A reinforcement learning-based optimal control approach for managing an elective surgery backlog after pandemic disruption.

Contagious disease pandemics, such as COVID-19, can cause hospitals around the world to delay nonemergent elective surgeries, which results in a large surgery backlog. To develop an operational solution for providing patients timely surgical care with limited health care resources, this study proposes a stochastic control process-based method that helps hospitals make operational recovery plans to clear their surgery backlog and restore surgical activity safely. The elective surgery backlog recovery process is modeled by a general discrete-time queueing network system, which is formulated by a Markov decision process. A scheduling optimization algorithm based on the piecewise decaying [Formula: see text]-greedy reinforcement learning algorithm is proposed to make dynamic daily surgery scheduling plans considering newly arrived patients, waiting time and clinical urgency. The proposed method is tested through a set of simulated dataset, and implemented on an elective surgery backlog that built up in one large general hospital in China after the outbreak of COVID-19. The results show that, compared with the current policy, the proposed method can effectively and rapidly clear the surgery backlog caused by a pandemic while ensuring that all patients receive timely surgical care. These results encourage the wider adoption of the proposed method to manage surgery scheduling during all phases of a public health crisis.

Developmental changes in spontaneous electrocortical activity and network organization from early to late childhood.

We investigated the development of spontaneous (resting state) cerebral electric fields and their network organization from early to late childhood in a large community sample of children. Critically, we examined electrocortical maturation across one-year windows rather than creating aggregate averages that can miss subtle maturational trends. We implemented several novel methodological approaches including a more fine grained examination of spectral features across multiple electrodes, the use of phase-lagged functional connectivity to control for the confounding effects of volume conduction and applying topological network analyses to weighted cortical adjacency matrices. Overall, there were major decreases in absolute EEG spectral density (particularly in the slow wave range) across cortical lobes as a function of age. Moreover, the peak of the alpha frequency increased with chronological age and there was a redistribution of relative spectral density toward the higher frequency ranges, consistent with much of the previous literature. There were age differences in long range functional brain connectivity, particularly in the alpha frequency band, culminating in the most dense and spatially variable networks in the oldest children. We discovered age-related reductions in characteristic path lengths, modularity and homogeneity of alpha-band cortical networks from early to late childhood. In summary, there is evidence of large scale reorganization in endogenous brain electric fields from early to late childhood, suggesting reduced signal amplitudes in the presence of more functionally integrated and band limited coordination of neuronal activity across the cerebral cortex.

GaitNet+ARL: A Deep Learning Algorithm for Interpretable Gait Analysis of Chronic Ankle Instability.

Chronic ankle instability (CAI) is a major public health concern and adversely affects people's mobility and quality of life. Traditional assessment methods are subjective and qualitative by means of clinician observation and patient self-reporting, which may lead to inaccurate assessment and reduce the effectiveness of treatment in clinical practice. Gait analysis becomes a commonly used approach for monitoring human motion behaviors, which can be applied to specific diagnosis and assessment of CAI. However, it is still challenging to recognize the pathological gait pattern for CAI subjects. In this paper, we propose an integrated deep learning framework to solve the CAI recognition problem using kinematic data. Specifically, inspired by the biomechanics of human body system, we create a simple graph neural network (GNN), termed GaitNet, that operates on a spatial domain and exploits interactions among 3-D joint coordinates. We also develop an attention reinforcement learning (ARL) model that determines attention weights of frames on a temporal domain, which is combined with GaitNet for prediction. The effectiveness of our method is validated on the kinematic NEU-CAI dataset which is collected in our institution using a stereophotogrammetric system. According to extensive experiments, we demonstrate that the selected key phases (i.e., sequences of frames with high attentions) significantly increase the predictability of the proposed biomechanics-based GNN model to differentiate between CAI cohort and control cohort. Moreover, we show a significant prediction accuracy improvement (20%-25%) by our approach compared to state-of-the-art machine learning and deep learning methods.

Multi-event survival analysis through dynamic multi-modal learning for ICU mortality prediction.

BACKGROUND AND OBJECTIVE: Survival analysis is widely applied for assessing the expected duration of patient status towards event occurrences such as mortality in healthcare domain, which is generally considered as a time-to-event problem. Patients with multiple complications have high mortality risks and oftentimes require specific intensive care and clinical treatments. The progression of complications is time-varying according to disease development and intrinsic interactions between complications with respect to mortality are uncertain. Classical methods for mortality prediction and survival analysis in critical care, such as risk scoring systems and cause-specific survival models, were not designed for this multi-event survival analysis problem and able to measure the competing risks of death for mutually exclusive events. In addition, multivariate temporal information of complications is not taken into consideration while estimating differentiated mortality risks in the early stage. METHODS: In this paper, we propose a novel multi-event survival analysis solution using a tree-based autoregressive survival model of multi-modal electronic health record data. Specifically, we focus on modeling the temporal trajectory of complications and estimating the mortality risk associated with multiple potential complications simultaneously. In dynamic modeling, no assumptions are made for the relationships between time-dependent variables and risk transition over time. RESULTS: Validated with the eICU database, our model achieves a better prediction performance with C-index ranging in 74-80%, compared to state-of-the-art machine learning methods in the literature, for the complications of acute respiratory distress syndrome and cardiovascular disease cases. CONCLUSIONS: Our model provides the distinguishable mortality risk curves over time for specific complications and the track of risk development that could potentially support the ICU resource reallocation.

Early ICU Mortality Prediction for Respiratory Failure by A Regression-Based Hazard Markov Model.

Respiratory failure is one of the major causes of death in critical care units. While respiratory failure could come with the acute symptoms progressively, an early warning model is urgently required to assess mortality risks in advance. To this end, an early mortality risk prediction in patients who suffer respiratory failures can provide support for timely decision making of clinical treatment and medical resource management. In the study, we propose a dynamic modeling approach for early mortality risk prediction of at-risk patients with respiratory failure based on the first 24 hours of ICU physiological data. Our proposed model is validated on the eICU Collaborate Research Database. We achieve high AUROC performance of around 80% and significantly improved AUCPR by 4% from Day 4 to Day 6 since ICU admission, compared to the state-of-art prediction models. Furthermore, we show the survival probability curve that contains the time-varying information for early ICU admission patients.

Deep multi-modal learning for joint linear representation of nonlinear dynamical systems.

Dynamical systems pervasively seen in most real-life applications are complex and behave by following certain evolution rules or dynamical patterns, which are linear, non-linear, or stochastic. The underlying dynamics (or evolution rule) of such complex systems, if found, can be used for understanding the system behavior, and furthermore for system prediction and control. It is common to analyze the system's dynamics through observations in different modality approaches. For instance, to recognize patient deterioration in acute care, it usually relies on monitoring and analyzing vital signs and other observations, such as blood pressure, heart rate, respiration, and electroencephalography. These observations convey the information describing the same target system, but the dynamics is not able to be directly characterized due to high complexity of individual modality and maybe time-delay interactions among modalities. In this work, we suppose that the state behavior of a dynamical system follows an intrinsic dynamics shared among these modalities. We specifically propose a new deep auto-encoder framework using the Koopman operator theory to derive the joint linear dynamics for a target system in a space spanned by the intrinsic coordinates. The proposed method aims to reconstruct the original system states by learning the information provided among multiple modalities. Furthermore, with the derived intrinsic dynamics, our method is capable of restoring the missing observations within and across modalities, and used for predicting the future states of the system that follows the same evolution rule.

Using citation network analysis to enhance scholarship in psychological science: A case study of the human aggression literature.

Researchers cannot keep up with the volume of articles being published each year. In order to develop adequate expertise in a given field of study, students and early career scientists must be strategic in what they decide to read. Here we propose using citation network analysis to characterize the literature topology of a given area. We used the human aggression literature as our example. Our citation network analysis identified 15 research communities on aggression. The five largest communities were: "media and video games", "stress, traits and aggression", "rumination and displaced aggression", "role of testosterone", and "social aggression". We examined the growth of these research communities over time, and we used graph theoretic approaches to identify the most influential papers within each community and the "bridging" articles that linked distinct communities to one another. Finally, we also examined whether our citation network analysis would help mitigate gender bias relative to focusing on total citation counts. The percentage of articles with women first authors doubled when identifying influential articles by community structure versus citation count. Our approach of characterizing literature topologies using citation network analysis may provide a valuable resource for psychological scientists by outlining research communities and their growth over time, identifying influential papers within each community (including bridging papers), and providing opportunities to increase gender equity in the field.

Recurrence Quantification Analysis of Ankle Kinematics During Gait in Individuals With Chronic Ankle Instability.

Purpose: An investigation of the ankle dynamics in a motor task may generate insights into the etiology of chronic ankle instability (CAI). This study presents a novel application of recurrence quantification analysis (RQA) to examine the ankle dynamics during walking. We hypothesized that CAI is associated with changes in the ankle dynamics as assessed by measures of determinism and laminarity using RQA. Methods: We recorded and analyzed the ankle position trajectories in the frontal and sagittal planes from 12 participants with CAI and 12 healthy controls during treadmill walking. We used time-delay embedding to reconstruct the position trajectories to a phase space that represents the states of the ankle dynamics. Based on the phase space trajectory, a recurrence plot was constructed and two RQA variables, the percent determinism (%DET) and the percent laminarity (%LAM), were derived from the recurrence plot to quantify the ankle dynamics. Results: In the frontal plane, the %LAM in the CAI group was significantly lower than that in the control group (p < 0.05. effect size = 0.86). This indicated that the ankle dynamics in individuals with CAI is less likely to remain in the same state. No significant results were found in the %DET or in the sagittal plane. Conclusion: A lower frontal-plane %LAM may reflect more frequent switching between different patterns of neuromuscular control states due to the instabilities associated with CAI. With further study and development, %LAM may have the potential to become a useful biomarker for CAI.

Association Rule Mining to Examine Predictors for the Outcome of Gait Rehabilitation Programs in Stroke Survivors.

ABSTRACT: This study presents a novel application of association rule data mining to determine the predictors of the response to locomotor training and home exercise for improving gait after stroke. The study was a secondary data analysis on the Locomotor Experience Applied Post Stroke Trial dataset. The association rule analysis was applied to analyze three interventions: (1) early locomotor training, (2) late locomotor training, and (3) home exercise program. The outcome variable was whether participants poststroke had greater than median improvement in the self-selected comfortable gait speed. Three types of predictors were investigated: (1) demographics, (2) behavioral and medical history, and (3) clinical assessments at baseline. Association rules were generated when they meet two criteria determined based on the data: 10% of support and 70% of confidence. The identified rules showed that the predictors of the response were different across the three interventions, which was inconsistent with the previous report based on traditional logistic regression. However, the rules were identified with high confidence but low support, indicating that they were reliable but did not appear often in the Locomotor Experience Applied Post Stroke Trial dataset. Further investigation of these rules with a larger sample size is warranted before applying them to clinical settings.

Evaluating Different Strategies on the Blood Collection Counter Settings to Improve Patient Waiting Time in Outpatient Units.

Long patient waiting time is one of the major problems in the healthcare system and it would decrease patient satisfaction. Previous studies usually investigated how to improve the treatment flow in order to reduce patient waiting time or length of stay. The studies on blood collection counters have received less attention. Therefore, the objective of this study is to reduce the patient waiting time at outpatient clinics for metabolism and nephrology outpatients. A discrete-event simulation is used to analyze the four different strategies for blood collection counter resource allocation. Through analyzing four different strategic settings, the experimental results revealed that the maximum number of patients waiting before the outpatient clinics was reduced from 41 to 33 (20%); the maximum patient waiti-ng time at the outpatient clinics was decreased from 201.6 minutes to 83 minutes (59%). In this study, we found that adjusting the settings of blood collection counters would be beneficial. Assigning one exclusive blood collection counter from 8 to 10 am is the most suitable option with the least impact on the operational process for hospital staff. The results provide managerial insight regarding the cost-effective strategy selection for the hospital operational strategy.

A Novel Switching State-Space Model for Post-ICU Mortality Prediction and Survival Analysis.

Predicting mortality risk in patients accurately during and after intensive care unit (ICU) stay is an essential component for supporting critical care decision-making. To date, various scoring systems have been designed for survival analysis and mortality prediction by providing risk scores based on patient's vital signs and lab results. However, it is challenging using these universal scores to represent the overall severity level of illness and to look into patient's deterioration leading to high mortality risk during ICU stay. Thus, a close monitoring of the severity level over time during ICU stay is more preferable. In this study, we design a new switching state-space model by correlating patient's condition dynamics in last hours of ICU stay to the risk probabilities in a short time period (1-6 days) after ICU discharge. More specifically, we propose to integrate a cumulative hazard function estimating survival probability into the autoregressive hidden Markov model using time-interval sequential SAPS II scores as features. We demonstrate the significant improvement of mortality prediction comparing to SAPS I, SAPS II, and SOFA scoring systems for the PhysioNet MIMIC II Challenge data.

Detecting Epileptic Seizures via Non-Uniform Multivariate Embedding of EEG Signals.

Efficient real-time detection of epileptic seizures remains a challenging task in clinical practice. In this study, we introduce a new thresholding method to monitor brain activities via a non-uniform multivariate (NUM) embedding of multi-channel electroencephalogram (EEG) signals. Specifically, we present a NUM embedding optimization problem to identify the best embedding parameters. We originate one feature, named non-uniform multivariate multiscale entropy (NUMME), which is extracted from the NUM embedded EEG data. Finally, the extracted feature, compared to an individualized threshold, is used for monitoring and detecting seizure onsets. Experimental results on the real CHB-MIT Scalp EEG database show that our approach achieves a comparable performance to the state-of-art methods. Moreover, it is important to note that we accomplish this without using any sophisticated machine learning algorithms.

Real-time Inference and Detection of Disruptive EEG Networks for Epileptic Seizures.

Recent studies in brain science and neurological medicine paid a particular attention to develop machine learning-based techniques for the detection and prediction of epileptic seizures with electroencephalogram (EEG). As a noninvasive monitoring method to record brain electrical activities, EEG has been widely used for capturing the underlying dynamics of disruptive neuronal responses across the brain in real-time to provide clinical guidance in support of epileptic seizure treatments in practice. In this study, we introduce a novel dynamic learning method that first infers a time-varying network constituted by multivariate EEG signals, which represents the overall dynamics of the brain network, and subsequently quantifies its topological property using graph theory. We demonstrate the efficacy of our learning method to detect relatively strong synchronization (characterized by the algebraic connectivity metric) caused by abnormal neuronal firing during a seizure onset. The computational results for a realistic scalp EEG database show a detection rate of 93.6% and a false positive rate of 0.16 per hour (FP/h); furthermore, our method observes potential pre-seizure phenomena in some cases.

Mixed-integer optimization approach to learning association rules for unplanned ICU transfer.

After admission to emergency department (ED), patients with critical illnesses are transferred to intensive care unit (ICU) due to unexpected clinical deterioration occurrence. Identifying such unplanned ICU transfers is urgently needed for medical physicians to achieve two-fold goals: improving critical care quality and preventing mortality. A priority task is to understand the crucial rationale behind diagnosis results of individual patients during stay in ED, which helps prepare for an early transfer to ICU. Most existing prediction studies were based on univariate analysis or multiple logistic regression to provide one-size-fit-all results. However, patient condition varying from case to case may not be accurately examined by such a simplistic judgment. In this study, we present a new decision tool using a mathematical optimization approach aiming to automatically discover rules associating diagnostic features with high-risk outcome (i.e., unplanned transfers) in different deterioration scenarios. We consider four mutually exclusive patient subgroups based on the principal reasons of ED visits: infections, cardiovascular/respiratory diseases, gastrointestinal diseases, and neurological/other diseases at a suburban teaching hospital. The analysis results demonstrate significant rules associated with unplanned transfer outcome for each subgroups and also show comparable prediction accuracy (>70%) compared to state-of-the-art machine learning methods while providing easy-to-interpret symptom-outcome information.

Adjusting Daily Inpatient Bed Allocation to Smooth Emergency Department Occupancy Variation.

STUDY OBJECTIVE: Overcrowding in emergency departments (ED) is an increasingly common problem in Taiwanese hospitals, and strategies to improve efficiency are in demand. We propose a bed resource allocation strategy to overcome the overcrowding problem. METHOD: We investigated ED occupancy using discrete-event simulation and evaluated the effects of suppressing day-to-day variations in ED occupancy by adjusting the number of empty beds per day. Administrative data recorded at the ED of Taichung Veterans General Hospital (TCVGH) in Taiwan with 1500 beds and an annual ED volume of 66,000 visits were analyzed. Key indices of ED quality in the analysis were the length of stay and the time in waiting for outward transfers to in-patient beds. The model is able to analyze and compare several scenarios for finding a feasible allocation strategy. RESULTS: We compared several scenarios, and the results showed that by reducing the allocated beds for the ED by 20% on weekdays, the variance of daily ED occupancy was reduced by 36.25% (i.e., the percentage of reduction in standard deviation). CONCLUSIONS: This new allocation strategy was able to both reduce the average ED occupancy and maintain the ED quality indices.

Detecting Abnormal Pattern of Epileptic Seizures via Temporal Synchronization of EEG Signals.

OBJECTIVE: Synchronization phenomena of epileptic electroencephalography (EEG) have long been studied. In this study, we aim at investigating the spatial-temporal synchronization pattern in epileptic human brains using the spectral graph theoretic features extracted from scalp EEG and developing an efficient multivariate approach for detecting seizure onsets in real time. METHODS: A complex network model is used for representing the recurrence pattern of EEG signals, based on which the temporal synchronization patterns are quantified using the spectral graph theoretic features. Furthermore, a statistical control chart is applied to the extracted features overtime for monitoring the transits from normal to epileptic states in multivariate EEG systems. RESULTS: Our method is tested on 23 patients from CHB-MIT Scalp EEG database. The results show that the graph theoretic feature yields a high sensitivity (  âˆ¼ 98%) and low latency (  âˆ¼ 6 s) on average, and seizure onsets in 18 patients are 100% detected. CONCLUSION: Our approach validates the increased temporal synchronization in epileptic EEG and achieves a comparable detection performance to previous studies. SIGNIFICANCE: We characterize the temporal synchronization patterns of epileptic EEG using spectral network metrics. In addition, we found significant changes in temporal synchronization in epileptic EEG, which enable a patient-specific approach for real-time seizure detection for personalized diagnosis and treatment.

Adaptive Seizure Onset Detection Framework Using a Hybrid PCA-CSP Approach.

Epilepsy is one of the most common neurological disorders in the world. Prompt detection of seizure onset from electroencephalogram (EEG) signals can improve the treatment of epileptic patients. This paper presents a new adaptive patient-specific seizure onset detection framework that dynamically selects a feature from enhanced EEG signals to discriminate seizures from normal brain activity. The proposed framework employs principal component analysis and common spatial patterns to enhance the EEG signals and uses the extracted discriminative feature as an input for adaptive distance-based change point detector to identify the seizure onsets. Experimental results from the Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) dataset show the computational efficiency of the proposed method (analyzing EEG signals in a time window of 3 s within 0.1 s using a Core i7 PC) while providing comparable results to the existing methods in terms of average sensitivity, latency, and false detection rate. The proposed method is advantageous for real-time monitoring of epileptic patients and could be used to improve early diagnosis and treatment of patients suffering from recurrent seizures.

Topological Pattern Recognition of Severe Alzheimer's Disease via Regularized Supervised Learning of EEG Complexity.

Alzheimer's disease (AD) is a progressive brain disorder with gradual memory loss that correlates to cognitive deficits in the elderly population. Recent studies have shown the potentials of machine learning algorithms to identify biomarkers and functional brain activity patterns across various AD stages using electroencephalography (EEG). In this study, we aim to discover the altered spatio-temporal patterns of EEG complexity associated with AD pathology in different severity levels. We employed the multiscale entropy (MSE), a complexity measure of time series signals, as the biomarkers to characterize the nonlinear complexity at multiple temporal scales. Two regularized logistic regression methods were applied to extracted MSE features to capture the topographic pattern of MSEs of AD cohorts compared to healthy baseline. Furthermore, canonical correlation analysis was performed to evaluate the multivariate correlation between EEG complexity and cognitive dysfunction measured by the Neuropsychiatric Inventory scores. 123 participants were recruited and each participant was examined in three sessions (length = 10 seconds) to collect resting-state EEG signals. MSE features were extracted across 20 time scale factors with pre-determined parameters (m = 2, r = 0.15). The results showed that comparing to logistic regression model, the regularized learning methods performed better for discriminating severe AD cohort from normal control, very mild and mild cohorts (test accuracy ~ 80%), as well as for selecting significant biomarkers arcoss the brain regions. It was found that temporal and occipitoparietal brain regions were more discriminative in regard to classifying severe AD cohort vs. normal controls, but more diverse and distributed patterns of EEG complexity in the brain were exhibited across individuals in early stages of AD.

Primary acute stroke thrombectomy within 3†h for large artery occlusion (PAST3-LAO): a pilot study.

BACKGROUND AND PURPOSE: In recent trials, acute ischemic stroke (AIS) from large artery occlusion (LAO) was resistant to intravenous thrombolysis and adjunctive stent retriever thrombectomy (SRT) was associated with better perfusion and outcomes. Despite benefit, 39-68% of patients had poor outcomes. Thrombectomy in AIS with LAO within 3 h is performed secondary to intravenous thrombolysis, which may be associated with delay. The purpose of our study is to evaluate the safety, feasibility, recanalization rate, and outcome of primary SRT within 3 h without intravenous thrombolysis in AIS from LAO. METHODS: Based on an institutionally approved protocol, stroke patients with LAO within 3 h were offered primary SRT as an alternative to intravenous recombinant tissue plasminogen activator. Consecutive patients who underwent primary SRT for LAO within 3 h from 2012 to 2014 were enrolled. Outcomes were measured using the modified Rankin Scale (mRS). RESULTS: 18 patients with LAO of mean age 62.83±15.32 years and median NIH Stroke Scale (NIHSS) score 16 (10-23) chose primary SRT after giving informed consent. Near complete (TICI 2b in 1 patient) or complete (TICI 3 in 17 patients) recanalization was observed in all patients. Time to recanalization from symptom onset and groin puncture was 188.5±82.7 and 64.61±40.14 min, respectively. NIHSS scores immediately after thrombectomy, at 24 h and 30 days were 4 (0-12), 1 (0-12), and 0 (0-4), respectively. Asymptomatic perfusion-related hemorrhage developed in four patients (22%). 90-day outcomes were mRS 0 in 50%, mRS 1 in 44.4%, and mRS 2 in 5.6%. CONCLUSIONS: Our study demonstrates that primary SRT in AIS from LAO is safe and feasible and is associated with complete recanalization and good outcome. Further study is required.

Exploring stability-based voxel selection methods in MVPA using cognitive neuroimaging data: a comprehensive study.

Feature selection plays a key role in multi-voxel pattern analysis because functional magnetic resonance imaging data are typically noisy, sparse, and high-dimensional. Although the conventional evaluation criterion is the classification accuracy, selecting a stable feature set that is not sensitive to the variance in dataset may provide more scientific insights. In this study, we aim to investigate the stability of feature selection methods and test the stability-based feature selection scheme on two benchmark datasets. Top-k feature selection with a ranking score of mutual information and correlation, recursive feature elimination integrated with support vector machine, and L1 and L2-norm regularizations were adapted to a bootstrapped stability selection framework, and the selected algorithms were compared based on both accuracy and stability scores. The results indicate that regularization-based methods are generally more stable in StarPlus dataset, but in Haxby dataset they failed to perform as well as others.