Through the development of a dashboard with participative methodology we present a centralized strategy to analyze and visualize EMRs data for the management of 15 public hospitals from Buenos Aires City. This approach could constitute an efficient option for public health systems from developing countries.
Although a proportion of families and communities in low resource settings continue to provide care to loved ones with autism spectrum conditions, many of the affected persons remain undiagnosed and without access to proven therapies due to high treatment cost and cultural pressures, in particular. Use of conversational agents on mobile phones in combination with behavior activation home care may provide an innovative, culturally appropriate and affordable platform for strengthening behavior and social functioning outcomes, in addition to an opportunity for participation of the persons with autism spectrum conditions in the intervention development process. We aim to assess the effectiveness of an intervention that incorporates artificial intelligence conversational agent technologies and behavioral activation therapy techniques.
Mohamed Ben Said, Laurence Robel, Pauline Chaste, Didier Perisse, Marie-Joelle Oreve, Pascale Zylberberg, Anne Philippe, Catherine Jousselme, Stéphanie Lacoste, Mario Speranza, Ines Hafsa, Fatouma Cisse, Zoubair Cherqaoui, Jean-Philippe Jais
1401 - 1402
TEDIS, an information system dedicated to patients affected with neuro-developmental disorders including autism, focuses on patient data generated during in-depth clinical assessment in nine expert centers in Ile-de-France region. Long term partnership involving methodologists and domain experts is necessary to support quality data production and analyses and to guarantee quality data and information governance in a domain characterized by frequent evolutions in clinical assessment instruments and in diagnostic criteria and classification.
Valentina Lichtner, Mirela Prgomet, Bryony Dean Franklin, Johanna I. Westbrook
1405 - 1406
Automated dispensing cabinets in clinical wards may contribute to improving safety by reducing the likelihood of medications not being available when needed. However, achieving this safety benefit is dependent on a ‘back office’ sociotechnical infrastructure that combines semi-automated processes with mindful, resilient work practices.
Kampol Khemthong, Niruwan Turnbull, Savittri Rattanopad Suwanlee, Karl Peltzer
1407 - 1408
Noncommunicable diseases (NCDs) were caused by risk factors also rising rapidly and killed more people. This study aimed to explore and determine the prevalence and distribution of alcohol and tobacco use as NCDs’s risk factors. We used a cross-sectional survey on Health dataset between October 2013 and April 2017 of people who were 13 years old and older. This study was investigated included demographics, alcohol consumption and tobacco use. This study found risk of NCDs 49.07%, The majority of risk factor were men (50.2 %), age_group were 40–59 years old(24.4%), The most were men having diabetes mellitus family (43.0%), hypertension family (17.9 %), alcohol consumption (26.9%), tobacco use (19.0%), most of the women were high blood pressure (23.0%), high blood sugar level (33.3%), overweight and obesity (23.4%), waist was over (22.5%) and high total cholesterol (21.4%), alcohol consumption among the gender 37.8%, most were male (26.9%), age_group mostly 45-59 years old (19.3 %), married (23.1%), agricultural (29.7%), primary school (29.7%). The prevalence of risk factors, most risk factors was tobacco use in men (18.9%), OR 16.789, (95%CI, p-value</001), alcohol consumption were men (26.9%), OR 3.934 (95%CI, p-value<.001).
Samson W. Tu, Csongor I. Nyulas, Tania Tudorache, Mark A. Musen, Andrea Martinuzzi, Coen van Gool, Vincenzo della Mea, Christopher G. Chute, Lucilla Frattura, Nick Hardiker, Huib ten Napel, Richard Madden, Ann-Helene Almborg, Jeewani Anupama Ginige, Catherine Sykes, Can Cekik, Robert Jakob
1409 - 1410
An overarching WHO-FIC Content Model will allow uniform modeling of classifications in the WHO Family of International Classifications (WHO-FIC) and promote their joint use. We provide an initial conceptualization of such a model.
A unified and integrated approach to represent mHealth apps and their characteristics is currently lacking. To fill this gap, the overall purpose of this project is to develop an ontology, to help address the objective of building ‘trustful’ mHealth apps. This paper is a brief presentation of the followed methods, and the preliminary results of the research, i.e. a first version of that ontology.
Morten Hasselstrøm Jensen, Simon Cichosz, Ole Hejlesen, Irl.B. Hirsch, Peter Vestergaard
1413 - 1414
In this study, we investigated which predictors from people with type 1 diabetes at initiation of intensive treatment that increase the risk of not achieving glycemic target. Data from a clinical trial with type 1 diabetes people (n=460) were used in a logistic regression model to analyze the effect of the predictors on achievement of glycemic target. Results indicate that age, smoking, glycated hemoglobin, 1,5-anhydroglucitol and fluctuation from continuous glucose monitoring are predictors of achievement of glycemic target, which can be used in an algorithm to predict people who fail to achieve glycemic target.
openEHR and FHIR are two competing clinical data modeling and data exchange standards, that are commonly seen as mostly incompatible. However, the two have quite much in common and bridging approaches between the two worlds can serve the benefit of both communities. In the presented work, the data models of openEHR are translated into FHIR data models.
The user interface of a mechanical ventilator is safety critical, as use errors can lead to patient harm. A systematic review was conducted to identify published usability issues and contributing factors that can lead to use errors. The findings were grouped in an Ishikawa diagram. Many of the problems mentioned based on inconsistent labeling and manufacturer-specific naming of ventilation modes. In the studies, usability was often measured quantitatively and did not allow any conclusions to be drawn about concrete problems.
In medical emergency situations, the language barrier is often a problem for healthcare quality. To face this situation, we developed BabelDr, an innovative and reliable fixed phrase speech-enabled translator specialised for medical language. Majority of participants (>85%) showed a positive satisfaction level using BabelDr.
Marie-Pierre Gagnon, Mame-Awa Ndiaye, Alain Larouche, Guylaine Chabot, Christian Chabot, Ronald Buyl, Jean-Paul Fortin, Anik Giguère, Annie Leblanc, France Légaré, Aude Motulsky, Claude Sicotte, Holly O. Witteman, Éric Kavanagh, Frédéric Lépinay, Jacynthe Roberge, Hina Hakim, Myriam Brunet-Gauthier, Carole Délétroz, Samira A. Rahimi, Jack Tchuente, Maxime Sasseville
1423 - 1424
Multimorbidity increases care needs among people with chronic diseases. In order to support communication between patients, their informal caregivers and their healthcare teams, we developed CONCERTO+, a patient portal for chronic disease management in primary care. A user-centered design comprising 3 iterations with patients and informal caregivers was performed. Clinicians were also invited to provide feedback on the feasibility of the solution. Several improvements were brought to CONCERTO+, and it is now ready to be implemented in real-life setting.
Emergency Department (ED) overcrowding is a major global healthcare issue. In this paper, we used Long Short-Term Memory (LSTM) recurrent neural networks to build a model to predict ED wait time in the next 2 hours using a randomly generated patient timestamp dataset of a typical patient hospital journey. Compared with Linear Regression model, the average mean absolute error for the LSTM model is decreased by 15% (3 minutes) (p<0.001). The LSTM model statistically outperforms the LR model, however, both models could be practically useful in ED wait time prediction.