Thesis (M.H.A.)--University of Michigan, 1974.

Thesis (M.H.A.)--University of Michigan, 1965.

Thesis (M.H.A.)--University of Michigan, 1974.

Thesis (Ph. D.)--University of Hong Kong, 1998. / Includes bibliographical references (leaves 347-365).

Magister Commercii (Information Management) - MCom(IM) / Health information systems (HIS) have much to offer in managing healthcare costs and in improving the quality of care for patients. However, the adoption of HIS can cause problems to health professionals in terms of efficiency as well as to the entire health organization in terms of acceptability and adaptability. The development of a national Information and Communication Technology (ICT) policy in Zambia was initiated in 2001 through an extensive consultation process which involved academics and civil society organizations. The aim of using ICT is to improve the quality of health service delivery at local levels. Maramba and Mahatma Gandhi Clinics are the largest primary health care (PHC) clinics in Livingstone and have been prioritized for the implementation of an electronic medical record (EMR) system. The current study explored health care workers' perceptions and experiences of the use of ICTbased EMR and factors that could determine acceptability of EMR at Maramba and Mahatma Gandhi clinics to feed into future program improvement.

A Personal Health Record (PHR) is an electronic record of a patient’s health-related information that is managed by the patient. The patient can give access to other parties, such as healthcare providers and family members, as they see fit. These parties can use the information in emergency situations, in order to help improve the patient’s healthcare. PHRs have an important role to play in ensuring that a patient’s complete health history is available to his healthcare providers at the point of care. This is especially true in South Africa, where the majority of healthcare organizations still rely on paper-based methods of record-keeping. Research indicates that physicians play an important role in encouraging the adoption of PHRs amongst patients. Whilst various studies have focused on the perceptions of South African citizens towards PHRs, to date no research has focused on the perceptions of South African physicians. Considering the importance of physicians in encouraging the adoption of PHRs, the problem being addressed by this research project thus relates to the lack of information relating to the perceptions of South African physicians of PHRs. Physicians with private practices at private hospitals in Port Elizabeth, South Africa were surveyed in order to determine their perceptions towards PHRs. Results indicate perceptions regarding benefits to the physician and the patient, as well as concerns to the physician and the patient. The levels of trust in various potential PHR providers and the potential uses of a PHR for the physician were also explored. The results of the survey were compared with the results of relevant international literature in order to describe the perceptions of physicians towards PHRs.

Η πραγματικότητα είναι ότι στη σημερινή εποχή τα Δημόσια Νοσοκομεία αντιμετωπίζουν σοβαρά προβλήματα διαχείρισης και εκσυγχρονισμού των παρεχόμενων υπηρεσιών υγείας με κύριο αποτέλεσμα την αναποτελεσματικότητα της λειτουργίας τους και δυστυχώς το χαμηλό βαθμό ικανοποίησης των πολιτών. Ο πολίτης που καταφεύγει σε ένα Δημόσιο Νοσοκομείο ζητώντας την απαραίτητη υγειονομική φροντίδα και περίθαλψη δηλώνει σιωπηρά την εμπιστοσύνη του στις υπηρεσίες παροχής υγείας, καθώς και την αποδοχή του στο σύστημα της Δημόσιας Διοίκησης. Το σύστημα όμως δημιουργεί παραλείψεις, καθυστερήσεις, χαοτική γραφειοκρατία και υπέρογκες χρηματικές και μη-επιβαρύνσεις που έχουν σαν αποτέλεσμα τη χαμηλή απόδοση παραγωγής υπηρεσιών υγείας και την άναρχη λειτουργία του ιδιωτικού τομέα. Στην παρούσα διπλωματική εργασία θα μελετήσουμε τις αιτίες των προβλημάτων αυτών καθώς και τον Ιατρικό Φάκελο μέσα από τη σκοπιά της Πληροφορικής και λιγότερο της Οικονομίας. Όπως γνωρίζουμε τα τελευταία χρόνια η ανάπτυξη της τεχνολογίας έχει επιβάλλει μια διαφορετική παρουσίαση και οργάνωση της πληροφορίας. Ολοένα και περισσότερα εργαλεία δημιουργούνται ώστε να εξυπηρετήσουν τις ανάγκες για διαχείριση και διάθεση πληροφοριών. Οι εξελίξεις, τα συμπεράσματα καθώς και οι προβληματισμοί που αφορούν τον ηλεκτρονικό φάκελο υγείας αποτελούν και τον επίλογο της παρούσης διπλωματικής εργασίας. / The reality is that in today's era public hospitals are facing serious problems of management and modernization of health services with primary outcome inefficiency of operation and unfortunately the low degree of satisfaction. The citizen who resorts to a Public Hospital seeking necessary health care and care implicitly declares its confidence in the health services and the acceptance of the system of public administration. But the system creates omissions, delays, chaotic bureaucracy and excessive monetary and non-charges have resulted in a low yield health services and the uncontrolled operation of the private sector. In this particular paper we will study the causes of these problems and the medical records through the perspective of IT and less of the economy. As we know in recent years the development of technology has imposed a different presentation and organization of information. More and more tools are created to serve the needs for management and disposal information. These developments, findings and concerns relating to electronic health records is also the epilogue of this paper.

published_or_final_version / Community Medicine / Master / Master of Public Health

The theme of this dissertation focuses on methods for estimating personalized treatment using machine learning algorithms leveraging information from electronic health records (EHRs). Current guidelines for medical decision making largely rely on data from randomized controlled trials (RCTs) studying average treatment effects. However, RCTs are usually conducted under specific inclusion/exclusion criteria, they may be inadequate to make individualized treatment decisions in real-world settings. Large-scale EHR provides opportunities to fulfill the goals of personalized medicine and learn individualized treatment rules (ITRs) depending on patient-specific characteristics from real-world patient data. On the other hand, since patients' electronic health records (EHRs) document treatment prescriptions in the real world, transferring information in EHRs to RCTs, if done appropriately, could potentially improve the performance of ITRs, in terms of precision and generalizability. Furthermore, EHR data domain usually consists text notes or similar structures, thus topic modeling techniques can be adapted to engineer features. In the first part of this work, we address challenges with EHRs and propose a machine learning approach based on matching techniques (referred as M-learning) to estimate optimal ITRs from EHRs. This new learning method performs matching method instead of inverse probability weighting as commonly used in many existing methods for estimating ITRs to more accurately assess individuals' treatment responses to alternative treatments and alleviate confounding. Matching-based value functions are proposed to compare matched pairs under a unified framework, where various types of outcomes for measuring treatment response (including continuous, ordinal, and discrete outcomes) can easily be accommodated. We establish the Fisher consistency and convergence rate of M-learning. Through extensive simulation studies, we show that M-learning outperforms existing methods when propensity scores are misspecified or when unmeasured confounders are present in certain scenarios. In the end of this part, we apply M-learning to estimate optimal personalized second-line treatments for type 2 diabetes patients to achieve better glycemic control or reduce major complications using EHRs from New York Presbyterian Hospital (NYPH). In the second part, we propose a new domain adaptation method to learn ITRs in by incorporating information from EHRs. Unless assuming no unmeasured confounding in EHRs, we cannot directly learn the optimal ITR from the combined EHR and RCT data. Instead, we first pre-train “super" features from EHRs that summarize physicians' treatment decisions and patients' observed benefits in the real world, which are likely to be informative of the optimal ITRs. We then augment the feature space of the RCT and learn the optimal ITRs stratifying by these features using RCT patients only. We adopt Q-learning and a modified matched-learning algorithm for estimation. We present theoretical justifications and conduct simulation studies to demonstrate the performance of our proposed method. Finally, we apply our method to transfer information learned from EHRs of type 2 diabetes (T2D) patients to improve learning individualized insulin therapies from an RCT. In the last part of this work, we report M-learning proposed in the first part to learn ITRs using interpretable features extracted from EHR documentation of medications and ICD diagnoses codes. We use a latent Dirichlet allocation (LDA) model to extract latent topics and weights as features for learning ITRs. Our method achieves confounding reduction in observational studies through matching treated and untreated individuals and improves treatment optimization by augmenting feature space with clinically meaningful LDA-based features. We apply the method to extract LDA-based features in EHR data collected at NYPH clinical data warehouse in studying optimal second-line treatment for T2D patients. We use cross validation to show that ITRs outperforms uniform treatment strategies (i.e., assigning insulin or another class of oral organic compounds to all individuals), and including topic modeling features leads to more reduction of post-treatment complications.

This dissertation aims to examine the collection and use of digital patient-generated health data (PGHD) in real-world settings, including existing barriers from the perspectives of patients and healthcare providers, and possible approaches to optimizing the process. In Chapter One, the potential of PGHD to improve health and wellness, particularly for individuals with chronic conditions, as well as known barriers to PGHD collection and use, are described. One chronic condition in particular, atrial fibrillation (AF), is then introduced as a use case for PGHD. Chapter Two contains an integrative review synthesizing findings from eleven studies reporting patients’ and providers’ needs when collecting and using PGHD, and identifying convergence and divergence between needs. Chapter Three contains a quantitative evaluation of sustained engagement, currently a major barrier to collection of PGHD, in a group of adults self-monitoring AF, as well as predictors and moderators of engagement that come from an adapted version of the Unified Theory of Acceptance and Use of Technology (UTAUT). These individuals were previously enrolled in the randomized, controlled trial, the iPhone® Helping Evaluate Atrial Fibrillation Rhythm through Technology (iHEART). In Chapter Four, the adapted UTAUT model is explored in more detail through a qualitative investigation of sustained engagement with patients, healthcare providers, and research coordinators involved in the iHEART trial. Chapter Five summarizes the findings of this dissertation, including strengths and limitations, and elicits implications for the intersection of health policy and clinical practice, design, nursing, and future research from the findings.