Moriarty, James

Abstract Objective Hospital acquired infections (HAIs) are one of the top 10 leading causes of death within the United States. While current standard of HAI risk prediction utilizes only a narrow set of predefined clinical variables, we propose a graph convolutional neural network (GNN)-based model which incorporates a wide variety of clinical features. Materials and Methods Our GNN-based model defines patients’ similarity based on comprehensive clinical history and demographics and predicts all types of HAI rather than focusing on a single subtype. An HAI model was trained on 38 327 unique hospitalizations while a distinct model for surgical site infection (SSI) prediction was trained on 18 609 hospitalization. Both models were tested internally and externally on a geographically disparate site with varying infection rates. Results The proposed approach outperformed all baselines (single-modality models and length-of-stay [LoS]) with achieved area under the receiver operating characteristics of 0.86 [0.84–0.88] and 0.79 [0.75–0.83] (HAI), and 0.79 [0.75–0.83] and 0.76 [0.71–0.76] (SSI) for internal and external testing. Cost-effective analysis shows that the GNN modeling dominated the standard LoS model strategy on the basis of lower mean costs ($1651 vs $1915). Discussion The proposed HAI risk prediction model can estimate individualized risk of infection for patient by taking into account not only the patient’s clinical features, but also clinical features of similar patients as indicated by edges of the patients’ graph. Conclusions The proposed model could allow prevention or earlier detection of HAI, which in turn could decrease hospital LoS and associated mortality, and ultimately reduce the healthcare cost.

Importance: A postoperative video telemedicine follow-up program was introduced by the Mayo Clinic. An attempt was made to understand the potential cost savings to patients before contemplating full-scale expansion across all potentially eligible surgical patients and practices. Objective: The primary purpose was to estimate potential cost savings to patients with video telemedicine follow-up to home compared with face-to-face follow-up in a standard clinic setting. Design: The research was designed collaboratively by the Center for Connected Care and the surgical practice to address the question of estimated cost savings of postoperative video telemedicine visits. The intervention arm is the postoperative video telemedicine follow-up visit to home setting and the comparator is the face-to-face visit at Mayo Clinic. Setting: Large, integrated, academic multispecialty practice supporting patient care delivery, research, and education. Participants: The population under study comprised routine uncomplicated postoperative patients who underwent video telemedicine or face-to-face follow-up visits that fell within the 90-day global period across multiple (general, neurosurgery, plastic, thoracic, transplant, and urology) surgical specialties. Main Outcome(s) and Measure(s): Economic outcomes were cost of travel, accommodations, meals, and missed work. Additional outcomes included time expenditure and patient satisfaction. Cost/benefit analysis unit was US dollars (USD). All costs were inflated to 2018 USD, using the Gross Domestic Product Implicit price deflator. Results: Patients who utilized video telemedicine rather than face-to-face clinic visit for postoperative follow-up were estimated to save $888 per visit on average. More specifically, patients residing more than 1,635 miles round trip from clinic saved an estimated $1,501 per visit and patients not needing accommodation still saved an estimated $256 per visit. Patient satisfaction over video telemedicine postoperative follow-up visits remained high over the 6-year period of study. Conclusions and Relevance: The use of video telemedicine for routine uncomplicated postoperative follow-up visits to replace face-to-face follow-up visits has the potential to be financially advantageous for patients. Key points Question: For postoperative patients, what are the health economic outcomes associated with video telemedicine follow-up to home compared with face-to-face follow-up in a standard clinic setting? Findings: Video telemedicine offers a cost benefit for patients through avoidance of travel costs and missed work. Meaning: For uncomplicated routine postoperative follow-up visits, video telemedicine is a less costly alternative for most patients.