Patient portals facilitate patients' access to their electronic health care records, and may also include features such as patient-clinician messaging, prescription renewal, and educational resources. There is evidence that portals support patient empowerment, therapeutic communication, adherence to treatment, and satisfaction with care. Nonetheless, patient portals are underutilized in mental health settings, with policies in some health care organizations restricting all access to mental health records through patient portals. A qualitative evidence synthesis was conducted to explore the perspectives of clinicians and patients on portal use in the mental health care context represented in the current literature. A systematic search of relevant databases, followed by citation and article screening, yielded 24 qualitative and mixed-methods studies for inclusion, and a thematic synthesis was performed. The synthesis yielded five themes: impacts to the efficiency of mental health care delivery; effects on therapeutic relationships between clinicians and patients; changes to the patient-clinician power balance; the suitability of patient portals for patients with mental illness; and the complexities of information management in mental health care. Ultimately, both clinicians and patients acknowledged numerous potential benefits of patient portals, but there were also concerns about their use specific to the mental health context. These concerns were voiced primarily by clinicians, and originated in part from concern for patient safety, but also from stigmatizing attitudes and the perceived threats of portals to clinicians' workloads and control over the record. This systematic review of qualitative studies highlights opportunities for organizations to support their clinicians through the implementation of recovery-oriented initiatives like patient portals, and to support patients with mental illness by ending discriminatory policies limiting access to their records.

Medical health providers use electronic health records (EHRs) to store information about patient treatment to support patient care management and securely share health information among healthcare organizations. EHRs have also been used in healthcare research in problems such as patient phenotyping, health risk prediction, and medical entity extraction. In this thesis, we focus on several important issues: (1) how to convert natural text from medical notes to vector representations suitable for deep learning algorithms, (2) how to help healthcare researchers select a patient cohort from EHRs, and (3) how to use EHRs to identify patient diagnoses and treatments. In the first part of the thesis, we present a new method for learning vector representations of medical terms. Learning vector representations of words is an important pre-processing step in many natural language processing applications. For example, EHRs contain clinical notes that describe patient health conditions and course of treatment in a narrative style. The notes contain specialized medical terminology and many abbreviations. Learning good vector representations of specialized medical terms can improve the quality of downstream data analysis tasks on EHR data. However, the traditional approaches struggle to learn vector representations of rarely used medical terms. To overcome this problem, we developed a neural network-based approach, called definition2vec, that uses external knowledge contained in medical vocabularies. We performed quantitative and qualitative analysis to measure the usefulness of the learned representations. The results demonstrate that definition2vec is superior to the state-of-the-art algorithms. In the second part of the thesis, we describe a new visual interface that helps healthcare researchers select patient cohorts from EHR data. Process of identifying patients of interest for observational studies from EHR data is known as cohort selection, a challenging research problem. We considered a problem of cohort selection from medical claim data, which requires identifying a set of medical codes for selection. However, there are tens of thousands of unique medical codes, and it becomes very difficult for any human to decide which codes identify patients of interest. To help users in defining a set of codes for cohort identification, we developed an interactive system, called Medical Claim Visualization system (MedCV), which visualizes medical code representations. MedCV analyzes a medical claim database and allows users to reason about medical code relationships and define inclusion rules for the selection by visualizing medical codes, claims, and patient timelines. Evaluation of our system through a user study indicates that MedCV enables domain experts to define inclusion rules efficiently and with high quality. The third part of the thesis is a study of the definition of acute kidney injury (AKI), which is a condition where kidneys suddenly cannot filter waste from the blood. AKI is a major cause of patient death in intensive care units (ICU) and it is critical to detect it early. Recently published KDIGO medical guideline proposed a clinical definition of AKI using blood serum creatinine and urine output. The KDIGO definition was developed based on the expert knowledge, but very little is known about how well it matches the medical practice. In this study, we investigated publicly available EHR data from 47,499 ICU admissions to determine the concordance between the KDIGO definition and AKI determination by the medical provider. We show that it is possible to find a formula using machine learning with much higher concordance with the medical provider AKI coding than KDIGO and discuss the medical relevance of this finding. / Computer and Information Science

Purpose:The thesis will shed light on the overall need of CDSSs in the Swedish health care system,  and  it  will  also  present  a  specific  efficiency  problem  that  could  be  solved  by implementing a CDSS. The need for a CDSS is where an implementation would improve patient outcome, by delivering the right care at the right time, and where the CDSS could reduce the cost of the delivered care. A better understanding of the current need could help eliminate the existing empirical gap and ultimately lead to better and more efficient health care in Sweden. The research question was formulated as: Where within Swedish health care can a need for increased efficiency be met through the implementation of a realistic CDSS system? Design and methodology: The  thesis  is  a  case  study  where qualitative data, collected through a literature review and interviews, was used to answer the research question. The methodology used was tailored to the unique setting of the research and in accordance to the purpose of the study. The method was divided into five phases. (1) Finding an area of focus, such as a specific diagnosis, within the health care system where the need for a CDSS system is deemed high. (2) Mapping the care chain of the identified area of interest. (3) Developing hypotheses concerning where in the care chain challenges could be solved using a clinical decision support system. (4) Confirming or rejecting the proposed hypotheses through interviews with relevant experts. (5) Presenting the specific efficiency problem that could be solved using a CDSS and a presentation of the design of said CDSS. Findings: The efficiency problem that could be solved using a CDSS was identified to be within the area of heart failure treatment. There were a multitude of areas of improvement found along the care chain and a number of them could be solved by developing and using specific CDSSs. A CDSS that could help physicians, within the primary care system, to identify patients that  could benefit from  being  assessed  by  cardiology specialist was  proposed  as  the  most beneficial  CDSS  system.  The  proposed  CDSS  would  be  both  beneficial  and  realistically implementable. / Syftet med uppsatsen är att belysa det övergripande behovet av kliniska beslutsstödssystem inom den svenska vården och slutligen finna det mest trängande behovet. En bättre förståelse för detta behov kan hjälpa att minska det existerande empiriska gapet och slutligen leda till en bättre och mer effektiv vård i Sverige. Forskarfrågan formulerades som uppdraget att finna ett behov för ökad effektivitet inom svensk sjukvård, som kan lösas genom implementering av ett realistiskt kliniskt beslutsstöd. Design och metodologi: Uppsatsen är en casestudie där kvalitativ data, samlad genom en litteraturstudie samt intervjuer, användes för att besvara forskningsfrågan. Metodologin som brukades var anpassad efter den unika naturen för forskningen, samt i enighet med syftet av studien. Metoden delades in i fem faser. (1) Finna ett fokusområde, exempelvis en specifik diagnos, där behovet av ett kliniskt beslutsstöd bedömdes högt. (2) Kartlägga vårdkedjan för den identifierade diagnosen. (3) Utveckla hypoteser angående var inom vårdkedjan som  utmaningar skulle kunna lösas med ett kliniskt beslutsstöd. (4) Bekräfta eller förkasta ypoteserna genom intervjuer med relevanta experter. (5) Presentera problemet med det mest trängande behovet efter ett kliniskt beslutsstöd och hur ett sådans skulle utformas. Fynd: Effektivitetsproblemet som kunde lösas bäst via ett kliniskt beslutsstöd identifierades att vara inom området hjärtsviktsbehandling. Det fanns flertalet områden med utvecklingspotential som urskiljdes ur vårdkedjan för hjärtsviktspatienter, och vissa av dessa utmaningar kunde lösas genom utveckling och implementering av specifika kliniska beslutsstöd. Det kliniska beslutsstöd som skulle lösa det mest trängande behovet inom vården idag föreslås vara ett system som hjälper läkare inom vårdcentralerna att identifiera patienter som skulle gagnas av en remiss till en kardiolog. Det föreslagna kliniska beslutsstödet skulle vara både fördelaktigt för vårdpersonal samt patienter samt är realistiskt implementerbart.

No description available.

Background: Patient experience is a crucial measure of patient-centeredness and quality care delivery. Digital health may contribute to patient experience by offering tailored and accessible avenues of care. Purpose: I explored how access to digital health, including telehealth, electronic health records, and online booking, may be associated with improved primary care experience for Ontario adults. Methods: This cross-sectional study included Ontario adults (16 years or older) who responded to waves 27 to 29 of the Health Care Experience Survey (HCES) between May 2019 and February 2020. Adults who did not see their primary care provider within the past 12 months or did not have a primary care provider were excluded. Outcomes included a summed patient experience score derived from five HCES experience-related questions and time to appointment for a health concern. Associations between outcomes and digital health interventions were tested through chi-square tests and logistic regression while adjusting for confounders and stratifying by health care utilization. Results: 3,700 participants met the inclusion criteria, where 2204 remotely communicated with their primary care provider (59.6%), 98 digitally accessed health records (2.6%), and 120 booked an appointment online (3.2%). We observed no significant associations between digital health tools and patient experience or time to appointments through chi-square tests. Participants with over three primary care visits in the past year who accessed online booking were 84% less likely to report poorer experience scores than participants without online booking access [Adjusted OR 0.16, 95% CI 0.02 – 0.56, p < 0.05]. Participants with three or fewer primary care encounters who accessed online booking, compared to the same reference group, were 72% less likely to report having a same or next day appointment with their primary care provider [Adjusted OR 0.25, 95% CI 0.08 – 0.64, p < 0.01]. Significant associations were observed between other sociodemographic factors and patient experience and access to care outcomes. Interpretation: The associations between digital health access and patient experience and access to care were inconsistent across different analyses. Despite experimental studies observing the benefits of digital health adoption in primary care, the effect is unclear in the real-world context. Furthermore, drawing conclusions on the relationship between digital health and quality care outcomes was limited due to the lack of adoption of digital health before the COVID-19 pandemic. As digital health adoption grows, future research should utilize the availability of further data to evaluate the effectiveness of digital health in Ontario primary care. / Thesis / Master of Science (MSc) / Patient outcomes such as experience and timeliness of care are frequently viewed as aims of quality health care. Although past studies indicate digital health supports quality care, the real-world effectiveness of digital health is underexplored in Ontario. This thesis aimed to explore relationships between real-world use of digital health in Ontario and primary care experience and access using survey data. This study found very few survey respondents used digital health before the COVID-19 pandemic. The primary care experience and access to care of adults who did use digital health did not differ very much from adults who did not use the technology. Some outcomes differed in adults who booked their primary care appointment online compared to those who did not; however, the study could not conclude on the relationship. Other personal factors such as age and residence area impacted the quality of primary care. This study was limited due to the lack of digital health users. Future studies should explore digital health's impact on patient outcomes beyond the pandemic.

No description available.

No description available.

No description available.

Electronic health record (EHR) systems are used by medical providers to streamline the workflow and enable sharing of patient data with different providers. Beyond that primary purpose, EHR data have been used in healthcare research for exploratory and predictive analytics. EHR data are heterogeneous collections of both structured and unstructured information. In order to store data in a structured way, several ontologies have been developed to describe diagnoses and treatments. On the other hand, the unstructured clinical notes contain various more nuanced information about patients. The multidimensionality and complexity of EHR data pose many unique challenges and problems for both data mining and medical communities. In this thesis, we address several important issues and develop novel deep learning approaches in order to extract insightful knowledge from these data. Representing words as low dimensional vectors is very useful in many natural language processing tasks. This idea has been extended to medical domain where medical codes listed in medical claims are represented as vectors to facilitate exploratory analysis and predictive modeling. However, depending on a type of a medical provider, medical claims can use medical codes from different ontologies or from a combination of ontologies, which complicates learning of the representations. To be able to properly utilize such multi-source medical claim data, we propose an approach that represents medical codes from different ontologies in the same vector space. The new approach was evaluated on the code cross-reference problem, which aims at identifying similar codes across different ontologies. In our experiments, we show the proposed approach provide superior cross-referencing when compared to several existing approaches. Furthermore, considering EHR data also contain unstructured clinical notes, we also propose a method that jointly learns medical concept and word representations. The jointly learned representations of medical codes and words can be used to extract phenotypes of different diseases. Various deep learning models have recently been applied to predictive modeling of Electronic Health Records (EHR). In EHR data, each patient is represented as a sequence of temporally ordered irregularly sampled visits to health providers, where each visit is recorded as an unordered set of medical codes specifying patient's diagnosis and treatment provided during the visit. We propose a novel interpretable deep learning model, called Timeline. The main novelty of Timeline is that it has a mechanism that learns time decay factors for every medical code. We evaluated Timeline on two large-scale real world data sets. The specific task was to predict what is the primary diagnosis category for the next hospital visit given previous visits. Our results show that Timeline has higher accuracy than the state of the art deep learning models based on RNN. Clinical notes contain detailed information about health status of patients for each of their encounters with a health system. Developing effective models to automatically assign medical codes to clinical notes has been a long-standing active research area. Considering the large amount of online disease knowledge sources, which contain detailed information about signs and symptoms of different diseases, their risk factors, and epidemiology, we consider Wikipedia as an external knowledge source and propose Knowledge Source Integration (KSI), a novel end-to-end code assignment framework, which can integrate external knowledge during training of any baseline deep learning model. To evaluate KSI, we experimented with automatic assignment of ICD-9 diagnosis codes to clinical notes, aided by Wikipedia documents corresponding to the ICD-9 codes. The results show that KSI consistently improves the baseline models and that it is particularly successful in rare codes prediction. / Computer and Information Science

Rates of immune-mediated diseases (IMDs) have rapidly increased. Although the exact etiology has not yet been fully elucidated, disruptions to the microbiome has been proposed as a potential mechanism. We conducted a retrospective, longitudinal, birth cohort study utilizing electronic health records (EHR) to investigate the association between early life antibiotic exposure and the risk of developing juvenile idiopathic arthritis (JIA), pediatric psoriasis, or type 1 diabetes. Incident rate ratios (IRR) were estimated using modified Poisson regression models and adjusted for significant confounders. Children exposed to two or more antibiotics prior to 12 months of age had a 69% increased risk of developing JIA (1.69 IRR, 95% CI [1.04-2.73]), which rose to 97% when exposed prior to 6 months (1.97 IRR, 95% CI [1.11-3.49]). Children exposed to a penicillin antibiotic had a 62% increase in risk for psoriasis (1.62 IRR, 95% CI [1.06-2.49]), which rose slightly to 64% when exposure occurred between 6 and 12 months of age [(1.64 IRR, 95% CI [1.04-2.59]). We found a moderate to strong association between early antibiotic exposure and risk for JIA and psoriasis when exposure was examined by age, frequency, and type of antibiotic, but not for type 1 diabetes. Potential interactions effects between infection and antibiotics with an increased susceptibility to early life infections among children with an IMD was also observed. Overall, children exposed to antibiotics at an early age have an increased probability of developing an IMD after 12 months of age. However, alternative explanations for this association should be considered. / Public Health