A Clinical Decision Support System for Diabetes Patients with Deep Learning: Experience of a Taiwan Medical Center.

Background: Diabetes mellitus (DM) is a major public health problem worldwide. It involves dysfunction of blood sugar regulation resulting from insulin resistance, inadequate insulin secretion, or excessive glucagon secretion. Methods: This study collated 971,401 drug usage records of 51,009 DM patients. These data include patient identification code, age, gender, outpatient visiting dates, visiting code, medication features (included items, doses, and frequencies of drugs), HbA1c results, and testing time. We apply a random forest (RF) model for feature selection and implement a regression model with the bidirectional long short-term memory (Bi-LSTM) deep learning architecture. Finally, we use the root mean square error (RMSE) as the evaluation index for the prediction model. Results: After data cleaning, the data included 8,729 male and 9,115 female cases. Metformin was the most important feature suggested by the RF model, followed by glimepiride, acarbose, pioglitazone, glibenclamide, gliclazide, repaglinide, nateglinide, sitagliptin, and vildagliptin. The model performed better with the past two seasons in the training data than with additional seasons. Further, the Bi-LSTM architecture model performed better than support vector machines (SVMs). Discussion & Conclusion: This study found that Bi-LSTM models is a well kernel in a CDSS which help physicians' decision-making, and the increasing the number of seasons will negative impact the performance. In addition, this study found that the most important drug is metformin, which is recommended as first-line treatment OHA in various situations for DM patients.

Diseases That Occur Prior to Spontaneous Intracerebral Hemorrhage: Identification of Predisposing and Risk Factors Using Lag Sequential Analysis.

Spontaneous intracerebral hemorrhage (sICH) has many predisposing/risk factors. Lag sequential analysis (LSA) is a method of analyzing sequential patterns and their associations within categorical data in different system states. The results of this study will assist in preventing sICH and improving the patient outcome after sICH. The correlations between a first sICH and previous clinic visits were examined using LSA with data obtained from the Taiwan National Health Insurance Research Database (NHIRD). In this study, LSA was employed to examine the data in the Taiwan NHIRD in order to identify predisposing and risk factors related to sICH, and the results increased our knowledge of the temporal relationships between diseases. This study employed LSA to identify predisposing/risk factors prior to the first occurrence of sICH using a healthcare administrative database in Taiwan. The data were managed using the clinical classification software (CCS). All cases of traumatic ICH were excluded. Ten disease groups were identified using CCS. Hypertension and dizziness/vertigo were identified as two important predisposing/risk factors for sICH, and early treatment of hypertension resulted in a greater survival rate. Five disease groups were found to have occurred prior to other diseases and affected mostly the elderly, resulting in subsequent sICH. The results of this study also showed that nutritional status and tooth health were highly associated with the occurrence of sICH owing to a poor state of the digestive system. In conclusion, there are many diseases that influence the risk of a subsequent sICH. This study demonstrated that LSA is a very useful tool for future study of healthcare administrative databases.

Rethinking preparedness planning in disaster emergency care: lessons from a beyond-surge-capacity event.

BACKGROUND: Large-scale burn disasters can produce casualties that threaten medical care systems. This study proposes a new approach for developing hospital readiness and preparedness plan for these challenging beyond-surge-capacity events. METHODS: The Formosa Fun Coast Dust Explosion (FFCDE) was studied. Data collection consisted of in-depth interviews with clinicians from four initial receiving hospitals and their relevant hospital records. A detailed timeline of patient flow and emergency department (ED) workload changes of individual hospitals were examined to build the EDs' overload patterns. Data analysis of the multiple hospitals' responses involved chronological process-tracing analysis, synthesis, and comparison analysis in developing an integrated adaptations framework. RESULTS: A four-level ED overload pattern was constructed. It provided a synthesis of specifics on patient load changes and the process by which hospitals' surge capacity was overwhelmed over time. Correspondingly, an integrated 19 adaptations framework presenting holistic interrelations between adaptations was developed. Hospitals can utilize the overload patterns and overload metrics to design new scenarios with diverse demands for surge capacity. The framework can serve as an auxiliary tool for directive planning and cross-check to address the insufficiencies of preparedness plans. CONCLUSIONS: The study examined a wide-range spectrum of emergency care responses to the FFCDE. It indicated that solely depending on policies or guidelines for preparedness plans did not contribute real readiness to MCIs. Hospitals can use the study's findings and proposal to rethink preparedness planning for the future beyond surge capacity events.

A drug identification model developed using deep learning technologies: experience of a medical center in Taiwan.

BACKGROUND: Issuing of correct prescriptions is a foundation of patient safety. Medication errors represent one of the most important problems in health care, with 'look-alike and sound-alike' (LASA) being the lead error. Existing solutions to prevent LASA still have their limitations. Deep learning techniques have revolutionized identification classifiers in many fields. In search of better image-based solutions for blister package identification problem, this study using a baseline deep learning drug identification (DLDI) aims to understand how identification confusion of look-alike images by human occurs through the cognitive counterpart of deep learning solutions and thereof to suggest further solutions to approach them. METHODS: We collected images of 250 types of blister-packaged drug from the Out-Patient Department (OPD) of a medical center for identification. The deep learning framework of You Only Look Once (YOLO) was adopted for implementation of the proposed deep learning. The commonly-used F1 score, defined by precision and recall for large numbers of identification tests, was used as the performance criterion. This study trained and compared the proposed models based on images of either the front-side or back-side of blister-packaged drugs. RESULTS: Our results showed that the total training time for the front-side model and back-side model was 5 h 34 min and 7 h 42 min, respectively. The F1 score of the back-side model (95.99%) was better than that of the front-side model (93.72%). CONCLUSIONS: In conclusion, this study constructed a deep learning-based model for blister-packaged drug identification, with an accuracy greater than 90%. This model outperformed identification using conventional computer vision solutions, and could assist pharmacists in identifying drugs while preventing medication errors caused by look-alike blister packages. By integration into existing prescription systems in hospitals, the results of this study indicated that using this model, drugs dispensed could be verified in order to achieve automated prescription and dispensing.

Coping With a Mass Casualty: Insights into a Hospital's Emergency Response and Adaptations After the Formosa Fun Coast Dust Explosion.

OBJECTIVE: The study provides a comprehensive insight into how an initial receiving hospital without adequate capacity adapted to coping with a mass casualty incident after the Formosa Fun Coast Dust Explosion (FFCDE). METHODS: Data collection was via in-depth interviews with 11 key participants. This was combined with information from medical records of FFCDE patients and admission logs from the emergency department (ED) to build a detailed timeline of patients flow and ED workload changes. Process tracing analysis focused on how the ED and other units adapted to coping with the difficulties created by the patient surge. RESULTS: The hospital treated 30 victims with 36.3% average total body surface area burn for over 5 hours alongside 35 non-FFCDE patients. Overwhelming demand resulted in the saturation of ED space and intensive care unit beds, exhaustion of critical materials, and near-saturation of clinicians. The hospital reconfigured human and physical resources differently from conventional drills. Graphical timelines illustrate anticipatory or reactive adaptations. The hospital's ability to adapt was based on anticipation during uncertainty and coordination across roles and units to keep pace with varying demands. CONCLUSION: Adapting to beyond-surge capacity incident is essential to effective disaster response. Building organizational support for effective adaptation is critical for disaster planning.

Exploration of Medical Trajectories of Stroke Patients Based on Group-Based Trajectory Modeling.

A high mortality rate is an issue with acute cerebrovascular disease (ACVD), as it often leads to a high medical expenditure, and in particular to high costs of treatment for emergency medical conditions and critical care. In this study, we used group-based trajectory modeling (GBTM) to study the characteristics of various groups of patients hospitalized with ACVD. In this research, the patient data were derived from the 1 million sampled cases in the National Health Insurance Research Database (NHIRD) in Taiwan. Cases who had been admitted to hospitals fewer than four times or more than eight times were excluded. Characteristics of the ACVD patients were collected, including age, mortality rate, medical expenditure, and length of hospital stay for each admission. We then performed GBTM to examine hospitalization patterns in patients who had been hospitalized more than four times and fewer than or equal to eight times. The patients were divided into three groups according to medical expenditure: high, medium, and low groups, split at the 33rd and 66th percentiles. After exclusion of unqualified patients, a total of 27,264 cases (male/female = 15,972/11,392) were included. Analysis of the characteristics of the ACVD patients showed that there were significant differences between the two gender groups in terms of age, mortality rate, medical expenditure, and total length of hospital stay. In addition, the data were compared between two admissions, which included interval, outpatient department (OPD) visit after discharge, OPD visit after hospital discharge, and OPD cost. Finally, the differences in medical expenditure between genders and between patients with different types of stroke-ischemic stroke, spontaneous intracerebral hemorrhage (sICH), and subarachnoid hemorrhage (SAH)-were examined using GBTM. Overall, this study employed GBTM to examine the trends in medical expenditure for different groups of stroke patients at different admissions, and some important results were obtained. Our results demonstrated that the time interval between subsequent hospitalizations decreased in the ACVD patients, and there were significant differences between genders and between patients with different types of stroke. It is often difficult to decide when the time has been reached at which further treatment will not improve the condition of ACVD patients, and the findings of our study may be used as a reference for assessing outcomes and quality of care for stroke patients. Because of the characteristics of NHIRD, this study had some limitations; for example, the number of cases for some diseases was not sufficient for effective statistical analysis.

Investigating the effect of daily sleep on memory capacity in college students.

BACKGROUND: Sleep is a natural periodic state of rest for body and mind and daily sleep affects physical and mental health. However, it is essential to address intensity of sleep characteristics affecting the memory capacity of humans positively or negatively. OBJECTIVE: Using wearable devices to observe and assess the effect of daily sleep on memory capacity of college students. METHODS: This study assessed the daily sleep characteristics and memory capacity of 39 college students who used wrist-worn devices. The spatial span test (SST) was used to evaluate the memory capacity. RESULTS: The study indicated a negative correlation between memory capacity and awake count on the test date and during the week before the test date (r=-0.153 (95% CI: -0.032, -0.282), r=-0.391 (95% CI: -0.520, -0.235), respectively). However, the minutes asleep on the test date and during the week before the test date positively affected memory capacity (r= 0.127 (95% CI: 0.220, 0.025), r= 0.370 (95% CI: 0.208, 0.500), respectively). In addition, spending ⩾ 6 hours and 42 minutes asleep on the test date or ⩾ 6 hours and 37 minutes asleep per day on average during the week before the test date resulted in a better memory capacity. CONCLUSIONS: A lower awake count led to a higher memory capacity in college students, as did more minutes asleep.

A Study of the Effects of Daily Physical Activity on Memory and Attention Capacities in College Students.

This study evaluated the relationship between daily physical activity (DPA) and memory capacity, as well as the association between daily activity and attention capacity, in college students in Taiwan. Participants (mean age = 20.79) wore wearable trackers for 106 days in order to collect DPA. These data were analyzed in association with their memory and attention capacities, as assessed using the spatial span test (SST) and the trail making test (TMT). The study showed significant negative correlations between memory capacity, time spent on the attention test (TSAT), calories burnt, and very active time duration (VATD) on the day before testing (r = -0.272, r = -0.176, r = 0.289, r = 0.254, resp.) and during the week prior to testing (r = -0.364, r = -0.395, r = 0.268, r = 0.241, resp.). The calories burnt and the VATD per day thresholds, which at best discriminated between normal-to-good and low attention capacity, were ≥2283 calories day-1, ≥20 minutes day-1 of very high activity (VHA) on the day before testing, or ≥13,640 calories week-1, ≥76 minutes week-1 of VHA during the week prior to testing. Findings indicated the short-term effects that VATD and calories burnt on the day before or during the week before testing significantly and negatively associated with memory and attention capacities of college students.

Differences in Spontaneous Intracerebral Hemorrhage Cases between Urban and Rural Regions of Taiwan: Big Data Analytics of Government Open Data.

This study evaluated the differences in spontaneous intracerebral hemorrhage (sICH) between rural and urban areas of Taiwan with big data analysis. We used big data analytics and visualization tools to examine government open data, which included the residents' health medical administrative data, economic status, educational status, and relevant information. The study subjects included sICH patients of Taipei region (29,741 cases) and Eastern Taiwan (4565 cases). The incidence of sICH per 100,000 population per year in Eastern Taiwan (71.3 cases) was significantly higher than that of the Taipei region (42.3 cases). The mean coverage area per hospital in Eastern Taiwan (452.4 km²) was significantly larger than the Taipei region (24 km²). The residents educational level in the Taipei region was significantly higher than that in Eastern Taiwan. The mean hospital length of stay in the Taipei region (17.9 days) was significantly greater than that in Eastern Taiwan (16.3 days) (p < 0.001). There were no significant differences in other medical profiles between two areas. Distance and educational barriers were two possible reasons for the higher incidence of sICH in the rural area of Eastern Taiwan. Further studies are necessary in order to understand these phenomena in greater depth.

Does the Short-Term Effect of Air Pollution Influence the Incidence of Spontaneous Intracerebral Hemorrhage in Different Patient Groups? Big Data Analysis in Taiwan.

Spontaneous intracerebral hemorrhage (sICH) has a high mortality rate. Research has demonstrated that the occurrence of sICH is related to air pollution. This study used big data analysis to explore the impact of air pollution on the risk of sICH in patients of differing age and geographic location. 39,053 cases were included in this study; 14,041 in the Taipei region (Taipei City and New Taipei City), 5537 in Taoyuan City, 7654 in Taichung City, 4739 in Tainan City, and 7082 in Kaohsiung City. The results of correlation analysis indicated that there were two pollutants groups, the CO and NO2 group and the PM2.5 and PM10 group. Furthermore, variations in the correlations of sICH with air pollutants were identified in different age groups. The co-factors of the influence of air pollutants in the different age groups were explored using regression analysis. This study integrated Taiwan National Health Insurance data and air pollution data to explore the risk factors of sICH using big data analytics. We found that PM2.5 and PM10 are very important risk factors for sICH, and age is an important modulating factor that allows air pollutants to influence the incidence of sICH.

Atlas-Free Cervical Spinal Cord Segmentation on Midsagittal T2-Weighted Magnetic Resonance Images.

An automatic atlas-free method for segmenting the cervical spinal cord on midsagittal T2-weighted magnetic resonance images (MRI) is presented. Pertinent anatomical knowledge is transformed into constraints employed at different stages of the algorithm. After picking up the midsagittal image, the spinal cord is detected using expectation maximization and dynamic programming (DP). Using DP, the anterior and posterior edges of the spinal canal and the vertebral column are detected. The vertebral bodies and the intervertebral disks are then segmented using region growing. Then, the anterior and posterior edges of the spinal cord are detected using median filtering followed by DP. We applied this method to 79 noncontrast MRI studies over a 3-month period. The spinal cords were detected in all cases, and the vertebral bodies were successfully labeled in 67 (85%) of them. Our algorithm had very good performance. Compared to manual segmentation results, the Jaccard indices ranged from 0.937 to 1, with a mean of 0.980 ± 0.014. The Hausdorff distances between the automatically detected and manually delineated anterior and posterior spinal cord edges were both 1.0 ± 0.5 mm. Used alone or in combination, our method lays a foundation for computer-aided diagnosis of spinal diseases, particularly cervical spondylotic myelopathy.

Rough set based rule induction in decision making using credible classification and preference from medical application perspective.

This paper presents a new heuristic algorithm for reduct selection based on credible index in the rough set theory (RST) applications. This algorithm is efficient and effective in selecting the decision rules particularly the problem to be solved in a large scale. This algorithm is capable to derive the rules with multi-outcomes and identify the most significant features simultaneously, which is unique and useful in solving predictive medical problems. The end results of the proposed approach are a set of decision rules that illustrates the causes for solitary pulmonary nodule and results of the long term treatment.

Trends and outcomes in the utilization of laparoscopic appendectomies in a low-income population in Taiwan from 2003 to 2011.

BACKGROUND: Numerous epidemiological studies have compared outcomes between laparoscopic appendectomies (LA) and open appendectomies (OA); however, few studies have assessed the efficacy of LA specifically in a low-income population (LIP). METHODS: We analyzed the trends in the utilization and outcomes of LA versus OA in an LIP in Taiwan using data from the National Health Insurance (NHI) Research Database. RESULTS: Steady temporal growth trends were observed for the patients who underwent LA in both the LIP and general population (GP); however, in each study year, the proportion of LIP patients who underwent LA was lower than the proportion of GP patients who underwent the procedure. The LIP patients were more susceptible to payment policies than the GP patients; thus, more attention should be paid to vulnerable patient populations when formulating and revising NHI payment policies. Compared with OAs, LAs were associated with a slightly higher rate of routine patient discharges and a lower rate of in-hospital complications (1.48% vs. 3.76%, p < 0.05). The rate of readmission for complications was lower in patients after LA than in patients after OA (1.64% vs. 3.89%, p < 0.05). The overall case-fatality rate of LIP patients who underwent LA was lower than that of those who underwent OA. LA was correlated with a significantly shorter length of hospital stay (LOS) compared with OA (3.80 ± 0.08 vs. 5.51 ± 0.11, p < 0.05). The average hospital cost for LA was slightly less than that for OA (1178 ± 13 vs. 1191 ± 19 USD, p < 0.05). A higher percentage of patients who underwent OA required an LOS longer than 14 days compared to patients who underwent LA (7.73% vs. 1.97%, p < 0.05). Regarding hospital costs and LOS, LA showed significant advantages over OA in the subpopulations of male patients, patients 45 years old and older, patients with Charlson Comorbidity Index (CCI) scores of two or more, and patients with complicated cases of appendicitis. CONCLUSION: The LIP patients benefited more from the LA approach than the OA approach in the treatment of appendicitis, especially regarding LOS, in-hospital complications, in-hospital mortality, and routine discharge rates.

The definition of a prolonged intensive care unit stay for spontaneous intracerebral hemorrhage patients: an application with national health insurance research database.

INTRODUCTION: Length of stay (LOS) in the intensive care unit (ICU) of spontaneous intracerebral hemorrhage (sICH) patients is one of the most important issues. The disease severity, psychosocial factors, and institutional factors will influence the length of ICU stay. This study is used in the Taiwan National Health Insurance Research Database (NHIRD) to define the threshold of a prolonged ICU stay in sICH patients. METHODS: This research collected the demographic data of sICH patients in the NHIRD from 2005 to 2009. The threshold of prolonged ICU stay was calculated using change point analysis. RESULTS: There were 1599 sICH patients included. A prolonged ICU stay was defined as being equal to or longer than 10 days. There were 436 prolonged ICU stay cases and 1163 nonprolonged cases. CONCLUSION: This study showed that the threshold of a prolonged ICU stay is a good indicator of hospital utilization in ICH patients. Different hospitals have their own different care strategies that can be identified with a prolonged ICU stay. This indicator can be improved using quality control methods such as complications prevention and efficiency of ICU bed management. Patients' stay in ICUs and in hospitals will be shorter if integrated care systems are established.

The incidence, hospital expenditure, and, 30 day and 1 year mortality rates of spontaneous intracerebral hemorrhage in Taiwan.

The risks of morbidity and mortality are high in patients with spontaneous intracerebral hemorrhage (sICH). The medical care resources associated with sICH are also substantial. This study aimed to evaluate the medical expenditure for sICH patients in Taiwan. We analyzed the National Health Insurance Research Database from 2005 to 2010. The inclusion criterion was first-event sICH; traumatic ICH patients were excluded. Student's t-test, multiple linear regression and the chi-squared test were employed as the statistical methods. Our results showed that the incidence of sICH was 40.77 patients per 100,000 of population per year in Taiwan. The incidence increased with age and was greater in men than women. The mean hospital length of stay (LOS) of first-event sICH patients was 31.8 days; the mean LOS in the intensive care unit was 7.9 days; and the mean survival time was 60.4 months. The mortality rate within 30 days and within 1 year was 19.8 and 29.6%, respectively. The mean hospital expenditure of first-event sICH patients was USD $7572, and was highly correlated with LOS. In conclusion, the incidence of sICH in Taiwan is higher than that in white and black populations of northern America and some European countries and lower than that in the Asian populations of Japan and China. The features of male and female sICH patients differ. Our findings suggest that the hospital expenditure and mortality rate of sICH patients in Taiwan are comparable with those of other countries.

Using an integrated COC index and multilevel measurements to verify the care outcome of patients with multiple chronic conditions.

BACKGROUND: The increasing prevalence of multiple chronic conditions has accentuated the importance of coordinating and integrating health care services. Patients with better continuity of care (COC) have a lower utilization rate of emergency department (ED) services, lower hospitalization and better care outcomes. Previous COC studies have focused on the care outcome of patients with a single chronic condition or that of physician-patient relationships; few studies have investigated the care outcome of patients with multiple chronic conditions. Using multi-chronic patients as subjects, this study proposes an integrated continuity of care (ICOC) index to verify the association between COC and care outcomes for two scopes of chronic conditions, at physician and medical facility levels. METHODS: This study used a dataset of 280,840 subjects, obtained from the Longitudinal Health Insurance Database (LHID 2005), compiled by the National Health Research Institutes, of the National Health Insurance Bureau of Taiwan. Principal Component Analysis (PCA) was used to integrate the indices of density, dispersion and sequence into ICOC to measure COC outcomes - the utilization rate of ED services and hospitalization. A Generalized Estimating Equations model was used to verify the care outcomes. RESULTS: We discovered that the higher the COC at medical facility level, the lower the utilization rate of ED services and hospitalization for patients; by contrast, the higher the COC at physician level, the higher the utilization rate of ED services (odds ratio > 1; Exp(ß) = 2.116) and hospitalization (odds ratio > 1; Exp(ß) = 1.688). When only those patients with major chronic conditions with the highest number of medical visits were considered, it was found that the higher the COC at both medical facility and physician levels, the lower the utilization rate of ED services and hospitalization. CONCLUSIONS: The study shows that ICOC is more stable than single indices and it can be widely used to measure the care outcomes of different chronic conditions to accumulate empirical evidence. Concentrated care of multi-chronic patients by a single physician often results in unsatisfactory care outcomes. This highlights the need for referral mechanisms and integration of specialties inside or outside medical facilities, in order to optimize patient-centered care.

Estimating postoperative skull defect volume from CT images using the ABC method.

OBJECTIVES: Surgeons often perform decompressive craniectomy to alleviate a medically-refractory increase of intracranial pressure. The frequency of this type of surgery is on the rise. The goal of this study is to develop a simple formula for clinicians to estimate the volume of the skull defect, based on postoperative computed tomography (CT) studies. METHODS: We collected thirty sets of postoperative CT images from patients undergoing craniectomy. We measured the skull defect volume by computer-assisted volumetric analysis (V(m)) and our own ABC technique (V(abc)). We then compared the volumes measured by these two methods. RESULTS: The V(m) ranged from 3.2 to 76.4 mL, with a mean of 38.9 mL. The V(abc) ranged from 3.8 to 71.5 mL, with a mean of 38.5 mL. The absolute differences between V(abc) and V(m) ranged from 0.05 to 17.5 mL (mean: 3.8±4.2). There was no statistically significant difference between V(abc) and V(m) (p=0.961). The correlation coefficient between V(abc) and V(m) was 0.969. In linear regression analysis, the slope was 1.00086 and the intercept was -0.0035 mL (r(2)=0.939). The residual was 5.7 mL. CONCLUSION: We confirmed that the ABC technique is a simple and accurate method for estimating skull defect volume, and we recommend routine application of this formula for all decompressive craniectomies.

Decision model for acute appendicitis treatment with decision tree technology--a modification of the Alvarado scoring system.

BACKGROUND: How to decide the proper time to do laparotomies for acute appendicitis patients is sometimes very difficult, especially in areas with no imaging diagnostic tools. The Alvarado scoring system (ASS) is a convenient and inexpensive decision making tool; however, its accuracy needs to be improved. The decision tree is the most frequently used data mining technology for diagnostic model building. This study used a decision tree to modify the ASS and to prioritize the variables. METHODS: We collected 532 patients who underwent appendectomy. Patients who had undergone incidental appendectomy were excluded from the study. The decision tree algorithm was constructed with the data mining workbench Clementine version 8.1. It is a top-down algorithm designed to generate a decision tree model with entropy. The algorithm chooses the best decision node with which to separate different classes from empirical data. The Wilcoxon signed rank test, Student t test and chi(2) test were used for statistical analysis. RESULTS: Among the 532 patients recruited into the study, 420 had acute appendicitis and 112 had normal appendix. Women with acute appendicitis were older than their male counterparts (p < 0.001). All patients had right lower quadrant tenderness. The new model was constructed with decision tree technology, and the accuracy of the diagnostic rate was better than that of ASS (p < 0.001). The sensitivity and specificity of the new model were 0.945 and 0.805, respectively. CONCLUSION: The new model is more convenient and accurate than ASS. Right lower quadrant tenderness is an inclusion criterion for acute appendicitis diagnosis. Migrating pain and neutrophil count > 75% were significant factors for acute appendicitis diagnosis if ASS score < 6. Although the criteria of nausea/vomiting and white blood cell count > 10,000/dL were significantly different between acute appendicitis and normal appendix, there was no significant contribution of entropy change below the "neutrophil count > 75%" nodes in the model. So they were erased from the decision tree model. Further studies need to be conducted to investigate why older women are at higher risk for acute appendicitis.

Good mortality prediction by Glasgow Coma Scale for neurosurgical patients.

BACKGROUND: How to effectively use the finite resources of an intensive care unit (ICU) for neurosurgical patients is a critical decision-making process. Mortality prediction models are effective tools for allocating facilities. This study intended to distinguish the prediction power of the Acute Physiology and Chronic Health Evaluation II (APACHE II), the Simplified Acute Physiology Score II (SAPS II), and the Glasgow Coma Scale (GCS) for neurosurgical patients. METHODS: According to the definitions of the APACHE II, this study recorded both APACHE II and SAPS II scores of 154 neurosurgical patients in the ICU of a 600-bed general hospital. Linear regression models of GCS (GCS-mr) were constructed. The t test, receiver operating characteristic (ROC) curve and Wilcoxon signed rank test were used as the statistical evaluation methods. RESULTS: There were 50 (32.5%) females and 104 (67.5%) males in this study. Among them, 108 patients survived and 46 patients died. The areas under the ROC curves (AUC) of SAPS II and APACHE II were 0.872 and 0.846, respectively. The AUC of GCS-mr was 0.866, and the R(2) was 0.389. The evaluation powers of SAPS II, GCS-mr and APACHE II were the same (p > 0.05). Patients with GCS 5 or GCS-M > 3 (p < 0.01). CONCLUSION: The predictive powers of SAPS II, APACHE II and GCS-mr were the same. The GCS-mr is more convenient for predicting mortality in neurosurgical patients. Both GCS

Physicians' characteristics in the usage of online database: a representative nationwide survey of regional hospitals in Taiwan.

Physicians have to deal with a broad range of medical problems in clinical practice, thus making the timely acquisition of relevant information is a critical skill for physicians to improve care quality. The current national study investigates how physicians search for medical information and analyses how they use online medical databases. A structured questionnaire survey was conducted, with 457 valid returns collected. Internet-based resources (Web portals, online databases, and electronic journals) were more often accessed by physicians to look for medical information than personal or paper ones. Almost universally, physicians have accessed online databases. MEDLINE was the most frequently accessed database. Furthermore, physicians under 50 years old tended to access online databases more often than their elder colleagues (OR = 5.27, 95% CI = 1.96-14.14 for age <35; OR = 4.68, 95% CI = 2.07-10.60 for ages 35-50). In addition, physicians with faculty position were more often accessing online databases (OR = 3.32; 95% CI = 1.75-6.30). Other factors - including clinical experience, administrative position, gender, academic degree, and professional specialty - carried no significant differences. These data may assist in determining how to promote the use of online evidence-based medical information for clinical services.