, we have developed and validated an automated analytics framework for a preoperative risk algorithm (MySurgeryRisk) that uses existing clinical data in electronic health records to forecast patient-level probabilistic risk scores for 8 major postoperative complications (acute kidney injury, sepsis, venous thromboembolism, intensive care unit admission >48 hours, mechanical ventilation >48 hours, wound, neurologic, and cardiovascular complications) and death up to 24 months after surgery. We used the area under the receiver characteristic curve (AUC) and predictiveness curves to evaluate model performance. RESULTS: MySurgeryRisk calculates probabilistic risk scores for 8 postoperative complications with AUC values ranging between 0.82 and 0.94 [99% confidence intervals (CIs) 0.81-0.94]. The model predicts the risk for death at 1, 3, 6, 12, and 24 months with AUC values ranging between 0.77 and 0.83 (99% CI 0.76-0.85). CONCLUSIONS: We constructed an automated predictive analytics framework for machine-learning algorithm with high discriminatory ability for assessing the risk of surgical complications and death using readily available preoperative electronic health records data. The feasibility of this novel algorithm implemented in real time clinical workflow requires further testing.

A smartwatch-based framework for real-time and online assessment and mobility monitoring.

Smartphone and smartwatch technology is changing the transmission and monitoring landscape for patients and research participants to communicate their healthcare information in real time. Flexible, bidirectional and real-time control of communication allows development of a rich set of healthcare applications that can provide interactivity with the participant and adapt dynamically to their changing environment. Additionally, smartwatches have a variety of sensors suitable for collecting physical activity and location data. The combination of all these features makes it possible to transmit the collected data to a remote server, and thus, to monitor physical activity and potentially social activity in real time. As smartwatches exhibit high user acceptability and increasing popularity, they are ideal devices for monitoring activities for extended periods of time to investigate the physical activity patterns in free-living condition and their relationship with the seemingly random occurring illnesses, which have remained a challenge in the current literature. Therefore, the purpose of this study was to develop a smartwatch-based framework for real-time and online assessment and mobility monitoring (ROAMM). The proposed ROAMM framework will include a smartwatch application and server. The smartwatch application will be used to collect and preprocess data. The server will be used to store and retrieve data, remote monitor, and for other administrative purposes. With the integration of sensor-based and user-reported data collection, the ROAMM framework allows for data visualization and summary statistics in real-time.

Primer on machine learning: utilization of large data set analyses to individualize pain management.

PURPOSE OF REVIEW: Pain researchers and clinicians increasingly encounter machine learning algorithms in both research methods and clinical practice. This review provides a summary of key machine learning principles, as well as applications to both structured and unstructured datasets. RECENT FINDINGS: Aside from increasing use in the analysis of electronic health record data, machine and deep learning algorithms are now key tools in the analyses of neuroimaging and facial expression recognition data used in pain research. SUMMARY: In the coming years, machine learning is likely to become a key component of evidence-based medicine, yet will require additional skills and perspectives for its successful and ethical use in research and clinical settings.

The behavioral intervention technology model: an integrated conceptual and technological framework for eHealth and mHealth interventions.

A growing number of investigators have commented on the lack of models to inform the design of behavioral intervention technologies (BITs). BITs, which include a subset of mHealth and eHealth interventions, employ a broad range of technologies, such as mobile phones, the Web, and sensors, to support users in changing behaviors and cognitions related to health, mental health, and wellness. We propose a model that conceptually defines BITs, from the clinical aim to the technological delivery framework. The BIT model defines both the conceptual and technological architecture of a BIT. Conceptually, a BIT model should answer the questions why, what, how (conceptual and technical), and when. While BITs generally have a larger treatment goal, such goals generally consist of smaller intervention aims (the "why") such as promotion or reduction of specific behaviors, and behavior change strategies (the conceptual "how"), such as education, goal setting, and monitoring. Behavior change strategies are instantiated with specific intervention components or "elements" (the "what"). The characteristics of intervention elements may be further defined or modified (the technical "how") to meet the needs, capabilities, and preferences of a user. Finally, many BITs require specification of a workflow that defines when an intervention component will be delivered. The BIT model includes a technological framework (BIT-Tech) that can integrate and implement the intervention elements, characteristics, and workflow to deliver the entire BIT to users over time. This implementation may be either predefined or include adaptive systems that can tailor the intervention based on data from the user and the user's environment. The BIT model provides a step towards formalizing the translation of developer aims into intervention components, larger treatments, and methods of delivery in a manner that supports research and communication between investigators on how to design, develop, and deploy BITs.

Transformers and large language models in healthcare: A review.

With Artificial Intelligence (AI) increasingly permeating various aspects of society, including healthcare, the adoption of the Transformers neural network architecture is rapidly changing many applications. Transformer is a type of deep learning architecture initially developed to solve general-purpose Natural Language Processing (NLP) tasks and has subsequently been adapted in many fields, including healthcare. In this survey paper, we provide an overview of how this architecture has been adopted to analyze various forms of healthcare data, including clinical NLP, medical imaging, structured Electronic Health Records (EHR), social media, bio-physiological signals, biomolecular sequences. Furthermore, which have also include the articles that used the transformer architecture for generating surgical instructions and predicting adverse outcomes after surgeries under the umbrella of critical care. Under diverse settings, these models have been used for clinical diagnosis, report generation, data reconstruction, and drug/protein synthesis. Finally, we also discuss the benefits and limitations of using transformers in healthcare and examine issues such as computational cost, model interpretability, fairness, alignment with human values, ethical implications, and environmental impact.

Prediction of Robotic Anastomosis Competency Evaluation (RACE) metrics during vesico-urethral anastomosis using electroencephalography, eye-tracking, and machine learning.

Residents learn the vesico-urethral anastomosis (VUA), a key step in robot-assisted radical prostatectomy (RARP), early in their training. VUA assessment and training significantly impact patient outcomes and have high educational value. This study aimed to develop objective prediction models for the Robotic Anastomosis Competency Evaluation (RACE) metrics using electroencephalogram (EEG) and eye-tracking data. Data were recorded from 23 participants performing robot-assisted VUA (henceforth 'anastomosis') on plastic models and animal tissue using the da Vinci surgical robot. EEG and eye-tracking features were extracted, and participants' anastomosis subtask performance was assessed by three raters using the RACE tool and operative videos. Random forest regression (RFR) and gradient boosting regression (GBR) models were developed to predict RACE scores using extracted features, while linear mixed models (LMM) identified associations between features and RACE scores. Overall performance scores significantly differed among inexperienced, competent, and experienced skill levels (P value < 0.0001). For plastic anastomoses, R2 values for predicting unseen test scores were: needle positioning (0.79), needle entry (0.74), needle driving and tissue trauma (0.80), suture placement (0.75), and tissue approximation (0.70). For tissue anastomoses, the values were 0.62, 0.76, 0.65, 0.68, and 0.62, respectively. The models could enhance RARP anastomosis training by offering objective performance feedback to trainees.

Developing a fair and interpretable representation of the clock drawing test for mitigating low education and racial bias.

The clock drawing test (CDT) is a neuropsychological assessment tool to screen an individual's cognitive ability. In this study, we developed a Fair and Interpretable Representation of Clock drawing test (FaIRClocks) to evaluate and mitigate classification bias against people with less than 8 years of education, while screening their cognitive function using an array of neuropsychological measures. In this study, we represented clock drawings by a priorly published 10-dimensional deep learning feature set trained on publicly available data from the National Health and Aging Trends Study (NHATS). These embeddings were further fine-tuned with clocks from a preoperative cognitive screening program at the University of Florida to predict three cognitive scores: the Mini-Mental State Examination (MMSE) total score, an attention composite z-score (ATT-C), and a memory composite z-score (MEM-C). ATT-C and MEM-C scores were developed by averaging z-scores based on normative references. The cognitive screening classifiers were initially tested to see their relative performance in patients with low years of education (< = 8 years) versus patients with higher education (> 8 years) and race. Results indicated that the initial unweighted classifiers confounded lower education with cognitive compromise resulting in a 100% type I error rate for this group. Thereby, the samples were re-weighted using multiple fairness metrics to achieve sensitivity/specificity and positive/negative predictive value (PPV/NPV) balance across groups. In summary, we report the FaIRClocks model, with promise to help identify and mitigate bias against people with less than 8 years of education during preoperative cognitive screening.

Identifying acute illness phenotypes via deep temporal interpolation and clustering network on physiologic signatures.

Using clustering analysis for early vital signs, unique patient phenotypes with distinct pathophysiological signatures and clinical outcomes may be revealed and support early clinical decision-making. Phenotyping using early vital signs has proven challenging, as vital signs are typically sampled sporadically. We proposed a novel, deep temporal interpolation and clustering network to simultaneously extract latent representations from irregularly sampled vital signs and derive phenotypes. Four distinct clusters were identified. Phenotype A (18%) had the greatest prevalence of comorbid disease with increased prevalence of prolonged respiratory insufficiency, acute kidney injury, sepsis, and long-term (3-year) mortality. Phenotypes B (33%) and C (31%) had a diffuse pattern of mild organ dysfunction. Phenotype B's favorable short-term clinical outcomes were tempered by the second highest rate of long-term mortality. Phenotype C had favorable clinical outcomes. Phenotype D (17%) exhibited early and persistent hypotension, high incidence of early surgery, and substantial biomarker incidence of inflammation. Despite early and severe illness, phenotype D had the second lowest long-term mortality. After comparing the sequential organ failure assessment scores, the clustering results did not simply provide a recapitulation of previous acuity assessments. This tool may impact triage decisions and have significant implications for clinical decision-support under time constraints and uncertainty.

A Network Analysis of Digital Clock Drawing for Command and Copy Conditions.

Graphomotor and time-based variables from the digital Clock Drawing Test (dCDT) characterize cognitive functions. However, no prior publications have quantified the strength of the associations between digital clock variables as they are produced. We hypothesized that analysis of the production of clock features and their interrelationships, as suggested, will differ between the command and copy test conditions. Older adults aged 65+ completed a digital clock drawing to command and copy conditions. Using a Bayesian hill-climbing algorithm and bootstrapping (10,000 samples), we derived directed acyclic graphs (DAGs) to examine network structure for command and copy dCDT variables. Although the command condition showed moderate associations between variables (µ|ßz|= 0.34) relative to the copy condition (µ|ßz| = 0.25), the copy condition network had more connections (18/18 versus 15/18 command). Network connectivity across command and copy was most influenced by five of the 18 variables. The direction of dependencies followed the order of instructions better in the command condition network. Digitally acquired clock variables relate to one another but differ in network structure when derived from command or copy conditions. Continued analyses of clock drawing production should improve understanding of quintessential normal features to aid in early neurodegenerative disease detection.

Wearable sensors in patient acuity assessment in critical care.

Acuity assessments are vital for timely interventions and fair resource allocation in critical care settings. Conventional acuity scoring systems heavily depend on subjective patient assessments, leaving room for implicit bias and errors. These assessments are often manual, time-consuming, intermittent, and challenging to interpret accurately, especially for healthcare providers. This risk of bias and error is likely most pronounced in time-constrained and high-stakes environments, such as critical care settings. Furthermore, such scores do not incorporate other information, such as patients' mobility level, which can indicate recovery or deterioration in the intensive care unit (ICU), especially at a granular level. We hypothesized that wearable sensor data could assist in assessing patient acuity granularly, especially in conjunction with clinical data from electronic health records (EHR). In this prospective study, we evaluated the impact of integrating mobility data collected from wrist-worn accelerometers with clinical data obtained from EHR for estimating acuity. Accelerometry data were collected from 87 patients wearing accelerometers on their wrists in an academic hospital setting. The data was evaluated using five deep neural network models: VGG, ResNet, MobileNet, SqueezeNet, and a custom Transformer network. These models outperformed a rule-based clinical score (Sequential Organ Failure Assessment, SOFA) used as a baseline when predicting acuity state (for ground truth we labeled as unstable patients if they needed life-supporting therapies, and as stable otherwise), particularly regarding the precision, sensitivity, and F1 score. The results demonstrate that integrating accelerometer data with demographics and clinical variables improves predictive performance compared to traditional scoring systems in healthcare. Deep learning models consistently outperformed the SOFA score baseline across various scenarios, showing notable enhancements in metrics such as the area under the receiver operating characteristic (ROC) Curve (AUC), precision, sensitivity, specificity, and F1 score. The most comprehensive scenario, leveraging accelerometer, demographics, and clinical data, achieved the highest AUC of 0.73, compared to 0.53 when using SOFA score as the baseline, with significant improvements in precision (0.80 vs. 0.23), specificity (0.79 vs. 0.73), and F1 score (0.77 vs. 0.66). This study demonstrates a novel approach beyond the simplistic differentiation between stable and unstable conditions. By incorporating mobility and comprehensive patient information, we distinguish between these states in critically ill patients and capture essential nuances in physiology and functional status. Unlike rudimentary definitions, such as equating low blood pressure with instability, our methodology delves deeper, offering a more holistic understanding and potentially valuable insights for acuity assessment.

Community-engaged artificial intelligence research: A scoping review.

The degree to which artificial intelligence healthcare research is informed by data and stakeholders from community settings has not been previously described. As communities are the principal location of healthcare delivery, engaging them could represent an important opportunity to improve scientific quality. This scoping review systematically maps what is known and unknown about community-engaged artificial intelligence research and identifies opportunities to optimize the generalizability of these applications through involvement of community stakeholders and data throughout model development, validation, and implementation. Embase, PubMed, and MEDLINE databases were searched for articles describing artificial intelligence or machine learning healthcare applications with community involvement in model development, validation, or implementation. Model architecture and performance, the nature of community engagement, and barriers or facilitators to community engagement were reported according to PRISMA extension for Scoping Reviews guidelines. Of approximately 10,880 articles describing artificial intelligence healthcare applications, 21 (0.2%) described community involvement. All articles derived data from community settings, most commonly by leveraging existing datasets and sources that included community subjects, and often bolstered by internet-based data acquisition and subject recruitment. Only one article described inclusion of community stakeholders in designing an application-a natural language processing model that detected cases of likely child abuse with 90% accuracy using harmonized electronic health record notes from both hospital and community practice settings. The primary barrier to including community-derived data was small sample sizes, which may have affected 11 of the 21 studies (53%), introducing substantial risk for overfitting that threatens generalizability. Community engagement in artificial intelligence healthcare application development, validation, or implementation is rare. As healthcare delivery occurs primarily in community settings, investigators should consider engaging community stakeholders in user-centered design, usability, and clinical implementation studies to optimize generalizability.

APRICOT-Mamba: Acuity Prediction in Intensive Care Unit (ICU): Development and Validation of a Stability, Transitions, and Life-Sustaining Therapies Prediction Model.

On average, more than 5 million patients are admitted to intensive care units (ICUs) in the US, with mortality rates ranging from 10 to 29%. The acuity state of patients in the ICU can quickly change from stable to unstable, sometimes leading to life-threatening conditions. Early detection of deteriorating conditions can assist in more timely interventions and improved survival rates. While Artificial Intelligence (AI)-based models show potential for assessing acuity in a more granular and automated manner, they typically use mortality as a proxy of acuity in the ICU. Furthermore, these methods do not determine the acuity state of a patient (i.e., stable or unstable), the transition between acuity states, or the need for life-sustaining therapies. In this study, we propose APRICOT-M (Acuity Prediction in Intensive Care Unit-Mamba), a 1M-parameter state space-based neural network to predict acuity state, transitions, and the need for life-sustaining therapies in real-time among ICU patients. The model integrates ICU data in the preceding four hours (including vital signs, laboratory results, assessment scores, and medications) and patient characteristics (age, sex, race, and comorbidities) to predict the acuity outcomes in the next four hours. Our state space-based model can process sparse and irregularly sampled data without manual imputation, thus reducing the noise in input data and increasing inference speed. The model was trained on data from 107,473 patients (142,062 ICU admissions) from 55 hospitals between 2014-2017 and validated externally on data from 74,901 patients (101,356 ICU admissions) from 143 hospitals. Additionally, it was validated temporally on data from 12,927 patients (15,940 ICU admissions) from one hospital in 2018-2019 and prospectively on data from 215 patients (369 ICU admissions) from one hospital in 2021-2023. Three datasets were used for training and evaluation: the University of Florida Health (UFH) dataset, the electronic ICU Collaborative Research Database (eICU), and the Medical Information Mart for Intensive Care (MIMIC)-IV dataset. APRICOT-M significantly outperforms the baseline acuity assessment, Sequential Organ Failure Assessment (SOFA), for mortality prediction in both external (AUROC 0.95 CI: 0.94-0.95 compared to 0.78 CI: 0.78-0.79) and prospective (AUROC 0.99 CI: 0.97-1.00 compared to 0.80 CI: 0.65-0.92) cohorts, as well as for instability prediction (external AUROC 0.75 CI: 0.74-0.75 compared to 0.51 CI: 0.51-0.51, and prospective AUROC 0.69 CI: 0.64-0.74 compared to 0.53 CI: 0.50-0.57). This tool has the potential to help clinicians make timely interventions by predicting the transition between acuity states and decision-making on life-sustaining within the next four hours in the ICU.