PoEMS: Policy Network-Based Early Warning Monitoring System for Sepsis in Intensive Care Units.

Sepsis is among the leading causes of morbidity and mortality in modern intensive care units (ICU). Due to accurate and early warning, the in-time antibiotic treatment of sepsis is critical for improving sepsis outcomes, contributing to saving lives, and reducing medical costs. However, the earlier prediction of sepsis onset is made, the fewer monitoring measurements can be processed, causing a lower prediction accuracy. In contrast, a more accurate prediction can be expected by analyzing more data but leading to the delayed warning associated with life-threatening events. In this study, we propose a novel deep reinforcement learning framework for solving early prediction of sepsis, called the Policy Network-based Early Warning Monitoring System (PoEMS). The proposed PoEMS provides accurate and early prediction results for sepsis onset based on analyzing varied-length electronic medical records (EMR). Furthermore, the system serves by monitoring the patient's health status consistently and provides an early warning only when a high risk of sepsis is detected. Additionally, a controlling parameter is designed for users to adjust the trade-off between earliness and accuracy, providing the adaptability of the model to meet various medical requirements in practical scenarios. Through a series of experiments on real-world medical data, the results demonstrate that our proposed PoEMS achieves a high AUROC result of more than 91% for early prediction, and predicts sepsis onset earlier and more accurately compared to other state-of-the-art competing methods.

Convolutional neural network based automatic screening tool for cardiovascular diseases using different intervals of ECG signals.

BACKGROUND AND OBJECTIVE: Automatic screening tools can be applied to detect cardiovascular diseases (CVDs), which are the leading cause of death worldwide. As an effective and non-invasive method, electrocardiogram (ECG) based approaches are widely used to identify CVDs. Hence, this paper proposes a deep convolutional neural network (CNN) to classify five CVDs using standard 12-lead ECG signals. METHODS: The Physiobank (PTB) ECG database is used in this study. Firstly, ECG signals are segmented into different intervals (one-second, two-seconds and three-seconds), without any wave detection, and three datasets are obtained. Secondly, as an alternative to any complex preprocessing, durations of raw ECG signals have been considered as input with simple min-max normalization. Lastly, a ten-fold cross-validation method is employed for one-second ECG signals and also tested on other two datasets (two-seconds and three-seconds). RESULTS: Comparing to the competing approaches, the proposed CNN acquires the highest performance, having an accuracy, sensitivity, and specificity of 99.59%, 99.04%, and 99.87%, respectively, with one-second ECG signals. The overall accuracy, sensitivity, and specificity obtained are 99.80%, 99.48%, and 99.93%, respectively, using two-seconds of signals with pre-trained proposed models. The accuracy, sensitivity, and specificity of segmented ECG tested by three-seconds signals are 99.84%, 99.52%, and 99.95%, respectively. CONCLUSION: The results of this study indicate that the proposed system accomplishes high performance and keeps the characterizations in brief with flexibility at the same time, which means that it has the potential for implementation in a practical, real-time medical environment.

Evaluating people's concern about their health information privacy based on power-responsibility equilibrium model: A case of Taiwan.

To address the issue of rising expenditure of healthcare service and to fulfill the skyrocketing demand for quality healthcare, the electronic medical records (EMR) exchange has become a vital and indispensable solution for healthcare facilities in terms of being able to share medical information among healthcare providers. Hence, EMR exchange was expected to improve the quality of healthcare and reduce the cost of repetitive medical check-ups and unnecessary treatments. However, recent reports affirming EMR data leaks and compromises have ignited major worldwide privacy concerns over the security of the EMR systems. How to effectively diminish patients' concern for EMR privacy has thus become an important issue that healthcare institution managers/stakeholders have to address urgently. This study leverages the power-responsibility equilibrium perspective to investigate the antecedents and consequences of concerns for the EMR exchange. A survey using 391 responses collected from medical centers, regional and district hospitals in Taiwan was used to conduct this study. The results show that government regulations have a positive effect on hospital privacy policies. Furthermore, both government regulations and hospital privacy policy are negatively associated with concern for EMR information privacy. Additional reports gathered from this study also showed that concern for EMR information privacy could result in patients' protective responses including refusal to provide personal health information (PHI), removal of PHI, negative word of mouth, complaining directly to the hospital, or complaining indirectly to third-party organizations. These findings demonstrate the need for healthcare facilities to formulate robust privacy policies in order to alleviate patients' concern for EMR information privacy based on governmental regulations. This regulation is top-priority as the incapability of reducing patients' concern for EMR information privacy may lead to the collapse of the campaign for the full-adoption of EMR or possibly jeopardize the promotion and application of EMR among healthcare facilities.

The adoption of electronic medical record by physicians: A PRISMA-compliant systematic review.

BACKGROUND: The electronic medical record (EMR) is considered to be a vital tool of information and communication technology (ICT) to improve the quality of medical care, but the limited adoption of EMR by physicians results in a considerable warning to its successful implementation. The purpose of the present review is to explore and identify the potential barriers perceived by physicians in the adoption of EMR. METHODS: The systematic review was carried out based on literature published in 5 databases: PubMed, Web of Science, Scopus, The Cochrane Library, and ProQuest from 2014 to 2018, concerning barriers perceived by physicians to the adoption of EMR. RESULTS: The present study incorporates 26 articles based on their appropriateness out of 1354 for the final analysis. Authors explore 25 barriers that appeared 112 times in the literature for the present review; the top 5 frequently mentioned barriers are privacy and security concerns, high start-up cost, workflow changes, system complexity, lack of reliability, and interoperability. CONCLUSION: The systematic review explores that physicians deal with different barriers as they intend to adopt EMR. The barriers explored in the present review are the potential to play as references for the implementer of the EMR system. Thus an attentive analysis of the definitive condition is needed before relevant intervention is determined as the implementation of EMR must be considered as a behavioral change in medical practice.

Do Patients' Privacy Concerns Influence Their Intention toward Medical Image Exchange Consent in Taiwan?

The primary purpose of this study was to examine patients' concerns surrounding information privacy and their intention toward medical image exchange consent. Patients' concerns about information privacy in terms of collection, unauthorized access, errors and secondary use all have significant relationships with patients' intention toward medical image exchange consent in Taiwan. Trust is the foundation for both parties. In this study, we aimed to determine the moderating effect of trust in order to examine patients' intention toward medical image exchange consent under the influence of their information privacy concerns. Three hundred and fifty patients responded to the survey, which yielded a 92.3% response rate. The results of data analysis revealed that patients' information privacy concerns had no significant relationship with patients' intention toward medical image exchange consent. After considering the moderating effect of trust, patients' information privacy concerns do have a significant relationship with patients' intention toward medical image exchange consent, however, the R-square was only 4.5%. Based on this research result, we modified the research framework in order to examine patients' information privacy concerns in terms of collection/non-collection. The R-square of the modified framework was 18.6%, and both collection and non-collection had significant relationships with patients' intention toward medical image exchange consent. Finally, the implications, limitations and future research have been discussed.

The Differing Effect of Gender and Clinical Specialty on Physicians' Intention to Use Electronic Medical Record.

BACKGROUND: The use of electronic medical record (EMR) is anticipated to bring benefits for patients, physicians, and organizations. But limited physicians' acceptance of EMR presents a serious threat to its effective implementation. OBJECTIVES: The current study incorporates technology acceptance model (TAM) with two antecedents, gender, and clinical specialty and one context-specific factor, financial incentives, to identify the factors that influence physicians' intention to use EMR in Taiwan. METHODS: The survey methodology was used to collect data from the physicians, working in the regional hospital that had implemented EMR system. A total of 119 out of 213 questionnaires returned in a response rate of 56%. But four responses were considered ineffective due to missing values. The structural equation modeling (SEM) technique was employed to analyze the research framework. RESULTS: The partial least squares (PLS) regression indicated that three factors perceived usefulness, financial incentives, and attitude toward using EMR significantly affect physicians' intention. But concerning perceived ease of use (PEOU), an insignificant path coefficient was reported. Additionally, regression analysis showed gender, and clinical specialty positively influenced physicians' intention to use EMR. DISCUSSION AND CONCLUSIONS: The proposed research framework contributes to the conclusive explanation for interpreting physicians' intention to use EMR. Physicians generally have a higher level of computer literacy. Therefore, the factor of PEOU could not be critical regarding adopting new health information technology (HIT). This study also brings perspectives from the gender, and clinical differences have primarily been missing in the literature of the physicians' intention to use HIT. In doing so, it infers how gender, and clinical specialty, may complement (and in some instances, reinforce) the influence of technological and attitudinal factors of HIT use. Thus, health care providers must take these factors into consideration in the development and validation of the theories regarding the intention to use EMR.

Exploring critical factors influencing nurses' intention to use tablet PC in Patients' care using an integrated theoretical model.

The use of health information technology (HIT) is expected to deliver benefits for patients, nurses, physicians, and organizations, but the benefits of HIT can only be attained if nurses accept and intend to use it as they are the leading user-group. The use of the tablet is becoming commonplace in healthcare organizations to improve patient care. The current study incorporates Technology Acceptance Model2 (TAM2) with two antecedents, facilitating condition and personal, to identify and understand the factors that influence nurses' intention to use the Tablet PC. The survey methodology was used to collect data from the nurses working in a regional healthcare center in Taiwan. The structural equation modeling (SEM) technique was employed to analyze the research framework. A total of 110 valid responses for analysis. The results suggest that the modified proposed research framework explains about 41.7% of the variance of nurses' behavioral intention. The partial least squares (PLS) regression indicated that perceived usefulness, subjective norm, and personal a positive and significant influence on nurses' intention to use the Tablet PC. But concerning the perceived ease of use, the insignificant path coefficient was reported. The finding also indicated that personal on the research model is much stronger than the subjective norm on Tablet PC performance. The proposed research framework contributes to the conclusive explanation for understanding nurses' intention to use. The current study brings perspectives from the technological and attitudinal differences that have largely been missing in the existing literature of the nurses' intention to use HIT. Thus, health care providers must take these factors into consideration as the findings of the current study advance theory and contribute to the basis for future study intended for enhancing our understanding of nurses' adoption behavior regarding HIT.

The differing privacy concerns regarding exchanging electronic medical records of internet users in Taiwan.

This study explores whether Internet users have different privacy concerns regarding the information contained in electronic medical records (EMRs) according to gender, age, occupation, education, and EMR awareness. Based on the Concern for Information Privacy (CFIP) scale developed by Smith and colleagues in 1996, we conducted an online survey using 15 items in four dimensions, namely, collection, unauthorized access, secondary use, and errors, to investigate Internet users' concerns regarding the privacy of EMRs under health information exchanges (HIE). We retrieved 213 valid questionnaires. The results indicate that the respondents had substantial privacy concerns regarding EMRs and their educational level and EMR awareness significantly influenced their privacy concerns regarding unauthorized access and secondary use of EMRs. This study recommends that the Taiwanese government organizes a comprehensive EMR awareness campaign, emphasizing unauthorized access and secondary use of EMRs. Additionally, to cultivate the public's understanding of EMRs, the government should employ various media, especially Internet channels, to promote EMR awareness, thereby enabling the public to accept the concept and use of EMRs. People who are highly educated and have superior EMR awareness should be given a comprehensive explanation of how hospitals protect patients' EMRs from unauthorized access and secondary use to address their concerns. Thus, the public can comprehend, trust, and accept the use of EMRs, reducing their privacy concerns, which should facilitate the future implementation of HIE.

E-healthcare maturity in Taiwan.

The purpose of this study was to explore the status of e-healthcare maturity in Taiwan following a nationwide investigation sponsored by the Department of Health. Based on Nolan's stage model and related studies, we propose a multidimensional model to gain a better understanding of the current status of e-healthcare maturity in hospitals. The target subjects included every hospital in Taiwan. A total of 538 hospitals were successfully interviewed, showing a high response rate of 94.4%. The results indicate that the overall e-healthcare maturity of Taiwanese hospitals is fairly high. Such a high degree of maturity is critical for formulating e-healthcare policy to stimulate the exchange of electronic medical record. This article provides a brief comparison of the situation in other countries and posits that Taiwan holds a position of relative maturity in the world of e-healthcare development.

A call for safer utilization of radio frequency identification in the e-health era.

The main purpose of this study was to investigate the perceptions of the electromagnetic interference (EMI) caused by radio frequency identification (RFID) with medical devices among hospitals as well as to call the attention of medical institutions to the development of RFID applications. A survey sponsored by the Department of Health of Taiwan was conducted and the target subjects were every hospital in Taiwan (486 in total). The survey topics included testing of RFID interference with medical devices and perceptions of safety issues of RFID. The main targets of the survey were the Chief Information Officers (CIOs) or the main person responsible for RFID systems in each hospital. Of the original 486 questionnaires mailed, 273 were returned. A return rate of 56.17% was obtained. The survey results revealed that only six hospitals had carried out tests on interference by RFID with medical devices, and the results of these tests indicated that RFID does not interfere with medical devices. A majority of hospitals understood that RFID may interfere with medical devices but did not think that this would seriously harm patients. The application of RFID in the healthcare industry is certainly promising; however, EMI issues must be appropriately handled. This study asserts that most hospitals do not understand or pay insufficient attention to the issue of RFID interference with patient safety or medical devices. In addition, most hospitals believe that the problem of RFID should be resolved by RFID vendors. Therefore, this study argues that medical institutions should develop more understanding of RFID issues and that more attention should be given to the potential problems of RFID interference when developing RFID applications.

Exploring nursing e-learning systems success based on information system success model.

E-learning is thought of as an innovative approach to enhance nurses' care service knowledge. Extensive research has provided rich information toward system development, courses design, and nurses' satisfaction with an e-learning system. However, a comprehensive view in understanding nursing e-learning system success is an important but less focused-on topic. The purpose of this research was to explore net benefits of nursing e-learning systems based on the updated DeLone and McLean's Information System Success Model. The study used a self-administered questionnaire to collected 208 valid nurses' responses from 21 of Taiwan's medium- and large-scale hospitals that have implemented nursing e-learning systems. The result confirms that the model is sufficient to explore the nurses' use of e-learning systems in terms of intention to use, user satisfaction, and net benefits. However, while the three exogenous quality factors (system quality, information quality, and service quality) were all found to be critical factors affecting user satisfaction, only information quality showed a direct effect on the intention to use. This study provides useful insights for evaluating nursing e-learning system qualities as well as an understanding of nurses' intentions and satisfaction related to performance benefits.

Key factors affecting healthcare professionals to adopt knowledge management: The case of infection control departments of Taiwanese hospitals.

Facing new infectious diseases that are result of continuous mutation of virus and bacteria and ever advancing communication and medical technologies, infection control professionals (ICPs) in the healthcare industry must be able to obtain instantly the needed knowledge in order to increase efficiency and effectiveness in their practice. The purpose of this study is, after an exhaustive literature review and necessary interviews with specialists in this field, to propose a research framework that explores the factors that affect the ICPs' willingness to adopt knowledge management (KM) into their tasks and to validate the usefulness of this research framework through a survey study. The research framework includes four constructs that affect infection control professionals' decision and willingness to introduce and to adopt infection control KM, and they are namely: hospital characteristics, infection control department, external environment, and project planning. The study conducted a survey among ICPs from 425 hospitals in Taiwan. A total of 227 valid questionnaire responses were returned from the ICPs from 90 hospitals. Among these responses, 55.00% are from medical centers and 47.83% are from regional hospitals. After analyzing the responses through the discriminant analysis method, the study found that "Hospital Resource Support," "Colleagues' Attitude," and "Users' Participation" are the three factors that significantly impact the professionals' willingness for adopting KM in infection control departments. This study not only provides the healthcare industry an understanding about introduction and impact of KM, which can assist in their decision making, but also emphasizes the importance of use of actual data in the study of research framework for introduction of KM in healthcare industry. Therefore, this study presents important results in both practical and academic aspects.

A study of the informatics literacy of clinical nurses in Taiwan.

The purpose of this study is to identify the essential components for informatics literacy for clinical nurses working in Taiwanese hospitals. We developed a framework to explore the critical informatics literacy factors that clinical nurses should understand to be proficient in performing their professional duties. Survey methodology was used and the participants were senior administrators of nursing and other personnel in charge of implementing nursing information systems for 84 regional hospitals and medical centers. A total of 50 valid questionnaires was returned, with a 59.5% response rate. In summary, the results of the Taiwanese study are divided into three factors: informatics knowledge, informatics skills, and computer attitudes. A total of 58 questions was used for the measurement of initial nursing informatics literacy, and 49 items were considered to be the most required informatics literacy skills specifically for clinical nurses.

The critical factors influencing the successful implementation of mobile nursing stations: a case study in Taiwan.

The purpose of this study is to conduct a comprehensive review of the factors affecting the successful implementation of Mobile Nursing Stations (MNS) by case study. A thorough validation process was used to identify the nine critical factors which influence the implementation of MNS, including the degree of peer competition, governmental and insurance policies, the Information Technology (IT) infrastructure, vendor selection, a clinical champion, top management support, task communications, user participation and training issues. The results of this study can enhance managements' understanding of the complete possibilities for the utilisation of MNS.

Factors affecting the adoption of electronic signature: Executives' perspective of hospital information department.

The healthcare industry is experiencing a major transformation towards e-healthcare, which delivers and enhances related information through the Internet among healthcare stakeholders and makes the electronic signature (e-signature) more and more important. This paper uses a mature framework, Technology-Organization-Environment (TEO), in information system discipline to identify factors that affect hospitals in adopting e-signature. A survey was conducted on regional hospitals and medical centers in Taiwan to verify the validity of the research framework. The results show that TEO framework is useful in distinguishing hospitals as adopters and non-adopters of e-signature. Based on the research findings, implications and limitations are discussed.

Establishing strategic alliance among hospitals through SAIS: a case study in Taiwan.

Due to a reformed healthcare insurance system and a gradually decreasing public affairs' budget by the government year by year, Central Taiwan Office (CTO), the Department of Health (DOH) in Taiwan, initiated a strategic alliance project of the hospitals subordinated to the DOH in November, 2001. This project was a five-year plan with an attempt to expand and develop three more strategic alliances covering the northern, southern and eastern regions of Taiwan respectively. Through a cooperative system, such an alliance allows the following: resource sharing, technique collaboration, marketing affiliations and so on. In order to decrease operation management costs and improve the quality of service at hospitals, the strategic alliance practice is supported by IS. We call this alignment the IS-enabled strategic alliance. All the IS-enabled functions are supported by the Strategic Alliance Information System (SAIS). In this article, the SAIS developed by the CTO of the DOH is introduced.

The design and evaluation of clinical decision support systems in the area of pharmacokinetics.

Gentamicin, an antibiotic drug, can be used in one-sided (unilateral) Meniere's disease to end frequent attacks of spontaneous disabling vertigo. However, with incorrect dose treatment it can profoundly damage patients' inner ear and kidney. The dosage of medication and the dosage interval will affect serum concentration that results therapeutic or damage. Pharmacokinetics is the study of managing the relationship between the dosage medication, dosing interval, and serum concentration. However, due to the complicated mathematical equations of pharmacokinetics, it is rarely used in clinics. The purpose of this study was to use a pharmacokinetics model to build a prototype of gentamicin CDSS embedded in a PDA. This system was implemented in a district teaching hospital in Chiayi area, Taiwan. Empirical data was collected under routine clinical setting with real patients and physicians to validate this CDSS. The research results showed that, considering the therapeutic effect, the pharmacokinetics-based CDSS outperforms physicians' experience. Regarding the intoxication, the pharmacokinetics-based CDSS also performed better than physicians' experience with less intoxication. The physicians using the system revealed a high degree of agreement with the perceived usefulness, perceived ease of use, and intention to use the pharmacokinetics-based CDSS.