Nationally, it has been estimated that 10 to 21% of children with psychosocial concerns are seen in primary care settings (Jellinek et al., 1999; McInerny, Szilagyi, Childs, Wasserman & Kelleher, 2000; Palermo et al., 2002). Often, however, children go undiagnosed with/treated for psychosocial concerns in pediatric primary care due to lack of physician time and poor referral rates to mental health providers. Evaluations of integrated care models, in which a behavioral health consultant is present in primary care practices, has shown to increase the availability of mental health services (Stancin, Perrin, & Ramirez, 2009). Using extant data from patient records extracted by a trained nurse, this study aims to assess practice scheduling habits and seasonal variation in behavioral health consultant (BHC) usage on days when a BHC is present versus non-BHC days in one rural pediatric office over the course of four years. This study aims to evaluate economic efficiency based on the number of patients scheduled per day. It is hypothesized that the presence of an onsite BHC will increase patient volume and, thus, economic efficiency. Information gathered from the clinic’s electronic scheduling system included: 1) the number of patients scheduled on a BHC day and 2) the number of patients scheduled on a non-BHC day for each week of the BHC’s employment. These data—both overall and by year and season—were analyzed using one-way ANOVA and post hoc Tukey testing. There were no significant differences in scheduled patient volume found between the day types overall. However, yearly analysis revealed significant differences between 2010 and 2012, 2013, and 2014 on BHC days and between 2010 and 2014 on non-BHC days. When examined by season, significant differences were found between Fall/Winter and Spring/Summer on both day types in post hoc Tukey testing. These findings have important implications for the trajectory of benefits provided by a BHC in a rural integrated care model.

Accurate predictions of patient volume are an essential tool to improve resource allocation and doctor utilization in the traditional, as well as the digital health care domain. Varying methods for patient volume prediction within the traditional health care domain has been studied in contemporary research, while the concept remains underexplored within the digital health care domain. In this paper, an evaluation of how two different non-linear state-of-the-art time series prediction models compare when predicting patient volume within the digital health care domain is presented. The models compared are the feed forward Multi-layer Percepron (MLP) and the recursive Long Short-Term Memory (LSTM) network. The results imply that the prediction problem itself is straightforward, while also indicating that there are significant differences in prediction accuracy between the evaluated models. The conclusions presented state that that the LSTM model offers substantial prediction advantages that outweigh the complexity overhead for the given problem. / En korrekt förutsägelse av patientvolym är essentiell för att förbättra resursallokering av läkare inom traditionell liksom digital vård. Olika metoder för förutsägelse av patientvolym har undersökts inom den traditionella vården medan liknande studier inom den digitala sektorn saknas. I denna uppsats undersöks två icke-linjära moderna metoder för tidsserieanalys av patientvolym inom den digitala sjukvården. Modellerna som undersöks är multi-lagersperceptronen (MLP) samt Long Short-Term Memory (LSTM) nätverket. Resultaten som presenteras indikerar att problemet i sig är okomplicerat samtidigt som det visar sig finnas signifikanta skillnader i korrektheten av förutsägelser mellan de olika modellerna. Slutsatserna som presenteras pekar på att LSTM-modellen erbjuder signifikanta fördelar som överväger komplexitets- och prestandakostnaden.