Fuzzy Modeling to Predict Severely Depressed Left Ventricular Ejection Fraction following Admission to the Intensive Care Unit Using Clinical Physiology.

Left ventricular ejection fraction (LVEF) constitutes an important physiological parameter for the assessment of cardiac function, particularly in the settings of coronary artery disease and heart failure. This study explores the use of routinely and easily acquired variables in the intensive care unit (ICU) to predict severely depressed LVEF following ICU admission. A retrospective study was conducted. We extracted clinical physiological variables derived from ICU monitoring and available within the MIMIC II database and developed a fuzzy model using sequential feature selection and compared it with the conventional logistic regression (LR) model. Maximum predictive performance was observed using easily acquired ICU variables within 6 hours after admission and satisfactory predictive performance was achieved using variables acquired as early as one hour after admission. The fuzzy model is able to predict LVEF ≤ 25% with an AUC of 0.71 ± 0.07, outperforming the LR model, with an AUC of 0.67 ± 0.07. To the best of the authors' knowledge, this is the first study predicting severely impaired LVEF using multivariate analysis of routinely collected data in the ICU. We recommend inclusion of these findings into triaged management plans that balance urgency with resources and clinical status, particularly for reducing the time of echocardiographic examination.

Missing data in medical databases: impute, delete or classify?

BACKGROUND: The multiplicity of information sources for data acquisition in modern intensive care units (ICUs) makes the resulting databases particularly susceptible to missing data. Missing data can significantly affect the performance of predictive risk modeling, an important technique for developing medical guidelines. The two most commonly used strategies for managing missing data are to impute or delete values, and the former can cause bias, while the later can cause both bias and loss of statistical power. OBJECTIVES: In this paper we present a new approach for managing missing data in ICU databases in order to improve overall modeling performance. METHODS: We use a statistical classifier followed by fuzzy modeling to more accurately determine which missing data should be imputed and which should not. We firstly develop a simulation test bed to evaluate performance, and then translate that knowledge using exactly the same database as previously published work by [13]. RESULTS: In this work, test beds resulted in datasets with missing data ranging 10-50%. Using this new approach to missing data we are able to significantly improve modeling performance parameters such as accuracy of classifications by an 11%, sensitivity by 13%, and specificity by 10%, including also area under the receiver-operator curve (AUC) improvement of up to 13%. CONCLUSIONS: In this work, we improve modeling performance in a simulated test bed, and then confirm improved performance replicating previously published work by using the proposed approach for missing data classification. We offer this new method to other researchers who wish to improve predictive risk modeling performance in the ICU through advanced missing data management.

Online access and literacy in Maori New Zealanders with diabetes.

INTRODUCTION: Online web-based interventions can be effective ancillary tools for managing diabetes. There is a high prevalence of diabetes in New Zealand Maori, and yet this group has generally been a low priority for web-based interventions due to perceptions of low Internet access and Internet literacy. AIM: To assess Internet access and literacy in New Zealanders with diabetes, especially high-risk Maori. METHODS: A telephone survey of all patients with diabetes in an urban general practice. Internet access is assessed by Internet presence in the home, and Internet literacy by the ability to use email and the World Wide Web. RESULTS: One hundred percent response rate with 68 participants, including 38% Maori. Internet access for Maori was 70% and Internet literacy 41%. DISCUSSION: Internet access and literacy for Maori with diabetes may be higher than previously thought. Health policies may wish to focus effective and cost-efficient web-based interventions on this high diabetes risk group.

Improving personal health records for patient-centered care.

OBJECTIVE: To assess the patient-centeredness of personal health records (PHR) and offer recommendations for best practice guidelines. DESIGN: Semi-structured interviews were conducted in seven large early PHR adopter organizations in 2007. Organizations were purposively selected to represent a variety of US settings, including medium and large hospitals, ambulatory care facilities, insurers and health plans, government departments, and commercial sectors. MEASUREMENTS: Patient-centeredness was assessed against a framework of care that includes: (1) respect for patient values, preferences, and expressed needs; (2) information and education; (3) access to care; (4) emotional support to relieve fear and anxiety; (5) involvement of family and friends; (6) continuity and secure transition between healthcare providers; (7) physical comfort; (8) coordination of care. Within this framework we used evidence for patient preferences (where it exists) to compare existing PHR policies, and propose a best practice model. RESULTS: Most organizations enable many patient-centered functions such as data access for proxies and minors. No organization allows patient views of clinical progress notes, and turnaround times for PHR reporting of normal laboratory results can be up to 7 days. CONCLUSION: Findings suggest patient-centeredness for personal health records can be improved, and recommendations are made for best practice guidelines.

Governance for personal health records.

Personal health records (PHR) are a modern health technology with the ability to engage patients more fully in their healthcare. Despite widespread interest, there has been little discussion around PHR governance at an organizational level. We develop a governance model and compare it to the practices of some of the early PHR adopters, including hospitals and ambulatory care settings, insurers and health plans, government departments, and commercial sectors. Decision-making structures varied between organizations. Business operations were present in all groups, but patients were not represented in any of the governance structures surveyed. To improve patient-centered care, policy making for PHRs needs to include patient representation at a governance level.