Ensemble deep learning for the prediction of proficiency at a virtual simulator for robot-assisted surgery

Background Artificial intelligence (AI) has the potential to enhance patient safety in surgery, and all its aspects, including education and training, will derive considerable benefit from AI. In the present study, deep-learning models were used to predict the rates of proficiency acquisition in robot-assisted surgery (RAS), thereby providing surgical programs directors information on the levels of the innate ability of trainees to facilitate the implementation of flexible personalized training. Methods 176 medical students, without prior experience with surgical simulators, were trained to reach proficiency in five tasks on a virtual simulator for RAS. Ensemble deep neural networks (DNN) models were developed and compared with other ensemble AI algorithms, i.e., random forests and gradient boosted regression trees (GBRT). Results DNN models achieved a higher accuracy than random forests and GBRT in predicting time to proficiency, 0.84 vs. 0.70 and 0.77, respectively (Peg board 2), 0.83 vs. 0.79 and 0.78 (Ring walk 2), 0.81 vs 0.81 and 0.80 (Match board 1), 0.79 vs. 0.75 and 0.71 (Ring and rail 2), and 0.87 vs. 0.86 and 0.84 (Thread the rings 2). Ensemble DNN models outperformed random forests and GBRT in predicting number of attempts to proficiency, with an accuracy of 0.87 vs. 0.86 and 0.83, respectively (Peg board 2), 0.89 vs. 0.88 and 0.89 (Ring walk 2), 0.91 vs. 0.89 and 0.89 (Match board 1), 0.89 vs. 0.87 and 0.83 (Ring and rail 2), and 0.96 vs. 0.94 and 0.94 (Thread the rings 2). Conclusions Ensemble DNN models can identify at an early stage the acquisition rates of surgical technical proficiency of trainees and identify those struggling to reach the required expected proficiency level.

Clinical incident reporting behaviors and associated factors among health professionals in Dessie comprehensive specialized hospital, Amhara Region, Ethiopia: a mixed method study

Background Understanding the type and causes of errors are necessary for the prevention of occurrence or reoccurrence. Therefore addressing the behavior of health professionals on reporting clinical incidents is crucial to create spontaneous knowledge from mistakes and enhance patient safety. Method A mixed type institution-based cross-sectional study design was conducted from March 1 - 30, 2020 in Dessie comprehensive specialized hospital among 319 and 18 participants for the quantitative and qualitative study, respectively. The professions and participants with their assigned proportions were selected using a simple random sampling technique. For quantitative and qualitative data, semi structured questionnaires and interviewer-guided questions were used to collect data, respectively. Finally, qualitative findings were used to supplement the quantitative result. Result The finding showed that the proportion of clinical incident reporting behavior among health professionals was 12.4%. Having training (AOR=3.6, 95% CI, 1.15-11.45), incident reporting help to minimize errors (AOR=2.8, 95% CI, 1.29-6.02), fear of legal penalty (AOR= 0.3, 95% CI, 0.13-0.82), and lack of feedback (AOR=0.3, 95% CI, 0.11-0.90) were identified as significant factors for clinical incident reporting behavior of the health professionals. Conclusions This study showed that the clinical incident reporting behavior of the health professionals was very low. Therefore health professionals should get training on clinical incident reporting and the hospital should have an incident reporting system and guideline.

A Qualitative Analysis of Observed Behavior of Pediatric Rapid Response Team Performance

BACKGROUND AND OBJECTIVES Pediatric rapid response teams (RRTs) enhance patient safety, reduce cardiorespiratory arrests outside the PICU, and detect deteriorating patients before decompensation. RRT performance may be affected by failures in communication, poor team dynamics, and poor shared decision-making. We aimed to describe factors associated with team performance using direct observation of pediatric RRTs. METHODS Our team directly observed 73 in situ RRT activations, collected field notes of qualitative data, and analyzed the data using conventional content analysis. To assess accuracy of coding, 20% of the coded observations were reassessed for interrater reliability. The codes influencing team performance were categorized as enhancers or threats to RRT teamwork and organized under themes. We constructed a framework of the codes and themes, organized along a spectrum of orderly versus chaotic RRTs. RESULTS Three themes influencing RRT performance were teamwork, leadership, and patient and family factors, with underlying codes that enhanced or threatened RRT performance. Novel factors that were found to threaten team performance included indecision, disruptive behavior, changing leadership, and family or patient distress. Our framework delineating features of orderly and chaotic RRTs may be used to inform training and design of RRTs to optimize performance. CONCLUSIONS Observations of in situ RRT activations in a pediatric hospital both verified previously described characteristics of RRTs and identified new characteristics of team function. Our proposed framework for understanding these enhancers and threats may be used to inform future interventions to improve RRT performance.

Influences of Physical Layout and Space on Patient Safety and Communication in Ambulatory Oncology Practices: A Multisite, Mixed Method Investigation

Objective: To examine how physical layouts and space in ambulatory oncology practices influence patient safety and clinician communication. Background: Ambulatory oncology practices face unique challenges in delivering safe care. With increasing patient volumes, these settings require additional attention to support patient safety and efficient clinical work processes. Methods: This study used a mixed methods design with sequential data collection. Eight ambulatory oncology practices (of 29 participating practices) participated in both the quantitative and qualitative phases. In surveys, clinicians ( n = 56) reported on safety organizing and communication satisfaction measures. Qualitative data included observations and semistructured interviews ( n = 46) with insight into how physical layout influenced care delivery. Quantitative analysis of survey data included descriptive and correlational statistics. Qualitative analysis used inductive and thematic content analysis. Quantitative and qualitative data were integrated using side-by-side comparison tables for thematic analysis. Results: Safety organizing performance was positively correlated with clinician communication satisfaction, r(54 df) = .414, p = .002. Qualitative analyses affirmed that the physical layout affected communication around chemotherapy infusion and ultimately patient safety. After data integration, safety organizing and clinician communication were represented by two themes: visibility of patients during infusion and the proximity of clinicians in the infusion center to clinicians in the clinic where providers see patients. Conclusions: Physical layouts of ambulatory oncology practices are an important factor to promote patient safety. Our findings inform efforts to construct new and modify existing infusion centers to enhance patient safety and clinician communication.

A novel approach to explore Safety-I and Safety-II perspectives in in situ simulations—the structured what if functional resonance analysis methodology

Objectives With ever increasingly complex healthcare settings, technology enhanced simulation (TES) is well positioned to explore all perspectives to enhance patient safety and patient outcomes. Analysis from a Safety-II stance requires identification of human adjustments in daily work that are key to maintaining safety. The aim of this paper is to describe an approach to explore the consequences of human variability from a Safety-II perspective and describe the added value of this to TES. Methods The reader is guided through a novel application of functional resonance analysis methodology (FRAM), a method to analyse how a system or activity is affected by human variability, to explore human adaptations observed in in situ simulations (ISS). The structured applicability of this novel approach to TES is described by application to empirical data from the standardised ISS management of paediatric time critical head injuries (TCHI). Results A case series is presented to illustrate the step-wise observation of key timings during ISSs, the construction of FRAM models and the visualisation of the propagation of human adaptations through the FRAM models. The key functions/actions that ensure the propagation are visible, as are the sequelae of the adaptations. Conclusions The approach as described in this paper is a first step to illuminating how to explore, analyse and observe the consequences of positive and negative human adaptations within simulated complex systems. This provides TES with a structured methodology to visualise and reflect upon both Safety-I and Safety-II perspectives to enhance patient safety and patient outcomes.

Standardized Handoffs After Pediatric Residency: Retention of Practices and Perceived Importance

The I-PASS Handoff Program is linked to reduced medical errors. The enduring handoff practices of residency graduates trained in I-PASS, and attitudes thereof, are unknown. Our objective was to investigate how often residency graduates use I-PASS or other handoff tools, and perspectives regarding standardized handoffs beyond residency. We performed an exploratory electronic survey of residency graduates from programs who participated in the original I-PASS study. Responses were analyzed using descriptive statistics. Of the 106 respondents, 64/106 (60%) identified as “attendings” and the remainder of respondents were subspeciality fellows. The most common practice setting was the inpatient hospital setting, 42/106 (39%). Regarding handoff use, 61/106 (58%) “rarely” or “never” used standardized handoffs. Of those using handoffs, 13/76 (17%) used I-PASS and 59/76 (78%) used a personal system. Most (95/101, 94%) were unaware of any dedicated handoff training or reported it did not exist for attendings, although 77/106 (73%) endorsed their importance for attendings. Despite rigorous residency training and belief in its importance, over one third of graduates did not use standardized handoffs. System-wide requirements for standardized handoffs may improve communication among all providers including physicians, advanced practice providers, and nurses, and enhance patient safety.

COVID-19 and Open Notes: A New Method to Enhance Patient Safety and Trust (Preprint)

UNSTRUCTURED From April 5, 2021, as part of the 21st Century Cures Act, all providers in the US must offer patients access to the medical information housed in their electronic records. Via secure health portals, patients can login to access lab and test results, lists of prescribed medications, referral appointments, and the narrative reports written by clinicians (so-called ‘open notes’). As US providers implement this practice innovation, we describe six promising ways in which patient access to their notes might help address problems that either emerged with, or were exacerbated, by the COVID-19 pandemic