Journal of Information and Optimization Sciences

Will J., Small W., Iturrate E., Testa P., Feldman J.

Abstract Background Electronic health record secure messaging (EHRSM) is an increasingly utilized tool for communication among clinicians. However, there is concern about the growing quantity of disruptions it presents via interruptive notification. Objectives The primary aim of this study is to assess whether introducing emoji reactions, which do not trigger push notifications in EHRSM, can alleviate the burden of interruptive notifications. The second aim is to use messaging notification metadata to identify subgroups that might benefit from targeted interventions to aid the adoption of this innovation. Methods We implemented the emoji reaction feature into EHRSM across a large academic health system. We evaluated the volume of push notifications 11 weeks before (pre-emoji period) and after (post-emoji period) introducing emoji reactions in EHRSM. Notification metadata was categorized by user type, and users were stratified based on notification volume. Results There were 1,387,506 fewer push notifications in the post-emoji period (a decrease of 4.7%). Subgroups of users with increasing mean daily push notifications in the pre-emoji period were associated with decreasing mean daily push notifications in the post-emoji period. Among the eight user subgroups, six experienced a significant reduction in interruptive notifications, with the pharmacy and “other” subgroups not observing a reduction. Users in the top quartile of notification volume saw the greatest reduction in burden across each user subgroup. Conclusion Integrating emoji reactions into EHRSM across a large academic health system significantly reduced the burden of push notifications among EHRSM users. Utilizing messaging notification metadata allowed us to identify subgroups that require additional intervention.

Mahendraker N., Gutierrez-Asis E., Park S., Williams L.S., Schleyer T., Umberfield E.E.

Abstract Background Mortality prediction data may aid in identifying seriously ill transferred patients at high risk of dying and facilitate early goals-of-care discussions (GOCD); however, this is rarely evaluated. We recently developed a model for predicting 30-day inpatient mortality, which may be useful for promoting early GOCD. Objectives Our objectives were to examine the effects of sharing model-generated mortality risk with hospitalists by assessing (1) if hospitalists agreed with the mortality risk prediction, (2) if they planned to conduct GOCD or consult palliative care within 72 hours of transfer, and (3) if the communication alert affected GOCD timing and other clinical outcomes. We also aimed to measure the association between both the model-generated and hospitalists' stratified risk assessments with patient mortality. Methods This was a nonrandomized quasi-experimental pilot study with a historical control group. On the second day of hospitalization, the model-generated risk was communicated to the hospitalists. Hospitalists were asked to answer questions via a HIPAA (Health Insurance Portability and Accountability Act)-compliant mobile communication system, and clinical outcomes were extracted via chart review. Results Eighty-four patients (42 in the control and 42 in the intervention group) were included in this study. Hospitalists agreed that all patients in the intervention group were at risk for inpatient mortality. Hospitalists were more likely to indicate a plan to conduct GOCD in the intervention group (n = 9) compared with the control group (n = 4, p < 0.001). In this subset of patients, GOCD was completed within 72 hours in 78% of intervention patients (n = 7) as compared with 50% in the control group (n = 2). The greater absolute value of the model-generated mortality risk was significantly associated with deaths (p = 0.01), similar to the hospitalists' prediction of the mortality risk (p = 0.02). Conclusion Communicating model-generated mortality risk to hospitalists is a promising approach to promote timely GOCD.

Jahedi F., Henman P.W., Ryan J.C.

AbstractIn recent years, despite significant progress in digital psychological interventions (DPIs), the prevalence of psychological issues among young adults remains a concern. While research on the feasibility and effectiveness of DPIs is extensive, there's a growing recognition of the need for a sociotechnical approach to enhance user engagement. This review aims to highlight the importance of integrating diversity, especially sociodemographic characteristics, into DPI design and implementation.The review meticulously examined literature from six academic databases focused on DPIs tailored for users aged 12 to 26, spanning the period between 2009 and 2019. The data extraction process specifically targeted biosocial factors such as gender and ethnicity, as well as sociocultural elements like remoteness and labor force status among users. Among the initial pool of 879 articles, a refined selection of 25 underwent detailed analysis. Intriguingly, 14 of these studies did not treat sociodemographic factors as independent variables, leaving only 11 that did. Notably, gender and ethnicity emerged as the most frequently studied factors, with remoteness and labor force considerations receiving comparatively less attention.Despite the acknowledged importance of user engagement in DPI effectiveness, the review highlights a critical gap: insufficient consideration of young adults' sociodemographic characteristics in intervention design and implementation. Therefore, the findings strongly support further mixed-method studies to fully understand the complex social factors influencing user engagement with DPIs. Closing this gap will undoubtedly refine and optimize DPIs to better meet the diverse needs of young adults dealing with psychological challenges.

Biady Y., Lee T., Pham L., Patanwala A., Poon S., Ritchie A., Burke R., Penm J.

Abstract Background Drug–drug interactions (DDIs) remain a highly prevalent issue for patients in both community and hospital settings. Electronic medication management systems have implemented DDI alerts to mitigate DDI-related harm from occurring. Objectives The primary aim of this study was to explore factors that influence health care professionals' (hospital doctors, hospital pharmacists, general practitioners, and community pharmacists) perceptions and action taken by them in response to DDI alerts. Methods A qualitative study was conducted using semi-structured interviews between early January and late February 2021. The top 20 most frequently triggered DDI alerts previously identified were used as examples of alert prompts shown to participants. Results A total of 20 participants were recruited. General practitioners (n = 4) were most likely to consider DDI alerts to be clinically relevant and important, and hospital doctors (n = 4) were most likely to consider these alerts not being clinically relevant nor important. Three main factors were identified to influence health care professionals' perceptions of DDI alerts, which included clinical relevance, visual presentation, and content of alerts. Conclusion Health care professionals' perceptions of DDI alerts are influenced by multiple factors and considerations are required to create tailored alerts for users and their clinical contexts. Improvement in DDI alerts should be a priority to improve patient medication safety and health outcomes.

Vivanti A., Murray E., Doola R., Hill J., Sullivan C.

Abstract Background Coronavirus disease 2019 (COVID-19) forced health care services to introduce virtual service delivery. Little is known about the impact on health care service delivery. Objectives This case study reports the impact of introducing remote access facilitating virtual service delivery. Methods Key performance indicators of health care service delivery (Nutrition and Dietetic Department, 26.9 full-time equivalents) were monitored over three 6-month periods. These periods were Phase 1 (pre-COVID restrictions), Phase 2 (zero tolerance to COVID), and Phase 3 (living with COVID). Virtual service delivery was initiated between Phases 1 and 2. Virtual service delivery days were defined as days worked virtually in lieu of leave. Results During Phase 2 and Phase 3, there were 87 and 188 extra days of virtual service delivery achieved and an opportunity cost saving of $26,000 USD and $56,000 USD, respectively. Leave hours reduced between Phases 1 and 2 (p < 0.006; mean ± standard deviation [SD] 591 ± 213 and 222 ± 91) and maintained between Phases 1 and 3 (p < 0.342; mean ± SD 494 ± 98) despite the pandemic. No adverse clinical events were reported. Professional quality of life scores were maintained. Conclusion Virtual service delivery through remote access provided many days of otherwise potentially lost productivity, maintained patient care with no adverse events, and sustained Professional Quality of Life despite pandemic challenges. Operationally, lessons learnt included the importance of positive team culture to working effectively, keeping teams connected and adapting different solutions to meet teams' requirements. Incorporating virtual service delivery options into a hospital clinical department showed performance stability across key service performance indicators during the COVID-19 pandemic.

Shu D., Xu C.T., Pandey S., Walls V., Tenney K., Georgilis A., Melink L., Wu D.T., Molano J.R.

Abstract Background Clinician burnout is increasingly prevalent in the health care workplace. Hospital leadership needs an informatics tool to measure clinicians' well-being levels and provide empirical evidence to improve their work environment. Objectives This study aimed to (1) design and implement a web-based application to collect and visualize clinicians' well-being levels and (2) conduct formative usability evaluation. Methods Clinician and staff well-being champions guided the development of the Well-being Check application. User-centered design and Agile principles were used for incremental development of the app. The app included a customizable survey and an interactive visualization. The survey consisted of six standard, two optional, and three additional questions. The interactive visualization included various charts and word clouds with filters for drill-down analysis. The evaluation was done primarily with the rehabilitation (REHAB) team using data-centered approaches through historical survey data and qualitative coding of the free-text explanations and user-centered approaches through the System Usability Scale (SUS). Results The evaluation showed that the app appropriately accommodated historical survey data from the REHAB team, enabling the comparison between self-assessed and perceived team well-being levels, and summarized key drivers based on the qualitative coding of the free-text explanations. Responses from the 23 REHAB team members showed an above-average score (SUS: 80.22), indicating high usability of the app. Conclusion The Well-being Check app was developed in a user-centered manner and evaluated to demonstrate its effectiveness and usability. Future work includes iterative refinement of the app and designing a pre-poststudy using the app to measure the change in clinicians' well-being levels for quality improvement intervention.

Leonard L.D., Driscoll B., Vemuru S., Kovar A., Billings J., Kim S., Lin C., Tevis S., Cumbler E.

Abstract Background Patient-reported outcome measures (PROMs) are standardized, validated tools that translate subjective patient-reported concerns about their health status into quantitative data. PROMs were initially developed as research instruments; however, they have more recently been recognized as important clinical tools. PROMs have not been widely adopted into surgical practices and this study sought to uncover the system requirements of a platform to integrate PROMs into surgical practice, as perceived by surgeons. Methods Semi-structured interviews were performed from November 2019 until August of 2020. Interviews continued until thematic saturation was achieved. All interviews were recorded and transcribed verbatim. Qualitative interview data were thematically analyzed using an inductive approach. Results Analysis revealed 12 system features desired by surgeons for a platform to integrate PROMs into clinical use. These were further grouped into four unique overarching themes. Surgeons asserted that the platform must (1) be user-friendly, (2) promote information transparency, (3) incorporate validated questionnaires while still allowing for some degree of customizability, and (4) support the collection and display of longitudinal data. Conclusions Health care systems planning to develop a platform to integrate PROMs into their clinical practices should investigate the feasibility of the system features identified as essential by this study. While surgeons represent an important stakeholder group when designing a new platform for use in surgical practice, it will also be crucial to explore the features desired by patients before designing or adopting a platform for clinical use.

Clarke M.A., Wardian J.L., Fleharty B.S., Reha C.G., Birge J.R.

Abstract Objective This study aimed to improve the quality measure performance for indwelling urinary catheter (IUC) duration, central venous catheter (CVC) duration, and telemetry duration by redesigning clinical decision support (CDS) tools within the documentation process and order workflow. Methods The effectiveness of the redesign was evaluated using system standard quality reporting methodology to observe device duration, central-line-associated bloodstream infection (CLABSI) rate, and catheter-associated urinary tract infection (CAUTI) rate preintervention (FY2017) and postintervention (FY2018). Electronic health record (EHR) reporting tools were used to evaluate CDS alert data both preintervention and postintervention. Results Total device duration and line days per patient days were reduced for CVC (12.8% [0.305–0.266]) and IUC (4.68% [0.171–0.163]). Mean telemetry duration was reduced by 16.94% (3.72–3.09 days), and CDS alert volume decreased 18.6% from a preintervention mean of 1.18 alerts per patient per day (81,190 total alerts) to a postintervention mean of 0.96 alerts per patient per day (61,899 total alerts). Both CLABSI (2.8% [1.07–1.04]) and CAUTI (8.1% [1.61–1.48]) rates were reduced, resulting in approximately $926,000 in savings. Conclusion In this novel model, the redesigned CDS tools improved clinician response to CDS alerts, prompting providers to take action on relevant orders that automatically updated the clinical documentation to reflect their actions. The study demonstrated that effective redesign of CDS tools within the documentation process and order workflow can reduce device duration, improve patient outcomes, and decrease CDS alert volume.

Epstein J.A., Lkhagvajav Z., Young T., Bertram A., Yeh H., Taylor C.O.

Abstract Objectives The coronavirus disease 2019 (COVID-19) pandemic led to a rapid adoption of telehealth. For underserved populations lacking internet access, telemedicine was accomplished by phone rather than an audio–video connection. The latter is presumed a more effective form and better approximation of an in-person visit. We sought to provide a telehealth platform to overcome barriers for underserved groups to hold video visits with their health care providers and evaluate differences between the two telehealth modalities as assessed by physicians and patients. Methods We designed a simplified tablet solution for video visits and piloted its use among patients who otherwise would have been completing audio-only visits. Patients consented to participation and were randomized in a 1:1 fashion to continue with their scheduled phone visit (control) versus being shipped a tablet to facilitate a video visit (intervention). Participants and providers completed communication and satisfaction surveys. Results Tablet and connectivity design features included removal of all functions but for the telemedicine program, LTE always-on wireless internet connectivity, absence of external equipment (cords chargers and keyboard), and no registration with a digital portal. In total, 18 patients were enrolled. Intervention patients with video-enabled devices compared to control patients agreed more strongly that they were satisfied with their visits (4.75/5 vs. 3.75/5, p = 0.02). Conclusion The delivered simplified tablet solution for video visits holds promise to improve access to video visits for underserved groups. Strategies to facilitate patient acceptance of devices are needed to expand the scope and potential impact of this effort.

Rivera R.L., Hosler H., Jang J.H., Schaffer J.T., Price J., Vest J.R., Schleyer T.K.

Abstract Objectives This article (1) develops a Fast Healthcare Interoperability Resources app, Health Dart, that integrates information from Indiana's community health information exchange (HIE), the Indiana Network for Patient Care (INPC), directly with Cerner, an electronic health record (EHR), and (2) evaluates the effect of Health Dart's implementation on HIE use. Methods Health Dart was implemented in 14 Indiana University Health emergency departments (EDs) using a stepped-wedge study design. We analyzed rates of INPC use in 286,175 ED encounters between October 1, 2019 and December 31, 2020. Logistic regression was used to model the probability of INPC use given the implementation context, such as user interface (UI) enhancements and the coronavirus disease 2019 pandemic. Results INPC use increased by 131% across all encounters (from 3.6 to 8.3%; p < 0.001) after Health Dart implementation. INPC use increased by 144% (from 3.6 to 8.8%; p < 0.001) more than 2 months postimplementation. After UI enhancements, postimplementation INPC use increased by 123% (from 3.5 to 7.8%) compared to 181% (from 3.6 to 10.1%; p < 0.001) in postimplementation encounters that occurred before UI enhancements. During the pandemic, postimplementation INPC use increased by 135% (from 3.4 to 8.0%; p < 0.001) compared to 178% (from 3.6 to 10%; p < 0.001) in postimplementation encounters that occurred before the pandemic. Statistical significance was determined using 95% confidence intervals (α = 0.05). Conclusion Direct integration of HIE information into an EHR substantially increased frequency of HIE use, but the effect was weakened by the UI enhancements and pandemic. HIE information integrated into EHRs in the form of problem-oriented dashboards can potentially make information retrieval more efficient and effective for clinicians.

Shannon E.M., Mueller S.K., Schnipper J.L.

Abstract Objectives As part of a study to assess whether a technologically enabled pillbox prescribed to patients at hospital discharge can improve medication safety, we sought to assess participant experiences with the intervention. Methods We conducted a series of semi-structured phone interviews with patients, patient caregivers, and inpatient and outpatient clinicians who participated in the Smart Pillbox Transition Study. We developed an interview guide using the Systems Engineering Initiative for Patient Safety (SEIPS) framework, which included the a priori domains of (1) barriers to implementation, (2) facilitators of the intervention, and (3) general feedback regarding experience with the intervention. Within these domains, we employed SEIPS-informed themes of environment and organization, logistics and tasks, personnel and patients, and technology and tools. Interviews were conducted between May 2018 and January 2019. We used content analysis to interpret findings. Results We interviewed 6 patients, 2 caregivers, and 5 inpatient and 2 outpatient clinicians. Patient-endorsed barriers in the theme of technology and tools included signal issues, inappropriate alarms, and portability. Barriers in the theme of logistics and tasks included coordination with pharmacists in the event of a prescription change. Barriers mentioned by clinicians included patients who were poor fits for the intervention (theme: personnel and patients) and competing demands at discharge (theme: logistics and tasks). Facilitators that were frequently mentioned by patients and caregivers in the theme of technology and tools included useful alarms and ease of use. Clinicians stated that communication with pharmacy and study staff helped facilitate the intervention (theme: personnel and patients). Conclusion We identified several key barriers and facilitators from patients, caregivers, and clinicians to successful implementation of this intervention. Reconciling these sometimes contrasting viewpoints will be crucial if the Smart Pillbox or similar health information technology interventions are to be adopted as tools to improve medication safety during care transitions.

Kadhim B., Khairat S., Li F., Gross I.T., Nath B., Hauser R.G., Melnick E.R.

Abstract Background Physician fatigue increases the likelihood of medical errors. Eye-tracking technology offers an unobtrusive and objective way to measure fatigue but has only been implemented in controlled settings. Objective Our objective was to determine the feasibility of capturing physiological indicators of fatigue using eye-tracking technology in a real-world clinical setting. Methods A mixed-methods feasibility study was performed in a convenience sample of clinicians practicing in an urban, academic emergency department from November 11 to December 15, 2021. Outcomes included fatigue assessed at the beginning and end of each shift via eye-tracking (with low scores indicating greater fatigue) and self-report. Results Among 15 participants, self-reported fatigue and task load increased from the beginning to the end of their shift (fatigue visual analog scale [FVAS] 3.7–4.6, p = 0.04; physician task load [PTL] 97.7–154.3, p = 0.01). It was feasible to collect eye-tracking data at a fixed computer workstation with twice daily calibration and 61% capture of reliable data when the clinician was working at the study computer. Eye-tracking metrics did not change significantly from the beginning to the end of the shift. Eye metric fatigue score was associated with the change in PTL score (r 0.59, p = 0.02) but not FVAS. This association persisted after adjusting for age, gender, and role, with every 10-point increase in PTL, there was a 0.02-point increase in fatigue score (p = 0.04). Conclusion It is unclear whether the inability to detect fatigue via eye-tracking in routine clinical care was due to confounding factors, the technology, study design, sample size, or an absence of physiological fatigue. Further research and advances in functionality are needed to determine the eye-tracking technology's role in measuring clinician fatigue in routine care.

Inagaki S., Kato K., Abe K., Takahashi H., Matsuda T.

Abstract Background People with diabetes are increasingly using smartphone health care applications (apps) to manage their health. However, few studies have examined the percentage of people with diabetes using health care apps and their relationship to self-care. Objective The purpose of this study is to determine the prevalence of health care apps among people with diabetes and the relationship between app use and self-management. Methods A cross-sectional study was conducted using an online survey among people with type 2 diabetes. Multiple linear regression analysis was conducted using the scores of the Japanese version of Summary of Diabetes Self-Care Activities and exercise and general diet subscales as the objective variables. Results Of 253 participants included in this study, 61 (24.1%) used health care apps. Approximately 20% of those aged ≥ 60 also used health care apps. Use of health care apps was a significant predictor of physical activity frequency along with autonomous motivation (p < 0.001). Participants who used health care apps showed a 0.91 point higher physical activity score than those who did not. Regarding the general diet score, the use of health care apps was not significantly associated with dietary habits (p = 0.29). Conclusion Among people with type 2 diabetes, 24.1% used health care apps, and self-management scores of exercise were significantly higher in people with diabetes who used health care apps than in those who did not.

Walters J.S., Higgins D., Irving M.J., Wallace J.P.

Abstract Background Business intelligence can give businesses the ability to understand their strengths, weaknesses, and opportunities for improvement and can help reduce uncertainty in the decision-making process. With the increasing use of electronic dental records creating more and more dental data each day, it is an opportune time to determine if the data can be coupled with business intelligence systems to improve the management decision-making process in dental organizations to result in service improvement. Methods A scoping review was performed to map the research on the use of business intelligence in dental organizations and to identify any gaps in the existing literature. This scoping review was conducted following the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-Scr) framework. The following databases were searched: Medline, Embase, Emcare, Cinahl, Informit, Web of Science, and Scopus. Data extracted from the articles included the organization type, purpose/aims, the software utilized, data sources utilized, outcomes measured, decision-makers involved, service benefit type, and service improvements. Results In all, 945 articles were found during the search strategy, with 25 articles selected for full-text review. Of these 25 articles, only 3 met the final inclusion in this review. All three included articles were centered around dental school organizations and all situated in the United States. All three articles demonstrated a benefit from management decision-makers utilizing business intelligence systems for improving service efficiency. Conclusion There is limited evidence to show that managers utilizing business intelligence systems in dental school organizations can lead to improvements in the organization's services. There was no evidence to support the use of a business intelligence system in other types of dental organizations. More research is required in this area.

Nekrasova E., Fiks A.G., Wynn C., Torres A., Griffith M., Shone L.P., Localio R., Shults J., Unger R., Ware L.A., Stockwell M.S.

Abstract Background Text messages can be an effective and low-cost mechanism for patient reminders; however, they are yet to be consistently integrated into pediatric primary care. Objective The aim of this study was to explore pediatric primary care clinician and staff perceptions of pediatric office text message communication with families. Methods As part of the National Institutes of Health–funded Flu2Text randomized controlled trial of second-dose influenza vaccine text message reminders, we conducted 7 focus groups and 4 individual interviews in July–August 2019 with primary care pediatric clinicians and staff (n = 39). Overall, 10 Pediatric Research in Office Settings (PROS) pediatric practices in 10 states were selected using stratified sampling. Semi-structured discussion guides included perspectives on possible uses, perceived usefulness, and ease of use of text messages; practices' current text messaging infrastructure; and perceived barriers/facilitators to future use of texting. Two investigators independently coded and analyzed transcripts based on the technology acceptance model using NVIVO 12 Plus (intercoder reliability, K = 0.86). Results Overall, participants were supportive of text reminders for the second-dose influenza vaccine, other vaccines, and appointments and perceived texting as a preferred method of communication for caregivers. Health information privacy and patient confidentiality were the main concerns cited. Only respondents from practices with no internal appointment text message reminder system prior to the study expressed concerns about technology implementation logistics, time, and cost. Conclusion Text message reminders, for various uses, appear to be well accepted among a group of geographically widespread pediatric practices after participation in a trial of influenza vaccine text message reminders. Privacy, confidentiality, and resource barriers need to be addressed to facilitate successful implementation.