Utilizing community level factors to improve prediction of out of hospital cardiac arrest outcome using machine learning.

OBJECTIVES: To evaluate the impact of community level information on the predictability of out-of-hospital cardiac arrest (OHCA) survival. METHODS: We used the Cardiac Arrest Registry to Enhance Survival (CARES) to geocode 9,595 Chicago incidents from 2014 to 2019 into community areas. Community variables including crime, healthcare, and economic factors from public data were merged with CARES. The merged data were used to develop ML models for OHCA survival. Models were evaluated using Area Under the Receiver Operating Characteristic curve (AUROC) and features were analyzed using SHapley Additive exPansion (SHAP) values. RESULTS: Baseline results using CARES data achieved an AUROC of 84%. The final model utilizing community variables increased the AUROC to 88%. A SHAP analysis between high and low performing community area clusters showed the high performing cluster is positively impacted by good health related features and good community safety features positively impact the low performing cluster. CONCLUSION: Utilizing community variables helps predict neurologic outcomes with better performance than only CARES data. Future studies will use this model to perform simulations to identify interventions to improve OHCA survival.

A machine learning approach for modeling decisions in the out of hospital cardiac arrest care workflow.

BACKGROUND: A growing body of research has shown that machine learning (ML) can be a useful tool to predict how different variable combinations affect out-of-hospital cardiac arrest (OHCA) survival outcomes. However, there remain significant research gaps on the utilization of ML models for decision-making and their impact on survival outcomes. The purpose of this study was to develop ML models that effectively predict hospital's practice to perform coronary angiography (CA) in adult patients after OHCA and subsequent neurologic outcomes. METHODS: We utilized all (N = 2398) patients treated by the Chicago Fire Department Emergency Medical Services included in the Cardiac Arrest Registry to Enhance Survival (CARES) between 2013 and 2018 who survived to hospital admission to develop, test, and analyze ML models for decisions after return of spontaneous circulation (ROSC) and patient survival. ML classification models, including the Embedded Fully Convolutional Network (EFCN) model, were compared based on their ability to predict post-ROSC decisions and survival. RESULTS: The EFCN classification model achieved the best results across tested ML algorithms. The area under the receiver operating characteristic curve (AUROC) for CA and Survival were 0.908 and 0.896 respectively. Through cohort analyses, our model predicts that 18.3% (CI 16.4-20.2) of patients should receive a CA that did not originally, and 30.1% (CI 28.5-31.7) of these would experience improved survival outcomes. CONCLUSION: ML modeling effectively predicted hospital decisions and neurologic outcomes. ML modeling may serve as a quality improvement tool to inform system level OHCA policies and treatment protocols.

Improving the In-Hospital Mortality Prediction of Diabetes ICU Patients Using a Process Mining/Deep Learning Architecture.

Diabetes intensive care unit (ICU) patients are at increased risk of complications leading to in-hospital mortality. Assessing the likelihood of death is a challenging and time-consuming task due to a large number of influencing factors. Healthcare providers are interested in the detection of ICU patients at higher risk, such that risk factors can possibly be mitigated. While such severity scoring methods exist, they are commonly based on a snapshot of the health conditions of a patient during the ICU stay and do not specifically consider a patient's prior medical history. In this paper, a process mining/deep learning architecture is proposed to improve established severity scoring methods by incorporating the medical history of diabetes patients. First, health records of past hospital encounters are converted to event logs suitable for process mining. The event logs are then used to discover a process model that describes the past hospital encounters of patients. An adaptation of Decay Replay Mining is proposed to combine medical and demographic information with established severity scores to predict the in-hospital mortality of diabetes ICU patients. Significant performance improvements are demonstrated compared to established risk severity scoring methods and machine learning approaches using the Medical Information Mart for Intensive Care III dataset.

Predicting clinical outcomes among hospitalized COVID-19 patients using both local and published models.

BACKGROUND: Many models are published which predict outcomes in hospitalized COVID-19 patients. The generalizability of many is unknown. We evaluated the performance of selected models from the literature and our own models to predict outcomes in patients at our institution. METHODS: We searched the literature for models predicting outcomes in inpatients with COVID-19. We produced models of mortality or criticality (mortality or ICU admission) in a development cohort. We tested external models which provided sufficient information and our models using a test cohort of our most recent patients. The performance of models was compared using the area under the receiver operator curve (AUC). RESULTS: Our literature review yielded 41 papers. Of those, 8 were found to have sufficient documentation and concordance with features available in our cohort to implement in our test cohort. All models were from Chinese patients. One model predicted criticality and seven mortality. Tested against the test cohort, internal models had an AUC of 0.84 (0.74-0.94) for mortality and 0.83 (0.76-0.90) for criticality. The best external model had an AUC of 0.89 (0.82-0.96) using three variables, another an AUC of 0.84 (0.78-0.91) using ten variables. AUC's ranged from 0.68 to 0.89. On average, models tested were unable to produce predictions in 27% of patients due to missing lab data. CONCLUSION: Despite differences in pandemic timeline, race, and socio-cultural healthcare context some models derived in China performed well. For healthcare organizations considering implementation of an external model, concordance between the features used in the model and features available in their own patients may be important. Analysis of both local and external models should be done to help decide on what prediction method is used to provide clinical decision support to clinicians treating COVID-19 patients as well as what lab tests should be included in order sets.

REDECA: A Novel Framework to Review Artificial Intelligence and Its Applications in Occupational Safety and Health.

INTRODUCTION: The field of artificial intelligence (AI) is rapidly expanding, with many applications seen routinely in health care, industry, and education, and increasingly in workplaces. Although there is growing evidence of applications of AI in workplaces across all industries to simplify and/or automate tasks there is a limited understanding of the role that AI contributes in addressing occupational safety and health (OSH) concerns. METHODS: This paper introduces a new framework called Risk Evolution, Detection, Evaluation, and Control of Accidents (REDECA) that highlights the role that AI plays in the anticipation and control of exposure risks in a worker's immediate environment. Two hundred and sixty AI papers across five sectors (oil and gas, mining, transportation, construction, and agriculture) were reviewed using the REDECA framework to highlight current applications and gaps in OSH and AI fields. RESULTS: The REDECA framework highlighted the unique attributes and research focus of each of the five industrial sectors. The majority of evidence of AI in OSH research within the oil/gas and transportation sectors focused on the development of sensors to detect hazardous situations. In construction the focus was on the use of sensors to detect incidents. The research in the agriculture sector focused on sensors and actuators that removed workers from hazardous conditions. Application of the REDECA framework highlighted AI/OSH strengths and opportunities in various industries and potential areas for collaboration. CONCLUSIONS: As AI applications across industries continue to increase, further exploration of the benefits and challenges of AI applications in OSH is needed to optimally protect worker health, safety and well-being.

Predicting Prolonged Hospitalization and Supplemental Oxygenation in Patients with COVID-19 Infection from Ambulatory Chest Radiographs using Deep Learning.

RATIONALE AND OBJECTIVES: The clinical prognosis of outpatients with coronavirus disease 2019 (COVID-19) remains difficult to predict, with outcomes including asymptomatic, hospitalization, intubation, and death. Here we determined the prognostic value of an outpatient chest radiograph, together with an ensemble of deep learning algorithms predicting comorbidities and airspace disease to identify patients at a higher risk of hospitalization from COVID-19 infection. MATERIALS AND METHODS: This retrospective study included outpatients with COVID-19 confirmed by reverse transcription-polymerase chain reaction testing who received an ambulatory chest radiography between March 17, 2020 and October 24, 2020. In this study, full admission was defined as hospitalization within 14 days of the COVID-19 test for > 2 days with supplemental oxygen. Univariate analysis and machine learning algorithms were used to evaluate the relationship between the deep learning model predictions and hospitalization for > 2 days. RESULTS: The study included 413 patients, 222 men (54%), with a median age of 51 years (interquartile range, 39-62 years). Fifty-one patients (12.3%) required full admission. A boosted decision tree model produced the best prediction. Variables included patient age, frontal chest radiograph predictions of morbid obesity, congestive heart failure and cardiac arrhythmias, and radiographic opacity, with an internally validated area under the curve (AUC) of 0.837 (95% CI: 0.791-0.883) on a test cohort. CONCLUSION: Deep learning analysis of single frontal chest radiographs was used to generate combined comorbidity and pneumonia scores that predict the need for supplemental oxygen and hospitalization for > 2 days in patients with COVID-19 infection with an AUC of 0.837 (95% confidence interval: 0.791-0.883). Comorbidity scoring may prove useful in other clinical scenarios.

Adversarial Attacks on Time Series.

Time series classification models have been garnering significant importance in the research community. However, not much research has been done on generating adversarial samples for these models. These adversarial samples can become a security concern. In this paper, we propose utilizing an adversarial transformation network (ATN) on a distilled model to attack various time series classification models. The proposed attack on the classification model utilizes a distilled model as a surrogate that mimics the behavior of the attacked classical time series classification models. Our proposed methodology is applied onto 1-nearest neighbor dynamic time warping (1-NN DTW) and a fully convolutional network (FCN), all of which are trained on 42 University of California Riverside (UCR) datasets. In this paper, we show both models were susceptible to attacks on all 42 datasets. When compared to Fast Gradient Sign Method, the proposed attack generates a larger faction of successful adversarial black-box attacks. A simple defense mechanism is successfully devised to reduce the fraction of successful adversarial samples. Finally, we recommend future researchers that develop time series classification models to incorporating adversarial data samples into their training data sets to improve resilience on adversarial samples.

Multivariate LSTM-FCNs for time series classification.

Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiring minimum preprocessing. The proposed models work efficiently on various complex multivariate time series classification tasks such as activity recognition or action recognition. Furthermore, the proposed models are highly efficient at test time and small enough to deploy on memory constrained systems.

A machine learning based model for Out of Hospital cardiac arrest outcome classification and sensitivity analysis.

BACKGROUND: Out-of-hospital cardiac arrest (OHCA) affects nearly 400,000 people each year in the United States of which only 10% survive. Using data from the Cardiac Arrest Registry to Enhance Survival (CARES), and machine learning (ML) techniques, we developed a model of neurological outcome prediction for OHCA in Chicago, Illinois. METHODS: Rescue workflow data of 2639 patients with witnessed OHCA were retrieved from Chicago's CARES. An Embedded Fully Convolutional Network (EFCN) classification model was selected to predict the patient outcome (survival with good neurological outcomes or not) based on 27 input features with the objective of maximizing the average class sensitivity. Using this model, sensitivity analysis of intervention variables such as bystander cardiopulmonary resuscitation (CPR), targeted temperature management, and coronary angiography was conducted. RESULTS: The EFCN classification model has an average class sensitivity of 0.825. Sensitivity analysis of patient outcome shows that an additional 33 patients would have survived with good neurological outcome if they had received lay person CPR in addition to CPR by emergency medical services and 88 additional patients would have survived if they had received the coronary angiography intervention. CONCLUSIONS: ML modeling of the complex Chicago OHCA rescue system can predict neurologic outcomes with a reasonable level of accuracy and can be used to support intervention decisions such as CPR or coronary angiography. The discriminative ability of this ML model requires validation in external cohorts to establish generalizability.

A New Approach towards Minimizing the Risk of Misdosing Warfarin Initiation Doses.

It is a challenge to be able to prescribe the optimal initial dose of warfarin. There have been many studies focused on an efficient strategy to determine the optimal initial dose. Numerous clinical, genetic, and environmental factors affect the warfarin dose response. In practice, it is common that the initial warfarin dose is substantially different from the stable maintenance dose, which may increase the risk of bleeding or thrombosis prior to achieving the stable maintenance dose. In order to minimize the risk of misdosing, despite popular warfarin dose prediction models in the literature which create dose predictions solely based on patients' attributes, we have taken physicians' opinions towards the initial dose into consideration. The initial doses selected by clinicians, along with other standard clinical factors, are used to determine an estimate of the difference between the initial dose and estimated maintenance dose using shrinkage methods. The selected shrinkage method was LASSO (Least Absolute Shrinkage and Selection Operator). The estimated maintenance dose was more accurate than the original initial dose, the dose predicted by a linear model without involving the clinicians initial dose, and the values predicted by the most commonly used model in the literature, the Gage clinical model.

Childhood Asthma Disparities in Chicago: Developing Approaches to Health Inequities.

We conducted a needs assessment to develop an evidence-based, locally tailored asthma care implementation plan for high-risk children with asthma in Chicago. Our team of health policy experts, clinicians, researchers, and designers included extensive stakeholder engagement (N = 162) in a mixed-methods community needs assessment. Results showed the lines of communication and collaboration across sectors were weak; caregivers were the only consistent force and could not always manage this burden. A series of recommendations for interventions and how to implement and measure them were generated. Cooperative, multidisciplinary efforts grounded in the community can target wicked problems such as asthma.

Learning optimal opioid prescribing and monitoring: a simulation study of medical residents.

OBJECTIVE: Hospitalized patients often receive opioids. There is a lack of consensus regarding evidence-based guidelines or training programs for effective management of pain in the hospital. We investigated the viability of using an Internet-based opioid dosing simulator to teach residents appropriate use of opioids to treat and manage acute pain. MATERIALS AND METHODS: We used a prospective, longitudinal design to evaluate the effects of simulator training. In face-to-face didactic sessions, we taught 120 (108 internal medicine and 12 family medicine) residents principles of pain management and how to use the simulator. Each trainee completed 10 training and, subsequently, 5 testing trials on the simulator. For each trial, we collected medications, doses, routes and times of administration, pain scores, and a summary score. We used mixed-effects regression models to assess the impact of simulation training on simulation performance scores, variability in pain score trajectories, appropriate use of short- and long-acting opioids, and use of naloxone. RESULTS: Trainees completed 1582 simulation trials (M = 13.2, SD = 6.8), with sustained improvements in their simulated pain management practices. Over time, trainees improved their overall simulated pain management scores (b = 0.05, P < .01), generated lower pain score trajectories with less variability (b = -0.02, P < .01), switched more rapidly from short-acting to long-acting agents (b = -0.50, P < .01), and used naloxone less often (b = -0.10, P < .01). DISCUSSION AND CONCLUSIONS: Trainees translated their understanding of didactically presented principles of pain management to their performance on simulated patient cases. Simulation-based training presents an opportunity for improving opioid-based inpatient acute pain management.

Revisiting Warfarin Dosing Using Machine Learning Techniques.

Determining the appropriate dosage of warfarin is an important yet challenging task. Several prediction models have been proposed to estimate a therapeutic dose for patients. The models are either clinical models which contain clinical and demographic variables or pharmacogenetic models which additionally contain the genetic variables. In this paper, a new methodology for warfarin dosing is proposed. The patients are initially classified into two classes. The first class contains patients who require doses of >30 mg/wk and the second class contains patients who require doses of ≤30 mg/wk. This phase is performed using relevance vector machines. In the second phase, the optimal dose for each patient is predicted by two clinical regression models that are customized for each class of patients. The prediction accuracy of the model was 11.6 in terms of root mean squared error (RMSE) and 8.4 in terms of mean absolute error (MAE). This was 15% and 5% lower than IWPC and Gage models (which are the most widely used models in practice), respectively, in terms of RMSE. In addition, the proposed model was compared with fixed-dose approach of 35 mg/wk, and the model proposed by Sharabiani et al. and its outperformance were proved in terms of both MAE and RMSE.

Control reconfiguration of discrete event systems controllers with partial observation.

In this paper, we develop a framework for reconfiguration of a discrete event system (DES) controller, which has a dynamic event observation set. We will show the designed reconfiguration yields a more tolerable controller than the one designed in [5]. Starting with a maximally permissive controller that has a full observation of its DES, we design a mega-controller that monitors the observation set of the DES controller and its state continuously. Upon a change in the observation set, the mega-controller reconfigures the controller by a aggregation or disaggregation of the controller states. The mega-controller is also responsible for feedback function adjustments if the available observation set causes a conflict in control. We illustrate the reconfiguration procedures by an example.