Sepsis, a life-threatening condition triggered by the body's exaggerated response to infection, demands urgent intervention to prevent severe complications. Existing machine learning methods for managing sepsis struggle in offline scenarios, exhibiting suboptimal performance with survival rates below 50%. This paper introduces thePosNegDM— “Reinforcement Learning with Positive and Negative Demonstrations for Sequential Decision-Making” framework utilizing an innovative transformer-based model and a feedback reinforcer to replicate expert actions while considering individual patient characteristics. A mortality classifier with 96.7% accuracy guides treatment decisions towards positive outcomes. ThePosNegDMframework significantly improves patient survival, saving 97.39% of patients, outperforming established machine learning algorithms (Decision Transformer and Behavioral Cloning) with survival rates of 33.4% and 43.5%, respectively. Additionally, ablation studies underscore the critical role of the transformer-based decision maker and the integration of a mortality classifier in enhancing overall survival rates. In summary, our proposed approach presents a promising avenue for enhancing sepsis treatment outcomes, contributing to improved patient care and reduced healthcare costs.

Maintaining situation awareness (SA) is essential for drivers to deal with the situations that Society of Automotive Engineers (SAE) Level 3 automated vehicle systems are not designed to handle. Although advanced physiological sensors can enable continuous SA assessments, previous single-modality approaches may not be sufficient to capture SA. To address this limitation, the current study demonstrates a multimodal sensing approach for objective SA monitoring. Physiological sensor data from electroencephalogram and eye-tracking were recorded for 30 participants as they performed three secondary tasks during automated driving scenarios that consisted of a pre-takeover (pre-TOR) request segment and a post-TOR segment. The tasks varied in terms of how visual attention was allocated in the pre-TOR segment. In the post-TOR segment, drivers were expected to gather information from the driving environment in preparation for a vehicle-to-driver transition. Participants' ground-truth SA level was measured using the Situation Awareness Global Assessment Techniques (SAGAT) after the post-TOR segment. A total of 23 physiological features were extracted from the post-TOR segment to train computational intelligence models. Results compared the performance of five different classifiers, the ground-truth labeling strategies, and the features included in the model. Overall, the proposed neural network model outperformed other machine learning models and achieved the best classification accuracy (90.6%). A model with 11 features was optimal. In addition, the multi-physiological sensor-model outperformed the single sensing model by comparing prediction performance. Our results suggest that multimodal sensing model can objectively predict SA. The results of this study provide new insight into how physiological features contribute to the SA assessment.

Mannequin-based simulations are widely used to train novice nurses. However, current mannequins have no dynamic facial expressions, which decreases the mannequins’ fidelity and impacts students’ learning outcomes and experience. This study proposes a projection-based AR system for overlaying dynamic facial expressions on a mannequin and implements the system in a stroke simulation. Thirty-six undergraduate nursing students participated in the study and were equally divided into the control (without the system) and experimental group (with the system). The participants’ gaze behavior, simulation performance, and subjective evaluation were measured. Results illustrated that the participants focused more on the face-animated mannequin than the traditional mannequin during the simulation. Nursing experts believed that the face-animated mannequin increased the participants’ performance in recognizing deviations but decreased their performance in seeking additional information. Moreover, the participants reported that the face-animated mannequin was more interactive and helpful for performing appropriate assessments than the traditional mannequin.

Safety practitioners widely use the lifting index (LI) to determine workers’ lifting risk but are hampered by the difficulties of estimating the lifting load without intervention or intrusive sensors. This study proposes a computer vision method for estimating the LI across varying lifting loads. The proposed method can also predict the Brog rating of perceived exertion (RPE), a measure associated with the lifting load. A controlled lifting experiment was conducted to demonstrate the approach. Thirty participants performed 2176 lifting tasks at three LI levels. These levels were controlled by varying the lifting load and fixing other task variables (e.g., the lifting distance). The proposed method combined the pose estimation (OpenPose) and the optical flow estimation (SelFlow) techniques for extracting the participants’ body motion and posture features; a facial expression recognition algorithm (OpenFace) built upon the facial action unit coding system (FACS) was used to extract the participants’ facial features. The extracted features were combined and used to develop prediction models. The best-performing model was an integration of the 1-D convolutional neural network and the long short-term memory network. It achieved an area under curve of 0.890 in classifying the LI and a root mean square of 2.264 in predicting the participants’ RPE. Critical indicators were identified by investigating the contribution of the features through interpretable machine learning techniques. In summary, this study demonstrates a nonintrusive method for lifting risk assessment and discovers behavioral indicators that predict changes in the LI and RPE due to varying loads.

Blood suction and irrigation are among the most critical support tasks in robotic-assisted minimally invasive surgery (RMIS). Usually, suction/irrigation tools are controlled by a surgical assistant to maintain a clear view of the surgical field. Thus, the assistant’s contribution to other emergency support tasks is limited. Similarly, when the surgical assistant is not available to perform the blood suction, the leading surgeon must take over this task, which in a complex surgical procedure can result in an unnecessary increment in the cognitive load. To alleviate this problem, we have developed a semi-autonomous robotic suction assistant, which was integrated with a Da Vinci Research Kit (DVRK). At the heart of the algorithm, there is an autonomous control based on a deep learning model to segment and identify the location of blood accumulations. This system provides automatic suction allowing the leading surgeon to focus exclusively on the main task through the control of key instruments of the robot. We conducted a user study to evaluate the user’s workload demands and performance while doing a surgical task under two modalities: (1) autonomous suction action and (2) a surgeon-controlled-suction. Our results indicate that users working with the autonomous system completed the task 161 seconds faster than in the surgeon-controlled-suction modality. Furthermore, the autonomous modality led to a lower percentage of bleeding in the surgical field and workload demands on the users (p-value<0.05). These results show how leveraging state-of-the-art AI algorithms can reduce cognitive demands and enhance performance.

Physical injuries induced by lifting are commonly reported in the workplace. Early risk detection is essential for reducing lifting injuries but requires trained observers to perform assessments manually. Machine learning and computer vision techniques have been proposed to aid ergonomists in lifting risk assessments. However, these methods may not bring the practitioners into the decision-making process and frequently not interpretable to practitioners. We conducted a user study with a proposed risk assessment system that consists of a prediction module, explanation module, and prototype user interface. The prediction module consists of a logistics regression model capable of distinguishing the injury risk levels induced by different levels of force exertion in common lifting tasks. The logistics regression model makes predictions based on explainable body motion, posture, and facial features extracted through computer vision techniques. The explanation module makes up of explainable AI techniques. Specifically, a surrogate model provides local explanations for presenting how the system makes each prediction to users. The prototype interface presents the system’s predictions and explanations. A usability study shows that the proposed system increases crowd-workers’ and domain scholars’ performance in assessing workers’ injury risks in lifting. Furthermore, the usability study also shows that the proposed system increases their confidence in the assessment tasks when the system’s evaluations agree with their subjective evaluations.

Monitoring surgeon workload during robot-assisted surgery can guide allocation of task demands, adapt system interfaces, and assess the robotic system's usability. Current practices for measuring cognitive load primarily rely on questionnaires that are subjective and disrupt surgical workflow. To address this limitation, a computational framework is demonstrated to predict user workload during telerobotic surgery. This framework leverages wireless sensors to monitor surgeons’ cognitive load and predict their cognitive states. Continuous data across multiple physiological modalities (e.g., heart rate variability, electrodermal, and electroencephalogram activity) were simultaneously recorded for twelve surgeons performing surgical skills tasks on the validated da Vinci Skills Simulator. These surgical tasks varied in difficulty levels, e.g., requiring varying visual processing demand and degree of fine motor control. Collected multimodal physiological signals were fused using independent component analysis, and the predicted results were compared to the ground-truth workload level. Results compared performance of different classifiers, sensor fusion schemes, and physiological modality (i.e., prediction with single vs. multiple modalities). It was found that our multisensor approach outperformed individual signals and can correctly predict cognitive workload levels 83.2% of the time during basic and complex surgical skills tasks.

In Robot-Assisted Surgery, predicting surgeon attributes such as task workload, operation performance, and expertise levels is important in providing tailored assistance. This paper proposes Joint Inference for Surgeon Attributes Prediction (JISAP), a computational framework to jointly infer surgeon attributes (i.e., task workload, operation performance, and expertise level) from multimodal physiological signals (heart rate variability, wrist motion, electrodermal, electromyography, and electroencephalogram activity). JISAP was evaluated with a dataset of twelve surgeons operating on the da Vinci Skills Simulator. It was found that JISAP can simultaneously predict surgeon attributes with a percentage error of 11.05%. Additionally, joint inference was found to outperform isolated inference with a boost of 10%.

OBJECTIVE: We assess working relationships and collaborations within and between diabetes health care provider teams using social network analysis and a multi-scale community detection. MATERIALS AND METHODS: Retrospective analysis of claims data from a large employer over 2 years was performed. The study cohort contained 827 patients diagnosed with diabetes. The cohort received care from 2567 and 2541 health care providers in the first and second year, respectively. Social network analysis was used to identify networks of health care providers involved in the care of patients with diabetes. A multi-scale community detection was applied to the network to identify groups of health care providers more densely connected. Social network analysis metrics identified influential providers for the overall network and for each community of providers. RESULTS: Centrality measures identified medical laboratories and mail-order pharmacies as the central providers for the 2 years. Seventy-six percent of the detected communities included primary care physicians, and 97% of the communities included specialists. Pharmacists were detected as central providers in 24% of the communities. DISCUSSION: Social network analysis measures identified the central providers in the network of diabetes health care providers. These providers could be considered as influencers in the network that could enhance the implication of promotion programs through their access to a large number of patients and providers. CONCLUSION: The proposed framework provides multi-scale metrics for assessing care team relationships. These metrics can be used by implementation experts to identify influential providers for care interventions and by health service researchers to determine impact of team relationships on patient outcomes.