Health Information Technology Systems Research Articles

The impact of health information technology on the management and follow-up of test results - a systematic review.

ObjectiveTo investigate the impact of health information technology (IT) systems on clinicians’ work practices and patient engagement in the management and follow-up of test results.Materials and MethodsA search for studies reporting health IT systems and clinician test results management was conducted in the following databases: MEDLINE, EMBASE, CINAHL, Web of Science, ScienceDirect, ProQuest, and Scopus from January 1999 to June 2018. Test results follow-up was defined as provider follow-up of results for tests that were sent to the laboratory and radiology services for processing or analysis.ResultsThere are some findings from controlled studies showing that health IT can improve the proportion of tests followed-up (15 percentage point change) and increase physician awareness of test results that require action (24–28 percentage point change). Taken as whole, however, the evidence of the impact of health IT on test result management and follow-up is not strong.DiscussionThe development of safe and effective test results management IT systems should pivot on several axes. These axes include 1) patient-centerd engagement (involving shared, timely, and meaningful information); 2) diagnostic processes (that involve the integration of multiple people and different clinical settings across the health care spectrum); and 3) organizational communications (the myriad of multi- transactional processes requiring feedback, iteration, and confirmation) that contribute to the patient care process.ConclusionExisting evidence indicates that health IT in and of itself does not (and most likely cannot) provide a complete solution to issues related to test results management and follow-up.

Patient-centered care via health information technology: a qualitative study with experts from Israel and the U.S.

ABSTRACT Although patient-centered care (PCC) is one of the cornerstones of modern healthcare, the role that health information technology (HIT) plays in supporting PCC remains unclear. In this qualitative study, we interviewed academic and clinical experts from the US and Israel to understand to what extent current HIT systems are supportive of PCC and how PCC should be supported by HIT in the future. A maximum variation sampling approach was used to identify nine experts in both HIT and PCC from clinical and academic settings in Israel and the US. A qualitative descriptive method was used to analyze the interviews and identify major themes. Experts suggested that patient ownership of their disease is a core component of PCC. The majority of the experts agreed that in both Israel and the US, the current situation of PCC implementation is relatively poor. However, HIT should play an important role in making patients owners of their health and treatment and helping providers in delivering better PCC. Central domains of PCC via HIT were providing clear information and support for patients and promoting care that is based on patient values and preferences.

An mHealth pilot designed to increase the reach of prevention of mother-to-child transmission of HIV (PMTCT) across the treatment cascade in a resource-constrained setting in Tanzania.

BackgroundData collection and integrated reporting between the multiple health facilities for supporting more efficient care linkages is an indispensable element for prevention of mother-to-child transmission of HIV (PMTCT) by fostering continuity of patient care and improving the treatment cascade for HIV-infected pregnant women. mHealth potentially presents timely solutions to the data challenges related to efficient and effective care delivery in resource-constrained settings, particularly in low- and middle-income countries.MethodsThis randomized controlled pilot study used stratified random sampling for the selection of seven intervention and seven control sites in Misungwi, Tanzania, a rural district in the northwestern region. Twenty-eight health workers at seven intervention health facilities used the Tanzania Health Information Technology (T-HIT) system during a 3-month period from February 23, 2015, through May 23, 2015, to capture antenatal, delivery, and postnatal patient visits.ResultsT-HIT was designed for use on tablets with the goal to improve reporting, surveillance and monitoring of HIV rates and care delivery in the remote and rural settings. Health workers successfully recorded 2,453 visits. Of these, 1,594 were antenatal visits, 484 deliveries were recorded, and 375 were postnatal visits. Within the antenatal visits, 96% of women had a single visit (1474). Healthcare workers were unable to test 6.7% of women antenatally for HIV.ConclusionThe T-HIT pilot demonstrated the feasibility for implementing an mHealth integrated solution in a rural, low-resource setting that links tablet-based surveillance, health worker capacity-building and patient reminders into a single robust and responsive system. Although the implementation phase was only three months, the pilot generated evidence that T-HIT has potential for improving patient outcomes by providing more comprehensive, linked, and timely PMTCT care data at the individual and clinic levels.

Beyond One-Off Integrations: A Commercial, Substitutable, Reusable, Standards-Based, Electronic Health Record-Connected App.

The Substitutable Medical Apps and Reusable Technology (SMART) Health IT project launched in 2010 to facilitate the development of medical apps that are scalable and substitutable. SMART defines an open application programming interface (API) specification that enables apps to connect to electronic health record systems and data warehouses without custom integration efforts. The SMART-enabled version of the Meducation app, developed by Polyglot, has been implemented at scores of hospitals and clinics in the United States, nation-wide. After expanding their product’s reach by relying on a universal, open API for integrations, the team estimates that one project manager can handle up to 20 simultaneous implementations. The app is made available through the SMART App Gallery, an open app store that supports discovery of apps and, because the apps are substitutable, market competition. This case illustrates how a universal open API for patient and clinician-facing health IT systems supported and accelerated commercial success for a start-up company. Giving end users a wide and ever-growing choice of apps that leverage data generated by the health care system and patients at home through a universal, open API is a promising and generalizable approach for rapid diffusion of innovation across health systems.

Bringing big data analytics closer to practice: A methodological explanation and demonstration of classification algorithms

BackgroundBig data analytics are becoming more prevalent due to the recent availability of health data. Yet in spite of evidence supporting the potential contribution of big data analytics to health policy makers and care providers, these tools are still too complex to be routinely used. Further, access to comprehensive datasets required for more accurate results is complex and costly. Consequently, big data analytics are mostly used by researchers and experts who are far removed from actual clinical practice. Hence, policy makers should allocate resources to encourage studies that clarify and simplify big data analytics so it can be used by non-experts (e.g., clinicians, practitioners and decision-makers who may not have advanced computer skills). It is also important to fund data collection and integration from various health IT, a pre-condition for any big data analytics project. ObjectivesTo methodologically clarify the rationale and logic behind several analytics algorithms to help non-expert users employ big data analytics by understanding how to implement relatively easy to use platforms as Azure ML. MethodsWe demonstrate the predictive power of four known algorithms and compare their accuracy in predicting early mortality of Congestive Heart Failure (CHF) patients. ResultsThe results of our models outperform those reported in the literature, attesting to the strength of some of the models, and the utility of comprehensive data. ConclusionsThe results support our call to policy makers to allocate resources to establishing comprehensive, integrated health IT systems, and to projects aimed at simplifying ML analytics.

A Framework for Contracted Health IT Performance Assessments

Limited research exists which aids in structuring health IT contracts in an era of performance-based payments. We provide an assessment of common approaches to contracting and measuring of performance in practice. We conducted a review of existing literature and compliment this approach with a survey of healthcare professionals directly involved with health IT systems to further understand and classify current approaches. We identified architypes for structuring healthcare IT performance contracts to include: (1) internal operations, (2) external evaluation and (3) joint agreement for the delivery of value-based care.

Prevalence and outcomes of atrial fibrillation in a European healthcare area gained through the processing of a health information technology system

IntroductionToday's healthcare policies rely heavily on data that has been gathered from multiple small studies in intrinsically varied populations. We sought to describe the prevalence, comorbidities and outcomes of atrial fibrillation (AF) in the population of a specific region where all healthcare centers have implemented a common information technology (IT) structure. MethodsThe total number of inhabitants was obtained from the healthcare area's IT system. Information pertaining to AF was derived from various datasets in the data warehouse of the Galician regional health service. ResultsIn the healthcare area of Santiago de Compostela (n=383000), the diagnosis of AF was coded in 7990 (2.08%) individuals in 2013. Mean age was 76.83±10.5 years, mean CHA2DS2-VASc score was 3.5, 4056 (50.8%) were female and 72.6% were receiving oral anticoagulants. Up until December 31, 2015, 1361 patients died from all causes (17%), 478 (6%) of them in-hospital, with 30 deaths secondary to intracranial bleeding (0.4%) and 125 to stroke (1.6%). On multivariate analysis, age, gender, heart failure, diabetes, previous thromboembolic events and dementia were independently associated with all-cause mortality. Similarly, age, gender and previous thromboembolic events were associated with future thromboembolic events. Oral anticoagulation was found to be protective against mortality and thromboembolic events. ConclusionsIn this study, we report for the first time the true prevalence of diagnosed AF and its clinical characteristics, treatment and prognosis in a Spanish healthcare area, based on the systematic integration of data available from a universally adopted health IT system within the region.

Iranian Health Information Technology Acceptance Model (IHITAM) from Users' Views.

Introduction:Information technology (IT) is an important component of medical informatics. Information needs to be accepted by users to function effectively. At different ages and from different views, several models have been proposed and used to show factors affecting users’ IT acceptance. However, such models are in need of frequent revision and development due to variable conditions.Aim:The present research aims to design a new health IT acceptance model from Iranian users’ views. The research aims both to design a model for status quo by reviewing previous models and consider features of Iranian users.Methods:This is a correlative, cross-sectional study. Firstly, the primary model was presented by studying important IT acceptance models. Then, a structured questionnaire was designed and, after confirmation of validity and reliability of the questionnaire, it was given to users of information and health IT systems in different wards of hospitals in Iran. Data were analyzed by SPSS and Lisrel and the final model was designed by structural equations.Results:The model showed that there are six key factors which are effective on attitude and use intention including performance expectancy, observability, effort expectancy, facilitating conditions, empowerment and subjective norms via three interface factors of perceived usefulness, perceived ease of use, self-efficacy. The size of technology use is an important factor in technology acceptance and application as well.Conclusion:The present model has more details compared to the other models and can show a new image of important factors in technology acceptance and their relationships.

Prevalence and outcomes of atrial fibrillation in a European healthcare area gained through the processing of a health information technology system

Today's healthcare policies rely heavily on data that has been gathered from multiple small studies in intrinsically varied populations. We sought to describe the prevalence, comorbidities and outcomes of atrial fibrillation (AF) in the population of a specific region where all healthcare centers have implemented a common information technology (IT) structure. The total number of inhabitants was obtained from the healthcare area's IT system. Information pertaining to AF was derived from various datasets in the data warehouse of the Galician regional health service. In the healthcare area of Santiago de Compostela (n=383 000), the diagnosis of AF was coded in 7990 (2.08%) individuals in 2013. Mean age was 76.83±10.5 years, mean CHA2DS2-VASc score was 3.5, 4056 (50.8%) were female and 72.6% were receiving oral anticoagulants. Up until December 31, 2015, 1361 patients died from all causes (17%), 478 (6%) of them in-hospital, with 30 deaths secondary to intracranial bleeding (0.4%) and 125 to stroke (1.6%). On multivariate analysis, age, gender, heart failure, diabetes, previous thromboembolic events and dementia were independently associated with all-cause mortality. Similarly, age, gender and previous thromboembolic events were associated with future thromboembolic events. Oral anticoagulation was found to be protective against mortality and thromboembolic events. In this study, we report for the first time the true prevalence of diagnosed AF and its clinical characteristics, treatment and prognosis in a Spanish healthcare area, based on the systematic integration of data available from a universally adopted health IT system within the region. As políticas dos cuidados de saúde confiam essencialmente em dados provenientes de múltiplos pequenos estudos no âmbito de populações diversificadas. Desejamos descrever a prevalência, as comorbilidades e os resultados da fibrilhação auricular (FA) numa população pertencente a uma área específica onde os centros dos cuidados de saúde implementaram uma estrutura informática comum. O número total de habitantes foi obtido através do sistema informático das áreas dos cuidados de saúde. A informação relativa à FA provém de diversos conjuntos de dados proveniente do banco de dados do Serviço Saúde da Galiza. Na área dos cuidados de saúde de Santiago de Compostela (n = 348 985), ao longo de 2013, o diagnóstico de FA foi codificado em 7990 (2,08%) indivíduos. A idade média foi 76,83 ± 10,5 anos, valor médio CHA2DS2-VASc = 3,5, sendo 4056 (50,8%) mulheres, 72,6% das quais administradas com anticoagulantes orais. Até 31 de dezembro de 2015, 1361 doentes morreram de mortalidade geral (17%). Destes, 478 (6%) estavam internados, tendo sido registadas 30 mortes secundárias a hemorragia intracraneana (0,4%) e 125 acidentes vasculares cerebrais (1,6%). Numa análise multivariável, a idade, o sexo, a insuficiência cardíaca, a diabetes, os eventos tromboembólicos e a demência foram associados independentemente da mortalidade em geral. Do mesmo modo, a idade, o sexo e o(s) tromboembólico(s) prévio(s) foram associados à ocorrência de futuros eventos tromboembólicos. Considerou-se que a anticoagulação oral teve um efeito protetor na mortalidade e nos eventos tromboembólicos. Neste estudo, apresentamos pela primeira vez a prevalência real da FA diagnosticada, com as características clínicas, tratamento e prognóstico de uma área específica de cuidados de saúde em Espanha, em conformidade com a integração sistemática dos dados disponíveis num processamento informático sanitário adotado na região.

Research IT maturity models for academic health centers: Early development and initial evaluation.

This paper proposes the creation and application of maturity models to guide institutional strategic investment in research informatics and information technology (research IT) and to provide the ability to measure readiness for clinical and research infrastructure as well as sustainability of expertise. Conducting effective and efficient research in health science increasingly relies upon robust research IT systems and capabilities. Academic health centers are increasing investments in health IT systems to address operational pressures, including rapidly growing data, technological advances, and increasing security and regulatory challenges associated with data access requirements. Current approaches for planning and investment in research IT infrastructure vary across institutions and lack comparable guidance for evaluating investments, resulting in inconsistent approaches to research IT implementation across peer academic health centers as well as uncertainty in linking research IT investments to institutional goals. Maturity models address these issues through coupling the assessment of current organizational state with readiness for deployment of potential research IT investment, which can inform leadership strategy. Pilot work in maturity model development has ranged from using them as a catalyst for engaging medical school IT leaders in planning at a single institution to developing initial maturity indices that have been applied and refined across peer medical schools.

Using Scenarios Throughout The User-Centered Design Process in Healthcare

Context-specific descriptions of the intended user interactions with health information technology (HIT) systems provide an important perspective to the overall goals of HIT design. These descriptions — or scenarios — that represent the clinicians’ perspectives can describe how HIT should support users in providing patient care effectively, efficiently, and safely. Scenarios may improve the design of HIT systems by ensuring clinician needs are well-articulated for high-value patient-care situations. This Practice- Oriented paper presents suggestions for the development and application of clinical scenarios throughout a robust user-centered design (UCD) process. As a flexible artifact, different types of scenarios can be used at each point across the UCD process and the rationale for their use are discussed, and we suggest key aspects that must be included for each specific type of scenario. This practice innovation will be beneficial to practitioners working within UCD processes, as guidance on adding scenarios as a tool in their work.

Identifying Improvements in Healthcare Systems Engineering Models for Chronic Care and Precision Medicine Applications

Over 48 million Americans are currently living with a chronic disease. To effectively manage chronic diseases, there is a need for interventions at multiple points in the care process, with integrated health information technology (HIT) systems to assist with information coordination for patients, caregivers, and providers. Systems engineering models can be useful for minimizing unintended consequences with HIT implementation; however, there are gaps in applying such models to precision medicine and chronic care management. The objective of this work was to review the key attributes of systems engineering models for chronic disease management and precision medicine applications. Several key attributes were selected to address: granularity, temporal dynamics, sociotechnical factors, chronic care applications, and HIT integration. The analysis found that the most difficult challenge is depicting granularity and temporal dynamics in systems engineering implementations so that they can still be easily applied by practitioners. Future work aims to determine appropriate systems engineering interventions and implementations that integrate information architecture, systems granularity, and event dynamics for longitudinal coordinated care activities.

Revising IEC 80001-1: Risk management of health information technology systems

IEC 80001-1 was published in 2010 and is now undergoing revision. Feedback gathered on the adoption of the standard has revealed a number of barriers that have impacted its adoption. The standard provides requirements related to the roles, responsibilities and activities that need to be performed for the risk management of medical IT networks. One reported barrier is a lack of drivers to motivate Top Management to implement the standard. In addition, there is a lack of alignment between IT and biomedical engineering departments within hospitals. Finally, the IEC 80001-1 standard was considered to be too complicated and complex to implement. This paper presents the barriers identified in the feedback and presents an approach to the revision of the standard as a process based standard following the structure outlined in ISO/IEC Directives Annex SL and aligned risk management standards as a means to overcome these barriers.

How Does Electronic Health Information Exchange Affect Hospital Performance Efficiency? The Effects of Breadth and Depth of Information Sharing.

This research was motivated by the large investment in health information technology (IT) by hospitals and the inconsistent findings related to the effects of health IT adoption on hospital performance. Building on resource orchestration theory and the information systems literature, the authors developed a research model to investigate how the configuration strategies for sharing information under health IT systems affect hospital efficiency. The hypotheses were tested using data from the 2010 annual and IT surveys of the American Hospital Association, Centers for Medicare & Medicaid Services case mix index, and U.S. Census Bureau's small-area income and poverty estimates. The study revealed that in health IT systems, the breadth (extent) and depth (level of detail) of digital information sharing among stakeholders each has a curvilinear relationship with hospital efficiency. In addition, breadth and depth reinforce each other's positive effects and attenuate each other's negative effects, and their balance has a positive effect on hospital efficiency. The results of this research have the potential to enrich the literature on the value of adopting health IT systems as well as in providing practitioner guidelines for meaningful use.

A mobile health model supporting Ethiopia's eHealth strategy.

A mobile health model supporting Ethiopia's eHealth strategy.

The Impact of a Health Information Technology-Focused Patient-centered Medical Neighborhood Program Among Medicare Beneficiaries in Primary Care Practices: The Effect on Patient Outcomes and Spending.

The Center for Medicare & Medicaid Innovation (CMMI) tests new models of paying for or delivering health care services and expands models that improve health outcomes while lowering medical spending. CMMI gave TransforMED, a national learning and dissemination contractor, a 3-year Health Care Innovation Award (HCIA) to integrate health information technology systems into physician practices. This paper estimates impacts of TransforMED's HCIA-funded program on patient outcomes and Medicare parts A and B spending. We compared outcomes for Medicare fee-for-service (FFS) beneficiaries served by 87 treatment practices to outcomes for Medicare FFS beneficiaries served by 286 matched comparison practices, adjusting for differences in outcomes between the 2 groups during a 1-year baseline period. We estimated impacts in 3 evaluation outcome domains: quality-of-care processes, service use, and spending. We estimated the program led to a 7.1% reduction in inpatient admissions and a 5.7% decrease in the outpatient emergency department visits. However, there was no evidence of statistically significant effects in outcomes in either the quality-of-care processes or spending domains. These results indicate that TransforMED's program reduced service use for Medicare FFS beneficiaries, but also show that the program did not have statistically significant favorable impacts in the quality-of-care processes or spending domains. These results suggest that providing practices with population health management and cost-reporting software-along with technical assistance for how to use them-can complement practices' own patient-centered medical home transformation efforts and add meaningfully to their impacts on service use.

Circling the Dragon-Taming Health IT Systems to Measure What Matters (TH367)

•Identify the challenges hospice and palliative care programs face when trying to use electronic health records and other IT systems to improve quality and meet requirements of quality payment programs.•Describe the mission and evolution of the AAHPM/HPNA Measuring What Matters Electronic Clinical Quality Measures (eCQMs) Working Group.•Describe the eCQM Group's progress to date on developing specifications for Measuring What Matters measures as electronic Clinical Quality Measures that can be integrated into electronic health records and clinical data registries and outline the work group's future priorities. In this team presentation, leaders from AAHPM and HPNA will showcase the work of the Measuring What Matters Electronic Clinical Quality Measures (eCQMs) Working Group. They will identify the challenges hospice and palliative care programs face when trying to use electronic health records (EHRs) and other IT systems to measure and improve quality. They will discuss how electronic systems have helped or presented challenges in meeting requirements of quality payment programs and describe how the eCQM Group is tackling them. In particular, presenters will explain why electronic clinical quality measures are necessary for interoperability and integration into a myriad of electronic health records and clinical data registries. Discussion may focus on what a data sheet looks like, how to engage with an EHR vendor, etc. They will highlight the committee's work to date to harness IT systems to measure what matters to patients and families living with serious illness. They will also outline the work group's future priorities and provide ample time for audience questions and comments.

Tanzania Health Information Technology (T-HIT) System: Pilot Test of a Tablet-Based System to Improve Prevention of Mother-to-Child Transmission of HIV.

BackgroundThe prevention of mother-to-child transmission (PMTCT) of HIV requires innovative solutions. Although routine monitoring is effective in some areas, standardized and easy-to-scale solutions to identify and monitor pregnant women, test them for HIV, and treat them and their children is still lacking. Mobile health (mHealth) offers opportunities for surveillance and reporting in rural areas of low- and middle-income countries.ObjectiveThe aim of this study was to document the preliminary impacts of the Tanzania Health Information Technology (T-HIT) system mHealth intervention aimed at health workers for PMTCT care delivery and capacity building in a rural area of Tanzania.MethodsWe developed T-HIT as a tablet-based system for an electronic data collection system designed to capture and report PMTCT data during antenatal, delivery, and postnatal visits in Misungwi, Tanzania. T-HIT was tested by health workers in a pilot randomized trial comparing seven sites using T-HIT assigned at random to seven control sites; all sites maintained standard paper record-keeping during the pilot intervention period. We compared numbers of antenatal visits, number of HIV tests administered, and women testing positive across all sites.ResultsHealth workers recorded data from antenatal visits for 1530 women; of these, 695 (45.42%) were tested for HIV and 3.59% (55/1530) tested positive. Health workers were unable to conduct an HIV test for 103 women (6.73%, 103/1530) because of lack of reagent, which is not captured on paper logs. There was no difference in the activity level for testing when comparing sites T-HIT to non-T-HIT sites. We observed a significant postintervention increase in the numbers of women testing positive for HIV compared with the preintervention period (P=.04), but this was likely not attributable to the T-HIT system.ConclusionsT-HIT had a high degree of acceptability and feasibility and is perceived as useful by health workers, who documented more antenatal visits during the pilot intervention compared with a traditional system of paper logs, suggesting potential for improvements in antenatal care for women at risk for HIV.

Customer Discovery as the First Essential Step for Successful Health Information Technology System Development.

ObjectivesCustomer discovery (CD) is a method to determine if there are actual customers for a product/service and what they would want before actually developing the product/service. This concept, however, is rather new to health information technology (IT) systems. Therefore, the aim of this paper was to demonstrate how to use the CD method in developing a comprehensive health IT service for patients with knee/leg pain.MethodsWe participated in a 6-week I-Corps program to perform CD, in which we interviewed 55 people in person, by phone, or by video conference within 6 weeks: 4 weeks in the United States and 2 weeks in Korea. The interviewees included orthopedic doctors, physical therapists, physical trainers, physicians, researchers, pharmacists, vendors, and patients. By analyzing the interview data, the aim was to revise our business model accordingly.ResultsUsing the CD approach enabled us to understand the customer segments and identify value propositions. We concluded that a facilitating tele-rehabilitation system is needed the most and that the most suitable customer segment is early stage arthritis patients. We identified a new design concept for the customer segment. Furthermore, CD is required to identify value propositions in detail.ConclusionsCD is crucial to determine a more desirable direction in developing health IT systems, and it can be a powerful tool to increase the potential for successful commercialization in the health IT field.

Improvements in Diabetic Patients’ Outcomes in a Clinical Decision Support System

Background: There is considerable interest worldwide in prevention and control of diabetes using health information technology systems. Although previous studies have acknowledged improvements of blood pressure control in a clinical decision support system (CDSS), little is known about whether it could contribute to diabetic patients‘ outcomes. Objectives: To compare diabetic patients‘ outcomes six months before and after the introduction of a CDSS. Methods: We considered patients with diabetes in a general hospital and ten clinics that embedded a CDSS within an electronic health record in April 2011, and tracked their medical records from October 2010 to March 2012 (split at April 2011; pre- and post-period). The CDSS mainly had two main functions: (1) to visually highlight abnormal laboratory values on longitudinal inspection data; and (2) to provide a list of patients with severe diabetes. Primary outcome measures included glycated hemoglobin (HbA1c), fasting blood glucose, low-density lipoprotein cholesterol (LDL-C), and glomerular filtration rate (eGFR). The values were averaged for each patient and compared between preand post-period using the Wilcoxon signed-rank test. Results: A total number of 3,678 blood test results from 705 patients were analyzed. The mean HbA1c levels (and standard deviation) among severe cases (baseline HbA1c ≥ 8.4%) were significantly improved over the study period, from 9.49 ± 1.13% to 8.73 ± 1.23% (p < 0.001). In contrast, the moderate group (baseline HbA1c < 8.4%) deteriorated, from 7.61 ± 0.40% to 7.70 ± 0.65%. In terms of fasting blood glucose levels, the severe group (baseline fasting blood glucose level ≥ 160 mg/dl) improved significantly (p < 0.001). On the contrary, the moderate group (baseline fasting blood glucose level < 160 mg/dl) deteriorated significantly (p < 0.001). The patients’ outcomes were improved with the CDSS. Conclusion: Improvements of patients‘ outcomes were observed, indicating the potential effectiveness of the CDSS. Visually emphasizing abnormal laboratory values and displaying severe patients may be effective for disease control of diabetes patients.