Start Your Search
Raza Abidi
Author of
-
OS08 - Future Priorities in Digital Health (ID 8)
- Event: e-Health 2017 Virtual Meeting
- Type: Oral Session
- Track: Clinical and Executive
- Presentations: 1
- Coordinates: 6/05/2017, 04:00 PM - 05:30 PM, Room 205CD
-
OS08.01 - Educating Nurses and Midwives Through eHealth Technologies: Potentials and Limitations (ID 248)
- Abstract
Purpose/Objectives: Continuous education and professional development of health care professionals (HCPs) through digital media (eLearning) is now quite popular. eLearning helps overcomes the traditional barriers faced by health professionals, especially those working in challenging contexts, to access specialized training opportunities offered by subject specialists. Aga Khan Development Network has developed and implemented an eLearning based continuous clinical education program that is currently operational and offers online educational and skill development programs to HCP working in Maternal, Neonatal and Child Health (MNCH) settings of various health facilities in Afghanistan and Tajikistan. To evaluate the efficacy of the program in terms of improvement in knowledge leading to improvement in the clinical practices of HCPs, a research study is also being conducted.
Methodology/Approach: From June to September 2016, seven online continuing education sessions were offered to the nurses and midwives at Bamyan, Faizabad and Mirwais Provincial Hospitals, and Khorog Oblast General Hospital. The topics for the session were finalized keeping in view the local needs of the HCPs. Topics for the sessions were: family planning, antenatal care, postnatal care, pre-eclampsia and eclampsia, post-partum hemorrhage, birth asphyxia and respiratory distress syndrome. The sessions were designed and offered by the Aga Khan University School of Nursing and Midwifery in Karachi. The sessions were of two hours each. In each session, participants took a pre-test and a post-test. These tests were administered through a mobile app, which was developed specifically for this purpose. The sessions were conducted in Dari. However, at each site a translator was present who translated the content in the local language. The sessions were delivered through a live video communication tool called Zoom. The support team in Karachi monitored the pre/post tests and the session using Zoom.
Finding/Results: After seeking informed consent, fifty participants were recruited for the study. These included nurses and midwives working in MNCH clinical areas at the four research sites. With each online session, the change in level of knowledge of the participants has been assessed through pre- and post-tests which shows 20% increase in session 1, 16% increase in session 2, no change in session 3, 12% increase in session 4, 3% increase in session 5, 17% increase in session 6 and 22% increase in session 7. The retention of knowledge will be measured by administering a comprehensive delayed post-test, which is scheduled after six-weeks of the last eLearning session.
Conclusion/Implication/Recommendations: The online education program currently being implemented is the first of its kind in Afghanistan and Tajikistan. Therefore, there are challenges associated with connectivity, language and preparedness of the local staff in each location to offer such programs. However, the initial results have indicated that online sessions have immense potential to improve the quality of care in challenging contexts such as Afghanistan and Tajikistan by enabling nurses and midwives to access up to date knowledge.
140 Character Summary: To assess the efficacy of an online education program in improving knowledge and clinical practices of HCPs working in Afghanistan and Tajikistan
-
OS10 - Disease and Clinical Management with Technology (ID 16)
- Event: e-Health 2017 Virtual Meeting
- Type: Oral Session
- Track: Clinical and Executive
- Presentations: 1
- Coordinates: 6/06/2017, 10:30 AM - 12:00 PM, Room 205B
-
OS10.02 - Digital Health Based Ambient Assisted Living to Improve Medication Adherence (ID 177)
- Abstract
Purpose/Objectives: Patient-centerd healthcare involves strategies to engage and motivate patients to self-manage their health conditions in home-based settings. Medication adherence is an important aspect in disease self-management since sub-optimal medication adherence leads to ineffectiveness of the therapy and discomfort for the patient. In order to overcome the limitations of self-reported medication adherence, our objective is to use ambient assistive living (AAL) technologies in smart environments to monitor, remind and motivate patients to adhere to their therapy plans. Our intent is to exploit sensor technologies and consumer health devices to remotely monitor and collect self-management related information, infer adherence through activity recognition, and send personalized reminders and motivational messages based on the observed patients behaviour to help them improve medication adherence. We present an AAL framework that monitor activities related to medication adherence.
Methodology/Approach: We take a data analytics and AAL approach that entails: (a) data collection for activities related to medication adherence; (b) patients high-level activity model generation based on their activity data; (c) recognition of medication related activities state based on the collected patient data and high-level activity models, and (d) contextual message generation from the activity recognition results. Medication adherence is monitored from a smart pillbox (Bluetooth Low Energy) that send events (accelerometer, reed switch on pill compartments lid) to a smartphone, and from smart home sensors that include: passive infrared sensors to detect motions in specific zones, reed switches on doors and radio-frequency identification tags on objects to detect when objects (e.g. cup or glass) are used by the patient, and (c) flow meter sensors to detect when the patient uses water tap in order to get drinkable water. Smartphone and smart home services allow to obtain contextual information about the patient and medication adherences activities from the collected data: localization service (patients current location) and action recognition (e.g. opening pillbox, opening door).
Finding/Results: We implemented our AAL based medication adherence system, comprising a sensor infrastrure for data collection and a mobile health app for patients to receive messages. We evaluated system performance for three activities related to medication adherence as performed by different individuals. The Taking medication activity is carried out when the patient takes pills from the pillbox (Take pills sub-activity), then gets a cup of water (Get water sub-activity), and finally swallows the pills. The activities were validated with 780 scenarios of activity realisation with six uncertainty levels (from certain observation to complete ignorance about the observation value). Our system is able to recognize the patients activity in these scenarios with 79% accuracy. When the system is enabled to predict the most plausible patients activity then the systems accuracy is around 98%.
Conclusion/Implication/Recommendations: Ubiquitous and pervasive solutions to ensure patients adhere to their medication are challenging, yet important to improve therapy outcomes and reduce healthcare costs. We have presented an innovative digital health application to remotely monitor patients for specific activities and send them timely reminders and messages to help improve medication adherence and behaviour modification. Our framework extend to other self-manageent activities pertaining to chonic disease management
140 Character Summary: Remote patient monitoring and motivational messaging to improve medication adherence using ambient assisted livign technologies
-
OS29 - Realizing the Promise of "Big" Data (ID 34)
- Event: e-Health 2017 Virtual Meeting
- Type: Oral Session
- Track: Clinical and Executive
- Presentations: 1
- Coordinates: 6/07/2017, 10:30 AM - 12:00 PM, Room 203CD
-
OS29.02 - Pathology Laboratory Utilization Scorecards (PLUS): A Pathology Data Analytics Platform (ID 170)
- Abstract
Purpose/Objectives: Pathology laboratories provide service to both primary-care and tertiary care providers, helping with disease diagnosis and therapeutic choices. Typically, physicians request a pathology test order which may contain multiple tests; the operational question is whether these tests are relevant and useful with respect to the patients profile. As service demands on pathology laboratories is increasing, there is a realization to streamline the operations with respect to clinical guidelines and local clinical workflows in order to optimize operational costs whilst improving order relevancy and result accuracy. The optimization of pathology laboratory utilization is approached by detecting superfluous (clinically irrelevant, unnecessary, repetitive) lab orders, predicting lab utilization for specific tests, resource planning in response to test volumes, educating physicians about clinical guidelines around test ordering and result interpretation. In this project, our objectives are: (1) To develop and deploy a Pathology Laboratory Utilization Scorecards (PLUS) platform that offers end-to-end pathology big data analytics services to optimize laboratory utilization; (2) To provide primary care physicians personalized laboratory utilization scorecards to visualize their test ordering pattern and adjust their test orders accordingly; (3) To provide pathology laboratory managers a live dashboard showing the volume and type of orders to assist them with resource planning; and (4) To generate meaningful order-sets to improve test ordering patterns and guideline compliance.
Methodology/Approach: Pathology laboratories generate large volumes of clinical data that can be analyzed to monitor, manage and optimize laboratory utilization. We take a big data analytics approach to develop the PLUS platform that hosts a suite of health data analytics tools/applications to (i) standardize pathology data using SNOMED-CT; (ii) integrate pathology data from multiple health information systems (such as ADT, EDS, EMR); (iii) link non-health data sources such as geo-location data and environmental data; and (iv) visualize and interact with analytical results to gain specialized insights. We have applied machine learning and statistical methods to develop specialized physician order profile comparison models to stratify physicians with respect to their patient demographics and their conditions, thus ensuring that inter-physician comparisons are adjusted by patient population they treat as opposed to just order volumes.
Finding/Results: PLUS is web-based system that is currently deployed in Nova Scotia and is used to optimize the pathology laboratory in the central zone (Halifax) that annually performs on average 15 million laboratory tests for 200,000 patients. We provide web-accessible lab utilization scorecards for (a) primary care physicians to highlight their ordering profile in terms of volume of lab test orders with abnormal rates, repetition rates, yearly comparison and comparison to their peers; and (b) lab managers to illustrate the volume, type and location (on a map) of orders, and gross prediction of the orders for chronic patients and seasonal diseases.
Conclusion/Implication/Recommendations: We demonstrate a big pathology data analytics platform to optimize pathology lab utilization. The project involves primary care physicians as users. PLUS is expected to significantly optimize lab utilization by reducing the rate of unnecessary orders, and by offering live operational intelligence to pathology lab managers. The approach can be extended to otehr provinces.
140 Character Summary: A big health data analytics platform, using advance analytics methods, to analyze pathology lab data in order to optimize pathology lab utilization