Voice-Enabled Response Analysis Agent (VERAA): Leveraging Large Language Models to Map Voice Responses in SDoH Survey.

Social Determinants of Health (SDoH) have been shown to have profound impacts on health-related outcomes, yet this data suffers from high rates of missingness in electronic health records (EHR). Moreover, limited English proficiency in the United States can be a barrier to communication with health care providers. In this study, we have designed a multilingual conversational agent capable of conducting SDoH surveys for use in healthcare environments. The agent asks questions in the patient's native language, translates responses into English, and subsequently maps these responses via a large language model (LLM) to structured options in a SDoH survey. This tool can be extended to a variety of survey instruments in either hospital or home settings, enabling the extraction of structured insights from free-text answers. The proposed approach heralds a shift towards more inclusive and insightful data collection, marking a significant stride in SDoH data enrichment for optimizing health outcome predictions and interventions.

Voice-Enabled Response Analysis Agent (VERAA): Leveraging Large Language Models to Map Voice Responses in SDoH Survey.

Social Determinants of Health (SDoH) have been shown to have profound impacts on health-related outcomes, yet this data suffers from high rates of missingness in electronic health records (EHR). Moreover, limited English proficiency in the United States can be a barrier to communication with health care providers. In this study, we have designed a multilingual conversational agent capable of conducting SDoH surveys for use in healthcare environments. The agent asks questions in the patient's native language, translates responses into English, and subsequently maps these responses via a large language model (LLM) to structured options in a SDoH survey. This tool can be extended to a variety of survey instruments in either hospital or home settings, enabling the extraction of structured insights from free-text answers. The proposed approach heralds a shift towards more inclusive and insightful data collection, marking a significant stride in SDoH data enrichment for optimizing health outcome predictions and interventions.

DeepAISE - An interpretable and recurrent neural survival model for early prediction of sepsis.

Sepsis, a dysregulated immune system response to infection, is among the leading causes of morbidity, mortality, and cost overruns in the Intensive Care Unit (ICU). Early prediction of sepsis can improve situational awareness among clinicians and facilitate timely, protective interventions. While the application of predictive analytics in ICU patients has shown early promising results, much of the work has been encumbered by high false-alarm rates and lack of trust by the end-users due to the 'black box' nature of these models. Here, we present DeepAISE (Deep Artificial Intelligence Sepsis Expert), a recurrent neural survival model for the early prediction of sepsis. DeepAISE automatically learns predictive features related to higher-order interactions and temporal patterns among clinical risk factors that maximize the data likelihood of observed time to septic events. A comparative study of four baseline models on data from hospitalized patients at three different healthcare systems indicates that DeepAISE produces the most accurate predictions (AUCs between 0.87 and 0.90) at the lowest false alarm rates (FARs between 0.20 and 0.25) while simultaneously producing interpretable representations of the clinical time series and risk factors.

Early Prediction of Sepsis From Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019.

OBJECTIVES: Sepsis is a major public health concern with significant morbidity, mortality, and healthcare expenses. Early detection and antibiotic treatment of sepsis improve outcomes. However, although professional critical care societies have proposed new clinical criteria that aid sepsis recognition, the fundamental need for early detection and treatment remains unmet. In response, researchers have proposed algorithms for early sepsis detection, but directly comparing such methods has not been possible because of different patient cohorts, clinical variables and sepsis criteria, prediction tasks, evaluation metrics, and other differences. To address these issues, the PhysioNet/Computing in Cardiology Challenge 2019 facilitated the development of automated, open-source algorithms for the early detection of sepsis from clinical data. DESIGN: Participants submitted containerized algorithms to a cloud-based testing environment, where we graded entries for their binary classification performance using a novel clinical utility-based evaluation metric. We designed this scoring function specifically for the Challenge to reward algorithms for early predictions and penalize them for late or missed predictions and for false alarms. SETTING: ICUs in three separate hospital systems. We shared data from two systems publicly and sequestered data from all three systems for scoring. PATIENTS: We sourced over 60,000 ICU patients with up to 40 clinical variables for each hour of a patient's ICU stay. We applied Sepsis-3 clinical criteria for sepsis onset. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: A total of 104 groups from academia and industry participated, contributing 853 submissions. Furthermore, 90 abstracts based on Challenge entries were accepted for presentation at Computing in Cardiology. CONCLUSIONS: Diverse computational approaches predict the onset of sepsis several hours before clinical recognition, but generalizability to different hospital systems remains a challenge.

Preclinical evaluation of injectable reduced hydroxocobalamin as an antidote to acute carbon monoxide poisoning.

BACKGROUND: Current management of acute inhalational carbon monoxide (CO) toxicity includes hyperbaric or normobaric O2 therapy. However, efficacy has not been established. The purpose of this study was to establish therapeutic proof of concept for a novel injectable antidote consisting of the combination of hydroxocobalamin and ascorbic acid into a reduced form (B12r) as demonstrated by clinically significant increase (>500 ppm) in CO2 production, reduced carboxyhemoglobin (COHgb) half-life (COHgb t1/2), and increased cerebral O2 delivery and attenuation of CO-induced microglial damage in a preclinical rodent model of CO toxicity. METHODS: B12r-mediated conversion of CO to CO2 and COHgb t1/2 in human blood were measured by gas analysis and Raman resonance spectroscopy. Rats were exposed to either air or CO and then injected with saline or B12r. Cognitive assessment was tested in a Morris water maze. Brain oxygenation was measured with Licox. Brain histology was assessed by fluorescent antibody markers and cell counts. RESULTS: B12r resulted in significant CO2 production (1,170 ppm), compared with controls. COHgb t1/2 was reduced from 33 minutes (normal saline) to 17.5 (p < 0.001). In rat models, severe CO-induced brain hypoxia (PbtO2, 18 mm Hg) was followed by significant reduction in τ25 to 12 minutes for B12r rats versus 40 minutes for normal saline-treated rats (p < 0.0001). There was major attenuation of CO-induced microglial damage, although cognitive performance differences were minimal. CONCLUSION: Our preclinical data suggest that the novel synergism of hydroxocobalamin with ascorbic acid has the potential to extract CO through conversion to CO2, independently of high-flow or high-pressure O2. This resulted in a clinically significant off-gassing of CO2 at levels five to eight times greater than those of controls, a clinically significant reduction in COHgb half-life, and evidence of increased brain oxygenation and amelioration of myoglial damage in rat models. Reduced hydroxocobalamin has major potential as an injectable antidote for CO toxicity.

A modern literature review of carbon monoxide poisoning theories, therapies, and potential targets for therapy advancement.

The first descriptions of carbon monoxide (CO) and its toxic nature appeared in the literature over 100 years ago in separate publications by Drs. Douglas and Haldane. Both men ascribed the deleterious effects of this newly discovered gas to its strong interaction with hemoglobin. Since then the adverse sequelae of CO poisoning has been almost universally attributed to hypoxic injury secondary to CO occupation of oxygen binding sites on hemoglobin. Despite a mounting body of literature suggesting other mechanisms of injury, this pathophysiology and its associated oxygen centric therapies persists. This review attempts to elucidate the remarkably complex nature of CO as a gasotransmitter. While CO's affinity for hemoglobin remains undisputed, new research suggests that its role in nitric oxide release, reactive oxygen species formation, and its direct action on ion channels is much more significant. In the course of understanding the multifaceted character of this simple molecule it becomes apparent that current oxygen based therapies meant to displace CO from hemoglobin may be insufficient and possibly harmful. Approaching CO as a complex gasotransmitter will help guide understanding of the complex and poorly understood sequelae and illuminate potentials for new treatment modalities.

Predicting the need for urgent intubation in a surgical/trauma intensive care unit.

BACKGROUND: Analysis and modeling of data monitoring vital signs and waveforms in patients in a surgical/trauma intensive care unit (STICU) may allow for early identification and treatment of patients with evolving respiratory failure. METHODS: Between February 2011 and March 2012, data of vital signs and waveforms for STICU patients were collected. Every-15-minute calculations (n = 172,326) of means and standard deviations of heart rate (HR), respiratory rate (RR), pulse-oxygen saturation (SpO2), cross-correlation coefficients, and cross-sample entropy for HR-RR, RR-SpO2, and HR-SpO2, and cardiorespiratory coupling were calculated. Urgent intubations were recorded. Univariate analyses were performed for the periods <24 and ≥24 hours before intubation. Multivariate predictive models for the risk of unplanned intubation were developed and validated internally by subsequent sample and bootstrapping techniques. RESULTS: Fifty unplanned intubations (41 patients) were identified from 798 STICU patients. The optimal multivariate predictive model (HR, RR, and SpO2 means, and RR-SpO2 correlation coefficient) had a receiving operating characteristic (ROC) area of 0.770 (95% confidence interval [CI], 0.712-0.841). For this model, relative risks of intubation in the next 24 hours for the lowest and highest quintiles were 0.20 and 2.95, respectively (15-fold increase, baseline risk 1.46%). Adding age and days since previous extubation to this model increased ROC area to 0.865 (95 % CI, 0.821-0.910). CONCLUSION: Among STICU patients, a multivariate model predicted increases in risk of intubation in the following 24 hours based on vital sign data available currently on bedside monitors. Further refinement could allow for earlier detection of respiratory decompensation and intervention to decrease preventable morbidity and mortality in surgical/trauma patients.