Background: Active patient engagement may improve their perioperative experience and outcomes. We sought to evaluate the use of a mobile device application (App) for patient engagement and patient reported outcomes (PROs) assessment following robotic lung cancer surgery. Methods: Patients with suspected lung cancer undergoing robotic resection between January-May 2019, were offered the SeamlessMD App, which was customized to meet requirements of the thoracic enhanced recovery pathway. The App guided patients through preoperative preparation, in-hospital recovery, and postop discharge care with personalized reminders, task lists, education, progress tracking, and surveys. Results: Fifty patients participated in the study (22.1%). Of the 50 patients, 20 (40%) patients completed the preoperative compliance survey, and 31 (62%) completed the hospital satisfaction survey. A total of 62 inpatient recovery checks were completed, identifying non-compliance with incentive spirometer use in 2 (3.2%) and patient worries about self-care after discharge in 18 (29%) instances. Postoperative health-checks were completed by 27 (54%) patients with a median of 3 [0-17] completed surveys per patient. Patient reported symptom scores up to 30 days after surgery, demonstrating a significant decrease maximum pain level (P=0.002) and anxiety scores (P<0.001). The App enabled health-checks improved confidence and decreased worries in over 80% of patients. Nine patients (40.9%) reported the health-checks helped avoid 1+ calls and 4 (18.2%) reported the App helped avoid 1+ visits to the hospital. Over 74% of patients reported the App was very or extremely useful in each of the preoperative, inpatient, and post-discharge settings. Conclusions: A mobile device platform may serve as an effective mechanism to record perioperative PROs and satisfaction while facilitating patient-provider engagement in perioperative care.

No abstract

No abstract

With all of the research and investment dedicated to artificial intelligence and other automation technologies, there is a paucity of evaluation methods for how these technologies integrate into effective joint human-machine teams. Current evaluation methods, which largely were designed to measure performance of discrete representative tasks, provide little information about how the system will perform when operating outside the bounds of the evaluation. We are exploring a method of generating Extensibility Plots, which predicts the ability of the human-machine system to respond to classes of challenges at intensities both within and outside of what was tested. In this paper we test and explore the method, using performance data collected from a healthcare setting in which a machine and nurse jointly detect signs of patient decompensation. We explore the validity and usefulness of these curves to predict the graceful extensibility of the system.

Background Operable esophageal carcinoma is potentially curable with surgical resection. The short-term outcomes and overall survival rate for operable esophageal carcinoma may be impacted by the healthcare facility type where patients receive care. Methods A total of 37, 271 cases with the American Joint Committee on Cancer clinical stage I, II, and III esophageal carcinoma that were reported to the National Cancer Data Base at over 12,721 facilities were analyzed. Healthcare facilities were dichotomized into the community and academic facility types. Marginal multivariable Cox proportional hazard models were used to evaluate differences in overall survival between facility types, which accounted for facility esophageal cancer volume. Propensity score methodology with inverse probability of treatment weighting was used to adjust for patient related baseline differences between facility types. Results Patients with clinical stage I-III esophageal carcinoma who underwent esophagectomy at academic healthcare facilities had a significantly better overall survival compared with patients who underwent esophagectomy at community healthcare facilities [HR = 0.89: CI [0.84-0.95] (p = 0.0005)]. The rate of esophagectomy was significantly higher at the academic facilities (49.0% versus 26.5%; p < 0.0001). The 30-day and 90-day mortality rates for esophagectomy were significantly better for patients who underwent esophagectomy for esophageal cancer at the academic facility types. Conclusion Patients with clinical stage I-III esophageal carcinoma who received care at academic facility types had significantly better overall survival compared with community facility types. The utilization of esophagectomy was significantly higher and the short-term surgical outcomes were better for patients treated at academic facility types.

We introduce the concept of machine fitness assessment, which is the process of correctly determining the degree of fit between a machine’s inferences on a specific world and the world itself. We describe its importance in complex, high-stakes worlds, including healthcare, and how it will be critically important to realize the potential of consumer health technologies that promise institutional-quality health diagnosis and planning in decidedly non-institutional settings (e.g., our homes, offices, or anywhere else).

Decompensation is a change in the overall ability to maintain physiological function in the presence of a stressor or disease. In the medical setting, clinicians utilize a wide range of technological tools to aid in their clinical decision making and to identify early warning signals for decompensation. However, many of these technologies have underperformed and are not aligned with the actual role of practitioners, resulting in unintended consequences and adverse events. The primary aim of this study is to explore how different nurses interpret early warning signs in order to anticipate decompensation. The secondary aim is to assess which technologies nurses rely on when anticipating decompensation, and if those technologies are adequately aiding them in their clinical decision making. Two researchers performed semi-structured ethnographic interviews that were recorded and transcribed during the summer of 2017. In total, 43 nurses were interviewed from different medical and surgical floors within the same hospital. Participants were asked questions focused on how they use and respond to alarms and how they anticipate patient decompensation. Constant Comparative Analysis was used to reveal patterns of responses between participants. Based on the qualitative analysis 6 major themes emerged:  1. Anticipating patient decompensation requires creating a complete mental “picture of the patient” by the nurses  2. Nurse-to-nurse communication and expertise is essential to understanding the patient’s history  3. Warning signs for decompensation were largely determined by a patient’s baseline  4. Change over time, or trends, is informative for anticipating decompensation. Numbers (regarding vital signs and labs) alone are not  5. Consistent care of patients improved nurse’s confidence in decision making  6. Anticipating decompensation requires “staying ahead of the machines Our research suggests that there is a gap between the information practitioners need to accurately anticipate patient decompensation, and the information current alarm technologies provide. Alarms are the primary tool provided to nurses to aid them in detecting hazardous events, however, current alarms are not well-suited in supporting signals that anticipate patient decompensation before it happens.

No abstract