INTRODUCTIONSeizure is the most common paediatric neurological disease which occurs in ten percent of children. In approaching a convulsive patient, finding the causes of seizure is essential, and the patient's history as well as the physical examination are important. The role of routine laboratory tests for children's seizures (except neonates) is undetermined, but checking for serum sodium, glucose, calcium and urea routinely has been advised. The purpose of this study was to determine the diagnostic efficacy of these serum chemistry tests in the seizures of children older than one month of age.

METHODSIn this descriptive, retrospective study, medical records of 302 hospitalised children with seizure were reviewed. Results of laboratory tests, like sodium, calcium, blood glucose and urea levels, pertinent history and physical examination, and the change in patient management based on serum chemistry test results, were analysed. All the children in the study were classified as having seizure with or without fever.

RESULTSIn 302 hospitalised children with seizure, about ten percent of 938 tests were abnormal. 27.7 percent of these abnormal results were seen in 1-12-month-old infants. Only 11 percent of abnormal tests (1.3 percent of total tests) might have caused a seizure. Also, 0.2 percent of the results could not be predicted from the history or physical examination, which was conducted in patients younger than one year of age.

CONCLUSIONRoutine determination of serum chemistry values in seizures of children does not contribute to therapy, and are costly and time-consuming. It may not be helpful and informative unless the patient is less than one year of age.

Blood Chemical Analysis ; methods ; Calcium ; blood ; Chemistry, Clinical ; methods ; Child ; Child, Preschool ; Female ; Glucose ; biosynthesis ; Humans ; Infant ; Male ; Retrospective Studies ; Seizures ; blood ; diagnosis ; Sodium ; blood ; Treatment Outcome ; Urea ; blood

OBJECTIVES: Smartphones represent a promising technology for patient-centered healthcare. It is claimed that data mining techniques have improved mobile apps to address patients’ needs at subgroup and individual levels. This study reviewed the current literature regarding data mining applications in patient-centered mobile-based information systems. METHODS: We systematically searched PubMed, Scopus, and Web of Science for original studies reported from 2014 to 2016. After screening 226 records at the title/abstract level, the full texts of 92 relevant papers were retrieved and checked against inclusion criteria. Finally, 30 papers were included in this study and reviewed. RESULTS: Data mining techniques have been reported in development of mobile health apps for three main purposes: data analysis for follow-up and monitoring, early diagnosis and detection for screening purpose, classification/prediction of outcomes, and risk calculation (n = 27); data collection (n = 3); and provision of recommendations (n = 2). The most accurate and frequently applied data mining method was support vector machine; however, decision tree has shown superior performance to enhance mobile apps applied for patients’ self-management. CONCLUSIONS: Embedded data-mining-based feature in mobile apps, such as case detection, prediction/classification, risk estimation, or collection of patient data, particularly during self-management, would save, apply, and analyze patient data during and after care. More intelligent methods, such as artificial neural networks, fuzzy logic, and genetic algorithms, and even the hybrid methods may result in more patients-centered recommendations, providing education, guidance, alerts, and awareness of personalized output.
Artificial Intelligence ; Data Collection ; Data Mining* ; Decision Trees ; Delivery of Health Care ; Early Diagnosis ; Education ; Follow-Up Studies ; Fuzzy Logic ; Humans ; Information Systems* ; Mass Screening ; Methods ; Mobile Applications ; Patient Care ; Self Care ; Smartphone ; Statistics as Topic ; Support Vector Machine ; Telemedicine

Background: Predicting the need for post-traumatic reconstruction of lower extremity injuries remains a challenge. Due to the larger volume of cases in adults than in children, the majority of the medical literature has focused on adult lower extremity reconstruction. This study evaluates predictive risk factors associated with the need for free flap reconstruction in pediatric patients following lower extremity trauma. Methods: An IRB-approved retrospective chart analysis over a 5-year period (January 1, 2012 to December 31, 2017) was performed, including all pediatric patients (<18 years old) diagnosed with one or more lower extremity wounds. Patient demographics, trauma information, and operative information were reviewed. The statistical analysis consisted of univariate and multivariate regression models to identify predictor variables associated with free flap reconstruction. Results: In total, 1,821 patients were identified who fit our search criteria, of whom 41 patients (2.25%) required free flap reconstruction, 65 patients (3.57%) required local flap reconstruction, and 19 patients (1.04%) required skin graft reconstruction. We determined that older age (odds ratio [OR], 1.134; P =0.002), all-terrain vehicle accidents (OR, 6.698; P<0.001), and trauma team activation (OR, 2.443; P=0.034) were associated with the need for free flap reconstruction following lower extremity trauma in our pediatric population. Conclusions Our study demonstrates a higher likelihood of free flap reconstruction in older pediatric patients, those involved in all-terrain vehicle accidents, and cases involving activation of the trauma team. This information can be implemented to help develop an early risk calculator that defines the need for complex lower extremity reconstruction in the pediatric population.