otherwise). Agreement in diagnosis of pathologic mitral and aortic regurgitation and morphologic ... more otherwise). Agreement in diagnosis of pathologic mitral and aortic regurgitation and morphologic features of RHD were assessed. One hundred echocardiograms were re-reported blindly for intra-observer assessment. Results: 3112 reports were analysed. Based on the reference readings, distribution of cases were: 67 (33.5%) borderline RHD, 53 (26.5%) definite RHD and 80 (40%) no RHD. Overall agreement in categorising echocardiograms as normal, borderline and definite RHD (primary end-point) was good, kappa 0.68 (95%CI 0.66-0.70; SE 0.0152, p-value <0.0001). Fig 1 shows inter/intra-observer agreement, sensitivity and specificity of individual readers. Agreement for pathologic mitral regurgitation was excellent, kappa 0.87 (95%CI 0.85-0.89), Fig 2. Agreement for subtle morphologic changes of RHD was variable ranging from fair to good. Conclusion: This study demonstrates that WHF echocardiographic criteria enable good level of agreement over categorizing screening echocardiograms as normal, borderline and definite RHD. Pathologic regurgitation is very consistently and reproducibly differentiated from physiologic regurgitation by experienced cardiologists. Reproducibility for morphologic features of RHD was lower. 1. Remenyi B, Wilson N, Steer A, et al. World Heart Federation criteria for echocardiographic diagnosis of rheumatic heart diseasean evidence-based guideline. Nature Reviews Cardiology 2012;9:297-309.
This study aims to improve uptake of secondary prophylaxis among Aboriginal people with ARF/RHD, ... more This study aims to improve uptake of secondary prophylaxis among Aboriginal people with ARF/RHD, to reduce progression or worsening of RHD. Methods: This is a stepped-wedge, randomised trial in consenting communities in Australia's Northern Territory. Pairs of randomly-chosen clinics from among those consenting enter the study at three-monthly steps. The intervention to which clinics are randomised comprises a multifaceted systems-based package, in which clinics are supported to develop and implement strategies to improve penicillin delivery, aligned with elements of the Chronic Care Model. Continuous quality improvement processes will be used, including three-monthly feedback to clinic staff of adherence rates of their ARF/ RHD clients. The primary outcome is the proportion of people with ARF/RHD receiving 80% of scheduled penicillin injections over a minimum 12-month period. The sample size of 300 ARF/RHD clients across five community clusters will power the study to detect a 20% increase in proportion of individuals achieving this target, from a worrying low baseline of 20% to 40%. Secondary outcomes pertaining to other measures of adherence will be assessed. Within the randomised trial design, a mixed-methods evaluation will be embedded to evaluate the efficiency, effectiveness, impact and relevance, sustainability, process and fidelity, and performance of the intervention. The evaluation will establish any causal link between outcomes and the intervention. The planned study duration is 2013 -2016. Results: The planned study duration is 2013-2016. Results are expected by the end of 2016 Conclusion: Continuous quality improvement has a strong track record in Australia's Northern Territory, and its use resulted in modest benefits in a pilot, non-randomised ARF/ RHD study. If successful, this new intervention using the Chronic Care Model as a scaffold, evaluated using a well-developed theory-based framework, will provide a practical and transferable approach to ARF/RHD control.
Cardiovascular Topics An open-access, mobile compatible, electronic patient register for rheumatic heart disease ('eRegister') based on the World Heart Federation's framework for patient registers
Background Antipsychotic medications have limited benefits in schizophrenia, and cognitive behavi... more Background Antipsychotic medications have limited benefits in schizophrenia, and cognitive behavioral therapy may be beneficial as an adjunct. There may be potential for implementing mobile cognitive behavioral therapy–based treatment for schizophrenia in addition to standard antipsychotic medications. Objective This study aims to determine whether PEAR-004, a smartphone-based investigational digital therapeutic, improves the symptoms of an acute psychotic exacerbation of schizophrenia when it is added to standard treatments. Methods This was a 12-week, multicenter, randomized, sham-controlled, rater-blinded, parallel group proof‑of‑concept study of 112 participants with moderate acute psychotic exacerbation in schizophrenia. This study was conducted in 6 clinical trial research sites in the United States from December 2018 to September 2019. The primary outcome, change in Positive and Negative Syndrome Scale (PANSS) from baseline to week 12 or the last available visit, was analyzed...
Transforming the ego-centered internal representation of an autonomous robot with the cascaded neural network
Proceedings of 1994 IEEE International Conference on MFI '94. Multisensor Fusion and Integration for Intelligent Systems
This paper addresses the problem how the ego-centered internal representation of a robot is to be... more This paper addresses the problem how the ego-centered internal representation of a robot is to be transformed upon robot movement if the robot's environment is represented in an occupancy grid. The transformation rules are derived and it is shown that for a single change in the robot's position, the parameters of this transformation can best be estimated with Monte Carlo sampling. A neural network architecture is introduced as a computational model of the Monte Carlo estimation method, which can calculate estimates of all parameters in parallel. The cascaded neural network is an extension to this architecture, which is capable of learning the relation between the change in the robot's configuration and the parameters of the corresponding transformation of occupancy grids
Could digital technology drive clinical research in Africa?
Sub-Saharan Africa suffers roughly a quarter of the burden of global disease in terms of years of... more Sub-Saharan Africa suffers roughly a quarter of the burden of global disease in terms of years of life lost due to premature death and years lived in ill health. Yet the number of clinical trials carried out in the region is tiny. This is mainly due to the lack of clinical research capacity, but, of course, such capacity can only be built and sustained through the ongoing experience of conducting trials. It’s a classic Catch-22 situation.
Digital Therapeutics: An Integral Component of Digital Innovation in Drug Development
Clinical pharmacology and therapeutics, 2018
Digital therapeutics represent a new treatment modality in which digital systems such as smartpho... more Digital therapeutics represent a new treatment modality in which digital systems such as smartphone apps are used as regulatory-approved, prescribed therapeutic interventions to treat medical conditions. In this article we provide a critical overview of the rationale for investing in such novel modalities, including the unmet medical needs addressed by digital therapeutics and the potential for reducing current costs of medical care. We also discuss emerging pathways to regulatory approval and how innovative business models are enabling further growth in the development of digital therapeutics. We conclude by providing some recent examples of digital therapeutics that have gained regulatory approval and highlight opportunities for the near future.
The large global burden of rheumatic heart disease (RHD) has come to light in recent years follow... more The large global burden of rheumatic heart disease (RHD) has come to light in recent years following robust epidemiologic studies. As an operational research component of a broad program aimed at primary and secondary prevention of RHD, we sought to determine the current prevalence of RHD in the country's capital, Lusaka, using a modern imaging-based screening methodology. In addition, we wished to evaluate the practicality of training local radiographers in echocardiography screening methods. Echocardiography was conducted on a random sample of students in 15 schools utilizing a previously validated, abbreviated screening protocol. Through a task-shifting scheme, and in the spirit of capacity-building to enhance local diagnostic and research skills, general radiographers based at Lusaka University Teaching Hospital (UTH) were newly trained to use portable echocardiography devices. Students deemed as screen-positive were referred for comprehensive echocardiography and clinical e...
Acute rheumatic fever (ARF) and rheumatic heart disease (RHD) remain major causes of heart failur... more Acute rheumatic fever (ARF) and rheumatic heart disease (RHD) remain major causes of heart failure, stroke and death among African women and children, despite being preventable and imminently treatable. From 21 to 22 February 2015, the Social Cluster of the Africa Union Commission (AUC) hosted a consultation with RHD experts convened by the Pan-African Society of Cardiology (PASCAR) in Addis Ababa, Ethiopia, to develop a 'roadmap' of key actions that need to be taken by governments to eliminate ARF and eradicate RHD in Africa. Seven priority areas for action were adopted: (1) create prospective disease registers at sentinel sites in affected countries to measure disease burden and track progress towards the reduction of mortality by 25% by the year 2025, (2) ensure an adequate supply of high-quality benzathine penicillin for the primary and secondary prevention of ARF/RHD, (3) improve access to reproductive health services for women with RHD and other non-communicable diseas...
Rheumatic heart disease (RHD) remains a major disease burden in low-resource settings globally. P... more Rheumatic heart disease (RHD) remains a major disease burden in low-resource settings globally. Patient registers have long been recognised to be an essential instrument in RHD control and elimination programmes, yet to date rely heavily on paper-based data collection and non-networked data-management systems, which limit their functionality. To assess the feasibility and potential benefits of producing an electronic RHD patient register. We developed an eRegister based on the World Heart Federation's framework for RHD patient registers using CommCare, an open-source, cloud-based software for health programmes that supports the development of customised data capture using mobile devices. The resulting eRegistry application allows for simultaneous data collection and entry by field workers using mobile devices, and by providers using computer terminals in clinics and hospitals. Data are extracted from CommCare and are securely uploaded into a cloud-based database that matches the...
Artificial Intelligence in Real-Time Control 1992, 1993
The paper describes a self-learning control system for a mobile robot. Based on sensor informatio... more The paper describes a self-learning control system for a mobile robot. Based on sensor information the control system has to provide a steering signal in such a way that collisions are avoided. Since in our case no 'examples' are available, the system learns on the basis of an external reinforcement signal which is negative in case of a collision and zero otherwise. We describe the adaptive algorithm which is used for a discrete coding of the state space, and the adaptive algorithm for learning the correct mapping from the input (state) vector to the output (steering) signal.
1996 IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems (Cat. No.96TH8242)
I n this paper we consider the conversion of sensor data to a probabilistic representation of the... more I n this paper we consider the conversion of sensor data to a probabilistic representation of the environment (occupancy grid). W e introduce a neural network which learns these conversions. The conversion of sensor data remains adaptive to changes in either the sensor or its environment. To place this work in a broader context we describe the architecture of our Sensor Data Fusion system in which these conversions are applied. W e also introduce the PDOP: a rule for fusing occupancy grids in this system.
How informatics can potentiate precompetitive open-source collaboration to jump-start drug discovery and development
Clinical pharmacology and therapeutics, 2010
... The largest issuesintellectual property and publication rightsmust be dealt with upfront an... more ... The largest issuesintellectual property and publication rightsmust be dealt with upfront and with transparency. ... Rosenthal, A., Mork, P., Li, MH, Stanford, J., Koester, D. & Reynolds, P. Cloudcomputing: a new business paradigm for biomedical information sharing. ...
Very high levels of adherence are required for ART to be effective. There is limited information ... more Very high levels of adherence are required for ART to be effective. There is limited information available from India on adherence to ART and its predictors. We carried out this study to examine adherence levels and to explore the factors associated with adherence among PLHA receiving ART in India. Using a cross-sectional study design 310 HIV+ patients receiving ART (252 paying out-of-pocket; 58 free via employee-insurance programme) were interviewed from Pune and Delhi health facilities, using a semi-structural questionnaire. The median age for patients was 36 yr. The median time from diagnosis of HIV-infection was 34.5 months, median time on ART was 16 months and median CD4 cell count at start of ART was 110 cells/microl. 98 per cent of the respondents were using a non protease inhibitor (PI) treatment regimen. Mean 4-day adherence was 93 per cent. Adherence was lower over longer periods of recall: 20 per cent reported missed does over the past 7 days; 33 per cent reported ever mi...
A review is given on the use of neural networks for mobile robots and autonomous vehicles. We foc... more A review is given on the use of neural networks for mobile robots and autonomous vehicles. We focus on neural methods for navigation, making a distinction between sensorbased `reactive' navigation and planned navigation methods.
Neural network applications in sensor fusion for an autonomous mobile robot
Lecture Notes in Computer Science, 1996
this article, we identify the problems with traditional conversion methods and we introduce a neu... more this article, we identify the problems with traditional conversion methods and we introduce a neural network whichleatin how to convert such measurements
Uploads
Papers by Joris Van Dam