Modeling stroke rehabilitation processes using the Unified Modeling Language (UML)
Introduction
Rehabilitation is an individually tailored programme of medical practice focused to reverse all or the most of disabling conditions produced by a disease that cannot be reversed by medical care alone [1].
Stroke rehabilitation is the process of helping a post-stroke patient regain the highest possible level of independence and quality of life. A growing body of evidence indicates that effective rehabilitation interventions delivered just after medical stability has been reached [2] can enhance the recovery of functional disabilities [3], [4].
Stroke continues to be a major public health concern, with more than 750,000 cases occurring each year in the United States; nearly one-third of these strokes are recurrent [5], [6], [7]. About 196,000 strokes occur in Italy every year, of which 80% are first strokes and 20% recurrent [8], [9]. Stroke is the leading neurological cause of acquired adult disability, and the third most frequent cause of death in industrialised countries [10]. One year after the acute event, one-third of the patients continue to be totally dependent on their caregivers [8]. Furthermore, as the population ages, the social and economic burden of stroke is expected to increase.
The heterogeneity of stroke aetiology and the initial severity of the lesion, differences in the resulting impairments, the variability of responses to rehabilitation treatments, and individual characteristics such as motivation, social support and learning ability all make the process of post-stroke recovery difficult to predict.
The stroke rehabilitation guidelines are “systematically developed statements, grounded on the current scientific knowledge, to assist practitioner and patient decisions about appropriate healthcare for specific clinical circumstances” [11]. However, although they provide general recommendations, they should be interpreted by healthcare professionals in such a way as to ensure the best strategies at local level. There is therefore a considerable degree of discretion when going from reading the guidelines to treating patients in clinical practice [12], [13]. Rehabilitation depends on organisational factors such as equipment, facilities, personnel competences, and the harmonised cooperation of staff in a particular healthcare institution. However, despite clinicians’ general mistrust of clinical guidelines, it was shown that the improvement in patient outcomes is greater the more the rehabilitation process adheres to their recommendations [14]. Moreover, it is recognised that it has to be provided by a specialised and multidisciplinary team of health professionals [15], [16], [17], [18].
An efficient and effective process must be well organised, characterised by a continuous improvement in outcomes, simple to control, clear in all its details to all of the players involved, and flexible enough in order to allow its frequent and easy updating [19]. The first step towards improving the complex process of post-stroke rehabilitation is to describe it clearly and in detail. One way of doing this is to model it because modelling makes it easier to break it down into its component parts, which can be handled one at a time. These are subsequently recombined in order to create a network of interdependence. Modelling increases the readability of a process and its evolution, and thus facilitates its control.
One widely used tool in process modelling is the Unified Modeling Language (UML), a visual modelling and specification language that is capable of providing multidimensional insights into a system using behavioural, conceptual, and physical abstractions [20]. It has not only become a gold standard in modelling complex processes and software systems, but has also been applied to e-healthcare with various objectives, including optimising hospital processes, [21] planning chemotherapy and organising hospital-based cancer registration processes, [22], [23] modelling the organisation of randomised controlled trials, [24] and creating a medical image case-based retrieval system for pathologists [25]. The UML allows the whole application domain to be simply visualised and understood.
The aim of the study was to design the first UML model of the multidisciplinary stroke rehabilitation process. The model was grounded on international guidelines and refined following the clinical pathway adopted at local level by an Italian specialized rehabilitation centre. A process representation through a comprehensive conceptual model was implemented in UML and then a part of the model was translated into a relational database for the digital administration and collection of assessment tests by means of clinical scales.
Section snippets
Organisational framework in rehabilitation medicine
Rehabilitation is used in different contexts such as cardiology, oncology, neurology, orthopaedic. The rehabilitation objectives and the type of therapy are obviously different in the different contexts. An older person who has had a stroke may simply want rehabilitation to be able to dress or bath without the help of a caregiver. A younger person who has had a heart attack may go through cardiac rehabilitation to try to return to work and normal activities. Someone with a lung disease may get
The context of the stroke rehabilitation process
The rehabilitation of post-stroke patients is a proactive, person-centred and goal-oriented process aimed at improving function and/or preventing deterioration of function, and bringing about the highest possible level of patient independence [15]. The complete effective care of stroke includes the early management of acute stroke in the Emergency Department, the planning of post-acute rehabilitation in a specialised centre and finally at home, and following up the patient [12]. The proposed
Discussion
A UML model providing an essential description of the stroke rehabilitation process was implemented. The model infrastructure is based on an organisational framework which is common to the rehabilitation medicine regardless the specialty chosen. The model describes what is needed to offer effective multidisciplinary rehabilitation to post-acute stroke patients admitted to an advanced Italian rehabilitation centre and how all of the actors take part in the process.
First, the main phases of the
Conclusions
To the best of our knowledge, ours is the first UML model of the multidisciplinary stroke rehabilitation process. It assumes post-acute stroke patients admitted to a specialised rehabilitation centre, and concentrates on representing the fundamental entities involved in the rehabilitation process. The model is grounded on and coherent with the international guidelines for the stroke rehabilitation process. It is then refined according to the clinical pathway adopted by a specific rehabilitation
Summary
The heterogeneity of stroke aetiology and of the initial severity of the lesion, differences in the resulting impairments, the variability of responses to rehabilitation treatments, and individual characteristics such as motivation, social support and learning ability all make the process of post-stroke recovery difficult to predict. In organising and providing rehabilitation procedures for stroke patients, the usual need for many refinements makes it inappropriate to attempt rigid
Conflict of interest statement
None declared.
Acknowledgements
We would like to thank the doctors, therapists and nurses for their contribution and Kevin Smart for his help in preparing the English version of the manuscript.
References (42)
- et al.
Motor recovery after stroke: a systematic review
Lancet Neurol.
(2009) - et al.
Evidence-based careflow management systems: the case of post-stroke rehabilitation
J. Biomed. Inform.
(2002) - et al.
Factors affecting functional outcome after stroke: a critical review of rehabilitation interventions
Arch. Phys. Med. Rehabil.
(1999) - et al.
Multidisciplinary rehabilitation versus medical care: a meta-analysis
Soc. Sci. Med.
(1995) - et al.
Modelling, designing, and implementing a family-based health record prototype
Comput. Biol. Med.
(2010) - et al.
Predicting home and community walking activity in people with stroke
Arch. Phys. Med. Rehabil.
(2010) - et al.
Development of the Italian version of the knee injury and osteoarthritis outcome score for patients with knee injuries: cross-cultural adaptation, dimensionality, reliability, and validity
Osteoarthritis Cartilage
(2012) - et al.
Process of pulmonary rehabilitation and program organization
Eur. J. Phys. Rehabil. Med.
(2011) - et al.
Management of adult stroke rehabilitation care: a Clinical Practice Guideline
Stroke
(2005) - et al.
Cycling induced by electrical stimulation improves motor recovery in postacute hemiparetic patients: a randomized controlled trial
Stroke
(2011)
Physical activity and exercise recommendations for stroke survivors; an American Heart Association Scientific Statement From the Council on Clinical Cardiology, Subcommittee on Exercise, Cardiac Rehabilitation, and Prevention; the Council on Cardiovascular Nursing; the Council on Nutrition, Physical Activity, and Metabolism; and the Stroke Council
Circulation
American Heart Association Statistics Committee and Stroke Statistics Subcommittee. Heart disease and stroke statistics—2007 update: a report from the American Heart Association Statistics Committee and Stroke Statistics Subcommittee
Circulation
SPREAD—Stroke Prevention and Educational Awareness Diffusion Ictus cerebrale: Linee guida italiane, Milano, Pellicole e stampa
The impact of stroke in Italy: first step for a national burden of disease study
Disabil. Rehabil.
Neurologia clinica
Lange Clinical Book
Clinical decision support systems for the practice of evidence-based medicine
J. Am. Med. Inform. Assoc.
Adherence to postacute rehabilitation guidelines is associated with functional recovery in stroke
Stroke
Cited by (17)
APLUS: A Python library for usefulness simulations of machine learning models in healthcare
2023, Journal of Biomedical InformaticsBPMN in healthcare: Challenges and best practices
2022, Information SystemsCitation Excerpt :Monitoring activities refer to continuous or repeated activities involving the observation of the patient, the measurement of his/her physiological function, and the assessment of life support equipment. Usually, monitoring runs in parallel with other diagnostic or therapeutic activities to check their efficacy and possibly adjusting them [63]. Continuous monitoring is common practice in intensive care settings and is realized with the help of (electronic) sensors and data processing devices (e.g., continuous EEG, transducers, glucose monitoring systems) that monitor the vital signs of the patient in real-time.
The Latin American laws of correct nutrition: Review, unified interpretation, model and tools
2016, Computers in Biology and MedicineCitation Excerpt :However, this is not the only field in which this language can be used as its applicability to cases that need to be modeled has been proved with multiple examples [6]. In medical systems, for example, there are models for stroke rehabilitation processes [7], models for the molecular biology domain [8], and UML forms the basis of the caCORE Software Development Kit [9]. Nevertheless, UML itself lacks of sufficient expressiveness to specify detailed restrictions of classes and data types.
Architecture for Groupware Oriented to Collaborative Medical Activities in the Rehabilitation of Strokes
2023, Programming and Computer SoftwareUsing Unified Modeling Language to Analyze Business Processes in the Delivery of Child Health Services
2022, International Journal of Environmental Research and Public HealthTowards the improvement of computer-assisted medical activities for stroke rehabilitation
2022, Proceedings - 2022 10th International Conference in Software Engineering Research and Innovation, CONISOFT 2022