Identifying Preventable Emergency Admissions in Hospitals Using Machine Learning.

Overcrowding in EDs has been viewed globally as a chronic health challenge. It is directly related to the increased use of EDs for non-urgent issues, leading to increased complications, long waiting times, a higher death rate, or delayed intervention of those more acutely ill. This study aims to develop Machine Learning models to differentiate immediate medical needs from unnecessary ED visits. A Decision Tree, Random Forest, AdaBoost, and XGBoost models were built and evaluated on real-life data. XGBoost achieved the best accuracy and F1-score.

Modified team-based and blended learning perception: a cohort study among medical students at King Saud University.

BACKGROUND & OBJECTIVE: Medical schools have evolved toward competency-based education and active learner-centered strategies. Medical informatics course was introduced in 2011 in the 3rd year at the College of Medicine (CoM), King Saud University (KSU), to enhance future medical graduates with technological and information competencies. Modified team-based learning and blended learning were emphasized using face-to-face lectures, various e-learning technologies, workshop and seminars. The current study's main objective was to assess students' perceptions towards blended and modified team-based learning at the CoM in KSU. METHODS: A survey was distributed to medical students in three consecutive years: 2017-2019. The survey contains items regarding student perception of various types of blended learning techniques applied in the course. The survey was administered using i-Clicker; an interactive device that enables students to answer survey questions. Descriptive statistics were used to examine the perception of students on these blended learning dimensions investigated. RESULTS: Seven-hundred and one student responded to the questionnaire (male; 69.5%, female 30.5%). Out of which, 59.1% of students found team interactions positively supported discussions and asked questions freely, and 48.1% expressed that working in groups facilitated their learning process. However, 56.0% of students chose face-to-face lectures as the most preferred class activities followed by discussion 23.8%. More than 78% of participants agree that online quizzes are good experience and enjoyable. Grade center where students can check for marks and attendance also received high perception (66.3%). CONCLUSION: Introducing modified team-based and blended-learning are considered challenging, and therefore, investigating their perceptions can provide useful insights into how these methods could be used more effectively. The blended-learning technique is highly essential in teaching medical informatics to overcome challenges faced due to a large number of students and the need for various exposures to reach the course's learning goals. Moreover, it is noticed that students were engaged in face-to-face and online activities, furthermore, modified team-based learning reported facilitating learning and asking questions without embarrassment.

Middle East Respiratory Syndrome (MERS): Comparing the knowledge, attitude and practices of different health care workers.

BACKGROUND: Middle East Respiratory Syndrome (MERS) is a viral respiratory illness that was recently recognized in humans. Recently, the Ministry of Health in Saudi Arabia reported a substantial increase in MERS cases, primarily from the Riyadh region. The objective of the present study was to evaluate knowledge, attitude and practices towards MERS among physicians, nurses, pharmacist and technicians individually. METHODS: A cross sectional study conducted at King Khalid University Hospital, Riyadh, Saudi Arabia among individual healthcare workers. The survey questionnaire was self-administrated and consisted of five sections: Demographic; Source of MERS information; Knowledge; Attitude; and Practice of healthcare workers towards MERS. RESULTS: A total of 391 participants of which physicians (162; 41.4%), pharmacists (18; 4.6%), nurses (130; 33.3%) and technicians (81; 20.7%) were included with a response rate of 95.71%. The majority of the participants were female (53.70%) and mostly in the nurse's category (40.5%). The participants reported the highest main source of information was seminars and workshops (n=191; 48%) followed by social media (n=179; 45%). The overall score indicates good knowledge among physicians (95.7%), pharmacists (88.9%), nurses (86.2%) and technicians (91.4%) and showed statistically significant (p=0.039). The study showed a positive attitude among physicians (96.3%), pharmacist (94.4%), nurses (94.6%) and technicians (90.1%) with no statistically significant (p=0.273). However, the majority of the participants showed average practices towards MERS. However, the least practice among participants was the use of facemask in the crowds (24.2%). The demographic characteristic's age, gender and professions showed significantly associated with mean knowledge score. Similarly, statistical significance observed in gender and experience demographic variables with a mean attitude score. CONCLUSIONS: The study concludes that different health workers showed good knowledge and positive attitudes, but low to average practices towards MERS with low adherence to facemask practice. When comparing workers, physicians have a high degree of knowledge and attitude when compared to nurses, pharmacist and technicians.

Assessment of physician's knowledge, perception and willingness of telemedicine in Riyadh region, Saudi Arabia.

INTRODUCTION: Telemedicine is the utilization of computer applications and telecommunication technologies to deliver clinical services remotely. The Ministry of Health in Saudi Arabia, recently established an e-Health strategy that includes the use of telemedicine in order to improve the accessibility and quality of care among patients and healthcare providers. OBJECTIVES: The present study aimed to assess the knowledge and perception of telemedicine and its applications among physicians. Secondly, to evaluate their willingness towards adopting telemedicine in clinical practice. METHODS: The study is a cross sectional conducted in four hospitals; King Abdulaziz Medical City, King Faisal Specialist Hospital and Research Center, King Saud Medical City and King Saud University Medical City in Riyadh, Saudi Arabia. The survey questionnaire was a self-administered, which was adopted from previous studies. The questionnaire consists of; access to a computer and its literacy, knowledge, perceptions and willingness of telemedicine. RESULTS: A total of 391 physicians of which male (301; 77.0%) and female (90; 23.0%) completed the questionnaire. Half of the participants never used personal computers or laptops at home. Interestingly, 89.2% of them have two or more smart devices. Participants have average knowledge about telemedicine technology (46.1%). Nearly, 77% of the professionals believed that continuous training is necessary for the use of telemedicine (P = 0.01). The highest level of perception was (90%) for telemedicine as a viable approach for providing medical care services to patients. More than 90% of specialties professional agreed that telemedicine can save time, money and further believed information and communication technology (ICT) has a potential role in healthcare. Overall, 70% of physicians reported a very low number of conferences, speeches or meetings held regarding telemedicine technology in their working places. Main issues reported in adopting telemedicine are patient privacy, the high cost of equipment, lack of suitable training, and lack of consultation between information technology expert and clinicians. CONCLUSIONS: Despite the fact that the majority of professionals have two or more smart devices and are communicating with patients via email or social media. However, the majority of medical professionals still have low knowledge of telemedicine technology. In addition, most of the participants showed positive perceptions of telemedicine and are willing to adopt it in clinical practice. The major reported barriers for the adoption of telemedicine were privacy issues, lack of training, cost and issues related to information and communication technology.

Assessment of patient safety challenges and electronic occurrence variance reporting (e-OVR) barriers facing physicians and nurses in the emergency department: a cross sectional study.

BACKGROUND: The purpose of patient safety is to prevent harm occurring in the healthcare system. Patient safety is improved by the use of a reporting system in which healthcare workers can document and learn from incidents, and thus prevent potential medical errors. The present study aimed to determine patient safety challenges facing clinicians (physicians and nurses) in emergency medicine and to assess barriers to using e-OVR (electronic occurrence variance reporting). METHODS: This cross-sectional study involved physicians and nurses in the emergency department (ED) at King Khalid University Hospital (KKUH) in Riyadh, Saudi Arabia. Using convenience sampling, a self-administered questionnaire was distributed to 294 clinicians working in the ED. The questionnaire consisted of items pertaining to patient safety and e-OVR usability. Data were analyzed using frequencies, means, and percentages, and the chi-square test was used for comparison. RESULTS: A total of 197 participants completed the questionnaire (67% response rate) of which 48 were physicians (24%) and 149 nurses (76%). Only 39% of participants thought that there was enough staff to handle work in the ED. Roughly half (48%) of participants spoke up when something negatively affected patient safety, and 61% admitted that they sometimes missed important patient care information during shift changes. Two-thirds (66%) of the participants reported experiencing violence. Regarding e-OVR, 31% of participants found reporting to be time consuming. Most (85%) participants agreed that e-OVR training regarding knowledge and skills was sufficient. Physicians reported lower knowledge levels regarding how to access (46%) and how to use (44%) e-OVR compared to nurses (98 and 95%, respectively; p < 0.01). Less than a quarter of the staff did not receive timely feedback after reporting. Regarding overall satisfaction with e-OVR, only 25% of physicians were generally satisfied compared to nearly half (52%) of nurses. CONCLUSION: Although patient safety is well emphasized in clinical practice, especially in the ED, many factors hinder patient safety. More awareness is needed to eliminate violence and to emphasize the needs of additional staff in the ED. Electronic reporting and documentation of incidents should be well supported by continuous staff training, help, and feedback.

Development of Saudi e-health literacy scale for chronic diseases in Saudi Arabia: using integrated health literacy dimensions.

OBJECTIVE: Health literacy has become a global issue, and it is important that patients and individuals are able to use information technology to access health information and educational services. The research objective is to develop a Saudi e-health literacy scale (SeHL) for measuring e-health literacy among Saudis suffering from non-communicable diseases (NCD). METHODS: Overall, 14 relevant papers in related interdisciplinary fields were reviewed to select the most useful literacy dimensions. From these articles, we extracted the most common dimensions used to measure e-health literacy across the disciplines. Multiple workshops with multidisciplinary team members reviewed and evaluated items for SeHL. RESULTS: Four key aspects of e-health literacy-use of technology/media, information-seeking, usefulness and confidence-were identified and integrated as e-health literacy dimensions. These will be used to measure e-health literacy among Saudi patients with NCDs. A translation from Arabic to English was performed in order to ensure that translation process was accurate. A SeHL scale was developed to measure e-health literacy among Saudi patients. By understanding e-health literacy levels, we will be able to create a patient-education system to be used by patients in Saudi Arabia. CONCLUSIONS: As information technology is increasingly used by people of all ages all over the world, e-health literacy has been identified as a key factor in determining health outcomes. To date, no comprehensive scale exists to assess e-health literacy levels among speakers of Arabic, particularly among people with NCD such as diabetes, cardiovascular diseases and hypertension.

The impact of obesity related websites on decision making among students in Saudi Arabia.

Background & Objectives: The present study was to investigate the use of the internet among university students accessing obesity health information and further to measure their satisfaction and in decision-making. Methods: A cross sectional study, among students at King Saud University (KSU), Riyadh, Saudi Arabia. This study received ethical clearance from Institutional Review Board, College of Medicine, KSU. Female and male of undergraduate and postgraduate, enrolled through a random sampling. The survey questionnaire was self-administered and consisted of two sections. Results: A total of 448 students (177 males and 271 females) participated in this study. The response rate was 66.86. The study showed that the prevalence of overweight and obesity was more common among male compared to female students. Majority of the students (58.7%) were of normal Body Mass Index (BMI). It also revealed that 187 (41.7%) reported always acquire obesity health information from the internet whereas 203 (45.35) sometimes use the internet. Half of the respondents reported using a search engine to seek information. Forty-five percent reported spending at least an hour per week. Nearly 52.2% of participants are taking decision related to their lifestyle and showed statistical significant (P = 0.0001). More than half of the students believed that the obesity information in the websites are very useful. Furthermore, 84.4% reported, language presented in the websites are easy to understand. With respect to quality, 46.9% rated as excellent whereas 39.5% as average. Interpretation & Conclusions: The present study findings have demonstrated that university students are using internet in higher rates for finding obesity health information and are satisfied with the decision they are making. Finally, the study concludes that the internet online health information considered as an essential tool for health promotion among student population regarding weight control or managing obesity.

Assessment of picture archiving and communication system (PACS) at three of ministry of health hospitals in Riyadh region - Content analysis.

BACKGROUND: Picture archiving and communication system (PACS) are management information systems used for distributing, viewing and archiving digital images by integrating different types of modalities through communication networks. PACS have many advantages that can lead to improving health care quality. PACS has been widely used in hospitals in Saudi Arabia for the past 10 years. However, an extensive review of literature in the field of PACS, among physicians and radiologists in Saudi Arabia, showed lack of local studies of this costly and newly implemented technology. Therefore, this assessment is very important to provide an insightful study of PACS in Saudi Arabia to provide proper recommendations for the PACS projects implementation nationwide. OBJECTIVES: The objectives of this study are to, firstly, assess the perceived benefits of PACS among physicians and radiologists specifically in quality of care, secondly, assess the perceived challenges of PACS implementation and adoption inside and outside the radiology department, and thirdly, to compare between physicians' and radiologists' perceptions toward PACS. METHODS: A cross-sectional descriptive study at three of Ministry of Health (MOH) Hospitals in the Riyadh region, Saudi Arabia. The researchers used two separate surveys questionnaires, for administration to the physicians and radiologists at the three hospitals. Apart from the questionnaire, included is feedback as responses to open-ended questions. Content analysis was used to analyze the feedback under two themes: benefits or challenges. RESULTS: The response rate was 46% (84/183) physicians and 88% (15/17) radiologists have participated in this study. The result showed that 70% physicians' views affirms that PACS improved physicians' efficiency. On the other hand, all radiologists who responded affirmed that PACS improved efficiency. For questions on the ability to make decisions, 69% of views have affirmed that PACS improved physician's abilities to make decisions regarding patient care. Using PACS has led to a reduction in patients' length of stay in hospital (LOS) question, 79% of total views were positive. In contrast, only 18% of physicians talked about PACS positively in summary views and 82% talked about the challenges of PACS whereas 20% of radiologists talked about PACS positively. CONCLUSIONS: The results in the present study conclude that PACS was well perceived due to its numerous benefits among physicians and radiologists. However, radiologists showed more focus on the benefits of PACS than physicians. The main disadvantages are that PACS has resulted in difficulty in finding images, recurrent downtime and insufficient training.

Vaccination adherence: Review and proposed model.

BACKGROUND: The prevalence of childhood vaccine-preventable diseases can be significantly reduced through adherence to confirmed vaccination schedules. However, many barriers to vaccination compliance exist, including a lack of awareness regarding the importance of vaccines, missing due dates, and fear of complications from vaccinations. The aim of this study is to review the existing tools and publications regarding vaccination adherence, and to propose a design for a vaccination adherence application (app) for smartphones. METHODS: Android and iOS apps designed for vaccination reminders have been reviewed to examine six elements: educational factor; customizing features; reminder tools; peer education facilitations; feedback, and the language of apps' interface and content. The literature from PubMed has been reviewed for studies addressing reminder systems or tools including apps. RESULTS: The study has revealed insufficient (n=6) technology-based interventions for increasing childhood vaccination rates by reminding parents in comparison to the fast growth in technology, out of which are two publications discussed mobile apps. Ten apps have been found in apps stores; only one out of them was designed for the Saudi vaccination schedule in Arabic language with some weaknesses. The study proposed a design for a vaccination reminder app that includes a number of features in order to overcome the limitations discussed in the studied reminders, apps, and systems. The design supports the Arabic language and the Saudi vaccination schedule; parental education including peer education; a variety of reminder methods, and the capability to track vaccinations and refer to the app as a personal health record. CONCLUSION: The study discussed a design for a vaccination reminder app that satisfies the specific requirements for better compliance to children's immunization schedules based on reviewing the existing apps and publications. The proposed design includes element to educate parents and answer their concerns about vaccines. It involves their peers and can encourage the exchange of experiences and overcome vaccine fears. In addition, it could form a convenient child personal health record.

Evaluating factors affecting the implementation of evidence based medicine in primary healthcare centers in Dubai.

OBJECTIVES: To assess the current evidence based medicine (EBM) knowledge, attitude and perceptions of physicians at Dubai Primary Health Care Sector (PHCS). Further to evaluate barrier and facilitator factors toward implementing the EBM practice. METHODOLOGY: A cross-sectional study, at Dubai PHCS, UAE between June and August 2010. The survey was composed of two phases. The first phase was a self administrated questionnaire employed for data collection and the second phase was qualitative method, which was in the form of individual interviews. Statistical Package for Social Sciences (SPSS) was used for data analysis. RESULTS: In total 48 participants responded to the survey questionnaire and 13 responded to individual interviews. The response rate was 70.0%. Mean age was 42.18 (SD 10.46). The majority were females (64.6%). The physicians who attended EBM courses reported 70.30% using EBM and showed statistical significance (p = 0.002) from those who did not attend the EBM courses. 65.0% believe that 50-75% of the patients are capable of participating in clinical decision while 71.8% disagreed that the concept of EBM is not applicable to their culture. In addition they showed significance (p = 0.03) between physician beliefs with regard to patient capacity to take decision. About 67.0% of the family physicians were knowledgeable and followed systematic review as the strongest evidence. They had no access to the EBM resources (37.0%) and had no time to practice the EBM (38.0%). Nearly 40.0% interviewees reported lack of encouragement to attend EBM courses. EBM activities (22.0%) and active audit (18.0%) were top rated facilitating factors. CONCLUSIONS: EBM is not fully utilized by indefinite physicians in the Dubai PHC sector. Factors associated with non-utilization of EBM in the PHCS are lack of encouragement to attend EBM courses, senior physicians resist adoption of EBM, lack of time and insufficient dissemination process for implementing the clinical guideline.

Assessment of legibility and completeness of handwritten and electronic prescriptions.

OBJECTIVES: To assess the legibility and completeness of handwritten prescriptions and compare with electronic prescription system for medication errors. DESIGN: Prospective study. SETTING: King Khalid University Hospital (KKUH), Riyadh, Saudi Arabia. SUBJECTS AND METHODS: Handwritten prescriptions were received from clinical units of Medicine Outpatient Department (MOPD), Primary Care Clinic (PCC) and Surgery Outpatient Department (SOPD) whereas electronic prescriptions were collected from the pediatric ward. The handwritten prescription was assessed for completeness by the checklist designed according to the hospital prescription and evaluated for legibility by two pharmacists. The comparison between handwritten and electronic prescription errors was evaluated based on the validated checklist adopted from previous studies. MAIN OUTCOME MEASURES: Legibility and completeness of prescriptions. RESULTS: 398 prescriptions (199 handwritten and 199 e-prescriptions) were assessed. About 71 (35.7%) of handwritten and 5 (2.5%) of electronic prescription errors were identified. A significant statistical difference (P < 0.001) was observed between handwritten and e-prescriptions in omitted dose and omitted route of administration category of error distribution. The rate of completeness in patient identification in handwritten prescriptions was 80.97% in MOPD, 76.36% in PCC and 85.93% in SOPD clinic units. Assessment of medication prescription completeness was 91.48% in MOPD, 88.48% in PCC, and 89.28% in SOPD. CONCLUSIONS: This study revealed a high incidence of prescribing errors in handwritten prescriptions. The use of e-prescription system showed a significant decline in the incidence of errors. The legibility of handwritten prescriptions was relatively good whereas the level of completeness was very low.

Academic satisfaction among traditional and problem based learning medical students. A comparative study.

OBJECTIVE: To evaluate the academic satisfaction and importance among traditional learning (TL) and problem based learning (PBL) medical students, and to further evaluate the areas of concern in the academic education from the student's point of view. METHODS: A cross sectional study was conducted at the College of Medicine, King Saud University, Riyadh, Kingdom of Saudi Arabia from May to June 2012. The survey questionnaires were self-administered and consisted of mainly 6 sections: teaching, learning, supervision, course organization, information technology (IT) facilities, and development of skills. RESULTS: A total of 92 TL (males: 66 [71.7%]; females: 26 [28.3%]), and 108 PBL (males: 84 [77.8%]; females: 24 [22.1%]), with a mean age of 21.3 +/- 1.3 (TL), and 20.7 +/- 1.0 (PBL) were included in the study. The overall satisfaction rate was higher in the PBL students when compared with TL students in: teaching (84.7%/60.3%); learning (81.4%/64.5%); supervision (80%/51.5%); course organization (69.3%/46.9%); IT facilities (74.0%/58.9%); and development of skills (79.1%/53.9%). There was statistical significance difference in academic satisfaction comparing both groups of students (p

Bayesian hierarchical approach to estimate insulin sensitivity by minimal model.

We adopted Bayesian analysis in combination with hierarchical (population) modelling to estimate simultaneously population and individual insulin sensitivity (SI) and glucose effectiveness (SG) with the minimal model of glucose kinetics using data collected during insulin-modified intravenous glucose tolerance test (IVGTT) and made comparison with the standard non-linear regression analysis. After fasting overnight, subjects with newly presenting Type II diabetes according to World Health Organization criteria (n =65; 53 males, 12 females; age, 54 +/- 9 years; body mass index, 30.4 +/- 5.2 kg/m2; means+/-S.D.) underwent IVGTT consisting of a 0.3 g of glucose bolus/kg of body weight given at time zero for 2 min, followed by 0.05 unit of insulin/kg of body weight at 20 min. Bayesian inference was carried out using vague prior distributions and log-normal distributions to guarantee non-negativity and, thus, physiological plausibility of model parameters and associated credible intervals. Bayesian analysis gave estimates of SI in all subjects. Non-linear regression analysis failed in four cases, where Bayesian analysis-derived SI was located in the lower quartile and was estimated with lower precision. The population means of SI and SG provided by Bayesian analysis and non-linear regression were identical, but the interquartile range given by Bayesian analysis was tighter by approx. 20% for SI and by approx. 15% for SG. Individual insulin sensitivities estimated by the two methods were highly correlated ( rS=0.98; P <0.001). However, the correlation in the lower 20% centile of the insulin-sensitivity range was significantly lower than the correlation in the upper 80% centile ( rS=0.71 compared with rS=0.99; P <0.001). We conclude that the Bayesian hierarchical analysis is an appealing method to estimate SI and SG, as it avoids parameter estimation failures, and should be considered when investigating insulin-resistant subjects.

Associations of glucose control with insulin sensitivity and pancreatic beta-cell responsiveness in newly presenting type 2 diabetes.

We examined the ability of indices of insulin sensitivity and pancreatic beta-cell responsiveness to explain interindividual variability of clinical measures of glucose control in newly presenting type 2 diabetes. Subjects with newly presenting type 2 diabetes (n = 65; 53 males and 12 females; age, 54 +/- 1 yr; body mass index, 30.5 +/- 0.7 kg/m(2); mean +/- SE) underwent an insulin-modified iv glucose tolerance test to determine minimal model-derived insulin sensitivity (S(I)), glucose effectiveness, first-phase insulin secretion, and disposition index. Subjects also underwent a standard meal tolerance test (MTT) to measure fasting/basal (M(0)) and postprandial (M(I)) pancreatic beta-cell responsiveness. Stepwise linear regression used these indices to explain interindividual variability of fasting and postprandial plasma glucose and insulin concentrations and glycated hemoglobin (HbA(1C)). All measures of pancreatic beta-cell responsiveness (M(0), M(I), and first-phase insulin secretion) were negatively correlated with fasting plasma glucose (P < 0.01) and positively correlated with fasting plasma insulin (FPI) and insulin responses to MTT (P < 0.05). S(I) demonstrated negative correlation with FPI (P < 0.001) but failed to correlate with any glucose variable. M(I) followed by disposition index (composite index of insulin sensitivity and pancreatic beta-cell responsiveness) were most informative in explaining interindividual variability. It was possible to explain 70-80% interindividual variability of fasting plasma glucose, FPI, HbA(1C), and insulin responses to MTT, and only 25-40% interindividual variability of postprandial glucose. In conclusion, postprandial insulin deficiency is the most powerful explanatory factor of deteriorating glucose control in newly presenting type 2 diabetes. Indices of insulin sensitivity and pancreatic beta-cell responsiveness explain fasting glucose and HbA(1C) well but fail to explain postprandial glucose.