J Med Syst
-
Early and accurate diagnosis of Parkinson's disease (PD) remains challenging. Neuropathological studies using brain bank specimens have estimated that a large percentages of clinical diagnoses of PD may be incorrect especially in the early stages. In this paper, a comprehensive computer model is presented for the diagnosis of PD based on motor, non-motor, and neuroimaging features using the recently-developed enhanced probabilistic neural network (EPNN). ⋯ The results are compared to four other commonly-used machine learning algorithms: the probabilistic neural network (PNN), support vector machine (SVM), k-nearest neighbors (k-NN) algorithm, and classification tree (CT). The EPNN had the highest classification accuracy at 92.5% followed by the PNN (91.6%), k-NN (90.8%) and CT (90.2%). The EPNN exhibited an accuracy of 98.6% when classifying healthy control (HC) versus PD, higher than any previous studies.
-
Review Meta Analysis
Compliance of blood donation apps with mobile OS usability guidelines.
The aim of this paper is to employ the guidelines of Android, iOS, Blackberry and Windows Phone to analyze the usability compliance of free blood donation (BD) apps. An analysis process based on a systematic review protocol is used to select free BD apps. An assessment is conducted using a questionnaire composed of 13 questions concerning the compliance of free BD apps with Android, Blackberry, iOS and Windows Phone usability guidelines. ⋯ Structure patterns should also be used to improve the structure aspect of a BD app. Usability is a quality aspect that should be improved in current BD apps. Our study provides smartphone users with a list of usable free BD apps and BD app developers with recommendations.
-
Hand hygiene compliance is the most significant, modifiable cause of hospital-acquired infections, yet national averages for compliance rates remain unsatisfactory. Noncompliance can contribute to patient mortality, extended hospital stays, higher re-admission rates, and lower reimbursement for hospitals under the Patient Protection and Affordable Care Act. Although several hand sanitizing tracking systems currently exist, they pose problems of personal tracking, workflow interference, system maintenance concerns, among others. Considering these barriers, we created a prototype system that includes compliance rate tracking, real-time sanitization reminders, and a data archive for future studies.
-
There is a growing emphasis on both cost containment and better quality health care. The creation of better methods for alerting providers and their departments to the costs associated with patient care is one tool for improving efficiency. Since anesthetic medications used in the OR setting are one easily monitored factor contributing to OR costs, anesthetic cost report cards can be used to assess the cost and, potentially the quality of care provided by each practitioner. ⋯ Also included can be subcategories of pre-medication, antibiotics, hypnotics, local anesthetics, neuromuscular blocking drugs, analgesics, vasopressors, beta-blockers, anti-emetics, volatile anesthetics, and reversal agents. The concept of anesthetic cost report card should be further developed for individual feedback, and could include many other dimensions. Such a report card can be utilized to encourage lower anesthetic costs, quality improvement among anesthesia providers, and for cost containment in the operating room.
-
Previous studies have identified some clinical parameters for predicting long-term functional recovery and mortality after traumatic brain injury (TBI). Here, data mining methods were combined with serial Glasgow Coma Scale (GCS) scores and clinical and laboratory parameters to predict 6-month functional outcome and mortality in patients with TBI. Data of consecutive adult patients presenting at a trauma center with moderate-to-severe head injury were retrospectively analyzed. ⋯ The best predictive model for mortality was NB with AUC of 91.14%, sensitivity of 81.17%, and specificity of 90.65%. Sensitivity analysis demonstrated GCS measurements on the 7th and 14th day and difference between emergency room and 14th day GCS score as the most influential attributes both in mortality and functional outcome prediction models. Analysis of serial GCS measurements using data mining methods provided additional predictive information in relation to 6-month mortality and functional outcome in patients with moderate-to-severe TBI.