Designing a mHealth clinical decision support system for Parkinson’s disease: a theoretically grounded user needs approach

Timotijević, Lada; Hodgkins, Charo; Banks, Adrian P.; Rusconi, Patrice; Egan, Bernadette; Peacock, Matthew; Seiss, Ellen; Touray, Morro; Gage, Heather; Pellicano, Clelia; Spalletta, Gianfranco; Assogna, Francesca; Giglio, Manuela; Marcante, Andrea; Gentile, Giovanni; Cikajlo, Imre; Gatsios, Dimitrios; Konitsiotis, Spiros; Fotiadis, Dimitrios I.

doi:10.1186/s12911-020-1027-1

Cited by 26 publications

(32 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The behavioral features involved in the decision-making process, i.e. how a recommender system may influence physician’s decision making [ 24 ], and how this technology could have a positive impact on patient’s care and better economic management is a problem that not only depends on the technical implementation and the AI component but also on the final user’s interface. For instance, in a recent investigation, it has been shown that , when designed well, recommender systems that incorporate treatment costs can result in significant cost savings, while providing similar or better health outcomes.…”

Section: Discussionmentioning

confidence: 99%

Medical recommender systems based on continuous-valued logic and multi-criteria decision operators, using interpretable neural networks

Ochoa¹,

Csiszár

Schimper³

2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Out of the pressure of Digital Transformation, the major industrial domains are using advanced and efficient digital technologies to implement processes that are applied on a daily basis. Unfortunately, this still does not happen in the same way in the medical domain. For this reason, doctors usually do not have the time or knowledge to evaluate all alternative treatment options for each patient accurately and individually. However, physicians can reduce their workload by using recommender systems, still having every decision under control. In this way, they also get an insight into how other physicians make treatment decisions in each situation. In this work, we report the development of a novel recommender system that uses predicted outcomes based on continuous-valued logic and multi-criteria decision operators. The advantage of this methodology is that it is transparent, since the model outcomes emulate logical decision processes based on the hierarchy of relevant physiological parameters, and second, it is safer against adversarial attacks than conventional deep learning methods since it drastically reduces the number of trainable parameters. Methods We test our methodology in a patient population with diabetes and heart insufficiency that becomes a therapy (beta-blockers, ACE or Aspirin). The original database (Pakistan database) is publicly available and accessible via the internet. However, to explore methods to protect the patient's identity and guarantee data privacy we implemented a methodology on a variable-by-variable basis by fitting a sequence of regression models and drawing synthetic values from the corresponding predictive distributions using linear regressions and norm rank. Furthermore, we implemented a deep-learning model based on logical gates modeled by perceptrons with fixed weights and biases. While a first trainable layer automatically recognizes a meaningful parameter hierarchy, the implemented Logic-Operator Neuronal Network (LONN) simulates cognitive processes like a rational, logical thinking process, considering that this logic is joined by fuzziness, i.e., logical operations are not exact but essentially fuzzy due to the implemented continuous-valued operators. The predicted outcomes of the model (kind of therapy-ACE, Aspirin or beta-blocker- and expected therapy time of the patient) are then implemented in a recommender system that compares two different models: model 1 trained on a population excluding negative outcomes (patient group 1, with no patient dead and long therapy times) and a model 2 trained on the whole patient population (patient group 2). In this way, we provide a recommendation of the best possible therapy based on the outcome of the model and the confidence of this recommendation when the outcome of model 1 is compared with the outcome of model 2. Results With the applied method for data synthetization, we obtained an error of about 1% for all the relevant parameters. Furthermore, we demonstrate that the LONN models reach an accuracy of about 75%. After comparing the LONN models against conventional deep-learning models we observe that our implemented models are less accurate (accuracy loss of about 8%). However, the loss of accuracy is compensated by the fact that LONN models are transparent and safe because the freezing of training parameters makes them less prone to adversarial attacks. Finally, we predict the best therapy as well as the expected therapy time. We were able to predict individualized therapies, which were classified as optimal (binary value) when the prediction fully matched predictions made with models 1 and 2. The results provided by the recommender system are displayed using a graphical interface. The current is a proof of concept to improve the quality of the disease management, while the methods are continuously visualized to preserve transparency for the customers. Conclusions This work contributes to simplify administrative functions and boost the quality of management of patients improving the quality of healthcare with models that are both transparent and safe. Our methodology can be extended to different clinical scenarios where recommender systems can be applied. The acceptance and further development of the app is one of the next important steps and still requires further development depending on specific requirements of the health management, the physicians or health professionals, and the patent population.

show abstract

Section: Discussionmentioning

confidence: 99%

Medical recommender systems based on continuous-valued logic and multi-criteria decision operators, using interpretable neural networks

Ochoa¹,

Csiszár

Schimper³

2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…FinJeHeW 2020;12(3) 164 [19][20][21][22]. There remains a lack of knowledge about PwP perspectives to better understand the factors, technological or otherwise, that influence PwP decisionmaking about mHealth use and its integration into daily life [23,24].…”

Section: 102020mentioning

confidence: 99%

Designing socially acceptable mHealth technologies for Parkinson's disease self-management

2020

View full text Add to dashboard Cite

Mobile health (mHealth) technologies for Parkinson’s disease management have developed quickly in recent years. Research in this area typically focuses on evaluation of the accuracy and reliability of the technology, often to the exclusion of social factors and patient perspectives. This qualitative systematic review aimed to investigate the barriers to and facilitators of use mHealth technologies for disease self-management from the perspective of People with Parkinson's (PwP). Findings revealed that technological, as well as social, and financial factors are key considerations for mHealth design, to ensure its acceptability, and long-term use by PwP. This study proposes that a co-design approach could contribute to the design and development of mHealth that are socially acceptable to PwP, and enable their successful long-term use in the context of daily life.

show abstract

“…For HCP interfaces, the importance of workflow integration to support data-driven consultations has been emphasized [44]. A European Union-funded project has reported on the design of a clinical decision support system for PD that takes a holistic approach, which is in line with the functionalities suggested in this study [45][46][47]. The researchers emphasize the importance of enabling shared decision making [46].…”

Section: Functionalities For Providing Feedback and Recommendationsmentioning

confidence: 67%

How People with Parkinson's Disease and Health Care Professionals Wish to Partner in Care Using eHealth: Co-Design Study (Preprint)

Wannheden¹,

Revenäs²

2020

Preprint

View full text Add to dashboard Cite

BACKGROUND Worldwide, the number of people with Parkinson’s disease (PwP) is predicted to double between the years 2005 and 2030. Given this predicted increase and the limited availability of healthcare resources, eHealth/mHealth services have the potential to provide considerable support for PwP's self-management and collaboration with healthcare professionals (HCPs). Chronic care management requires a different practice of healthcare compared to the management of acute conditions, emphasizing both patients’ and HCP's knowledge and active collaboration for best possible health outcomes, which has been described as 'co-care'. OBJECTIVE The aim of this study was to explore how co-care could be operationalized in PD care, supported by eHealth/mHealth. More specifically, this study explores PwP's and HCPs' expectations and desired eHealth/mHealth functionalities to achieve co-care. METHODS Principles of participatory design were used to enable the identification of PwP's and HCP's views on co-care. The collaborative work was performed in a series of four half-day co-design workshops. Seven (4 women) PwP and 9 HCPs (4 women) participated; 4 neurologists, 3 nurses and 2 physiotherapists. Data were collected through note cards produced by the participants during the first 3 workshops and focus group discussions during the 3rd and 4th workshop. The focus groups were transcribed verbatim. The data were analyzed using qualitative thematic analysis. RESULTS The qualitative analysis of data resulted in two main themes. The first theme, Core eHealth functionalities and their expected values, describes six desired eHealth functionalities for supporting Parkinson's disease co-care between PwP and HCP: 1) self-tracking, 2) pre-visit questionnaires, 3) graphical visualization, 4) clinical decision support, 5) self-care recommendations, 6) asynchronous communication). The second theme, Individual and organizational constraints, describes constraints that need to be addressed to succeed with an eHealth/mHealth service for co-care. Individual constraints: eHealth literacy and acceptance; organizational constraints: teamwork and administrative workload. CONCLUSIONS This study adds to our knowledge on how co-care in Parkinson's Disease care could be operationalized. Co-care implies a shift from episodic routine-driven care to more flexible care management that is driven by patients' needs and enabled by active information exchange between PwP and HCPs and further supported by automated information processing to generate patient-specific advice. More research is needed to further explore the concept of co-care in chronic care management and what it means for self-care and healthcare. INTERNATIONAL REGISTERED REPORT RR2-10.2196/11278

show abstract

Designing a mHealth clinical decision support system for Parkinson’s disease: a theoretically grounded user needs approach

Cited by 26 publications

References 53 publications

Medical recommender systems based on continuous-valued logic and multi-criteria decision operators, using interpretable neural networks

Medical recommender systems based on continuous-valued logic and multi-criteria decision operators, using interpretable neural networks

Designing socially acceptable mHealth technologies for Parkinson's disease self-management

How People with Parkinson's Disease and Health Care Professionals Wish to Partner in Care Using eHealth: Co-Design Study (Preprint)

Contact Info

Product

Resources

About