Repeated sclerotherapy eradicates esophageal varices in most alcoholic cirrhotic patients with a reduction in rebleeding. Despite control of variceal bleeding, survival at 5 years was only 26% because of death due to liver failure in most patients.

SummaryBackground: Clinical and research data are essential for patient care, research and healthcare system planning. REDCapTM is a web-based tool for research data curatorship developed at Vanderbilt University in Nashville, USA. The Faculty of Health Sciences at the University of the Witwatersrand, Johannesburg South Africa identified the need for a cost effective data management instrument. REDCap was installed as per the user agreement with Vanderbilt University in August 2012. Objectives: In order to assist other institutions that may lack the in-house Information Technology capacity, this paper describes the installation and support of REDCap and incorporates an analysis of user uptake over the first year of use. Methods: We reviewed the staffing requirements, costs of installation, process of installation and necessary infrastructure and end-user requests following the introduction of REDCap at Wits. The University Legal Office and Human Research Ethics Committee were consulted regarding the REDCap end-user agreement. Bi-monthly user meetings resulted in a training workshop in August 2013. We compared our REDCap software user numbers and records before and after the first training workshop. Results: Human resources were recruited from existing staff. Installation costs were limited to servers and security certificates. The total costs to provide a functional REDCap platform was less than $9000. Eighty-one (81) users were registered in the first year. After the first training workshop the user numbers increased by 59 in one month and the total number of active users to 140 by the end of August 2013. Custom software applications for REDCap were created by collaboration between clinicians and software developers. Conclusion: REDCap was installed and maintained at limited cost. A small number of people with defined skills can support multiple REDCap users in two to four hours a week. End user training increased in the number of users, number of projects created and the number of projects moved to production.

Background Electronic data capture (EDC) in academic health care organizations provides an opportunity for the management, aggregation, and secondary use of research and clinical data. It is especially important in resource-constrained environments such as the South African public health care sector, where paper records are still the main form of clinical record keeping. Objective The aim of this study was to describe the strategies followed by the University of the Witwatersrand Faculty of Health Sciences (Wits FHS) during the period from 2013 to 2021 to overcome resistance to, and encourage the adoption of, the REDCap (Research Electronic Data Capture; Vanderbilt University) system by academic and clinical staff. REDCap has found wide use in varying domains, including clinical studies and research projects as well as administrative, financial, and human resource applications. Given REDCap’s global footprint in >5000 institutions worldwide and potential for future growth, the strategies followed by the Wits FHS to support users and encourage adoption may be of importance to others using the system, particularly in resource-constrained settings. Methods The strategies to support users and encourage adoption included top-down organizational support; secure and reliable application, hosting infrastructure, and systems administration; an enabling and accessible REDCap support team; regular hands-on training workshops covering REDCap project setup and data collection instrument design techniques; annual local symposia to promote networking and awareness of all the latest software features and best practices for using them; participation in REDCap Consortium activities; and regular and ongoing mentorship from members of the Vanderbilt University Medical Center. Results During the period from 2013 to 2021, the use of the REDCap EDC system by individuals at the Wits FHS increased, respectively, from 129 active user accounts to 3447 active user accounts. The number of REDCap projects increased from 149 in 2013 to 12,865 in 2021. REDCap at Wits also supported various publications and research outputs, including journal articles and postgraduate monographs. As of 2020, a total of 233 journal articles and 87 postgraduate monographs acknowledged the use of the Wits REDCap system. Conclusions By providing reliable infrastructure and accessible support resources, we were able to successfully implement and grow the REDCap EDC system at the Wits FHS and its associated academic medical centers. We believe that the increase in the use of REDCap was driven by offering a dependable, secure service with a strong end-user training and support model. This model may be applied by other academic and health care organizations in resource-constrained environments planning to implement EDC technology.

Data-Driven Healthcare, IBM Research Africa, Johannesburg, South Africa The National Cancer Registry (NCR) in South Africa plays a significant role in reporting nationwide cancer statistics and raising the global awareness of the massive impact of cancer. The government requires confirmed cancer cases to be reported to the NCR. Due to manual processes and the increasing magnitude of reports received annually, a considerable lag time exists in cancer statistics, which means the extent of the cancer cases is currently not understood. In addition, the unstructured free-text also needs to be processed in order to identify clinical information that could be important for public health planning. We present initial results from a deep learning approach to address this time lag. Deep learning is a powerful machine-learning algorithm that has made strides in the area of medical image recognition and speech processing. The deep learning system takes as input 2000 de-identified breast cancer pathology reports provided by the NCR in collaboration with the University of Witwatersrand Medical School. The pathology reports are first preprocessed using the Tf-idf (term frequency-inverse document frequency) method, which suggests how important a word is to a document in a corpus by assigning a numerical statistic to each word and hence obtain a term frequency document matrix. The high dimensional data matrix is, input into an unsupervised learning autoencoder, a data compression algorithm used to attain rich features that best represents the specific breast cancer topography and morphology. Unlike other approaches, our approach relies on non-dictionary sources such as clinical empirical knowledge extracted from the reports and dictionary sources such as the 12,000 medical diagnoses available in the International Statistical Classification of Diseases and Related Health Problems (ICD-10). The output from the deep learning system can be used to automate the classification of reports into their corresponding topography and morphology. The system could also be used to create a visual analytics system to aid data exploration and trend analysis of the current state of cancer in South Africa. Citation Format: Waheeda Banu Saib, Pavan Kumar, Geoffrey Siwo, Gciniwe Dlamini, Elvira Singh, Sue Candy, Michael Klipin. A deep learning approach for extracting clinically relevant information from pathology reports [abstract]. In: Proceedings of the AACR International Conference: New Frontiers in Cancer Research; 2017 Jan 18-22; Cape Town, South Africa. Philadelphia (PA): AACR; Cancer Res 2017;77(22 Suppl):Abstract nr A11.