Proof of Concept Study of EMBalance Decision Support System to Evaluate Balance Disorders (EMBalance)

A Decision Support System Incorporating a Validated Patient-specific, Multi-scale Balance Hyper Model Towards Early Diagnostic Evaluation and Efficient Management Plan Formulation of Balance Disorders (EMBalance)

Balance is crucial for an individual's mobility and independence. Human balance is achieved and maintained by a complex set of sensorimotor systems that include sensory input from vision, proprioception and the vestibular system (motion, equilibrium, spatial orientation). This information is then integrated by the brain. This complexity leads to undiagnosed or mistreated patients with balance disorders for long period which can affect their daily activities. The EMBalance project is a research project funded by the European Union, involving 10 universities across Europe. Its aim is to create a Decision Support System (DSS) to support doctors in diagnosing and treating balance disorders. It will be available to primary and secondary care doctors of different specialties, levels of training and in different parts of the country. The DSS will: Be used by primary and secondary health care professionals Assist the doctor on the evaluation and management of dizzy patients Predict how the balance disorder may progress Reduce patient waiting time and the onward referrals Ensure patients receive prompt and efficient treatment plans The EMBalance randomised clinical trial (RCT) is a proof-of-concept, multicentre, single-blind, and parallel group study, conducted in Belgium, Germany, Greece and United Kingdom. At present, the question that this study aims to answer is whether the algorithms developed for the EMBalance Platform will yield meaningful information and how these algorithms and platform can be improved, performing an offline comparison of the classical diagnostic approach and the outcome of the EMBalance platform, without any consequence for the patient. Patients who present with balance related symptoms at primary care will be randomised to either intervention group (non-specialist doctor +DSS) or control group (non-specialist doctor -DSS). An overseeing expert will then confirm the diagnosis and management decisions made by the non-specialist doctors in order to determine whether the use of the DSS can help them in a more precise assessment.

Balance is crucial for an individual's mobility and independence. Dizziness and imbalance symptoms are one of the most common reasons for visits to a doctor and affect up to 30-40% of the population by 60 years of age. The healthcare service provision to address vestibular pathology remains inadequate and is regarded as low priority. The complexity of balance control mechanisms, the lack of medical expertise, and the absence of specialised equipment can be contributory factors to the mismanagement of patients suffering balance disorders. However, the mean number for patient visits to their Health Care providers required to establish a correct diagnosis and start appropriate treatment, both in the US and the UK, is 4.5. The overall socio-economic impact of balance disorders on the affected individual, patient's families as well as the burden on society and the health services is considerable. Advances in computer science and artificial intelligence have allowed the development of computer systems that support clinical diagnosis or therapeutic and treatment decisions based on individualised patient data. However, a review of existing Decision Support Systems used in Medicine demonstrated there are not many successful integrated software systems or standalone tools that address the early diagnosis and effective management of balance disorders. All this said, the EMBalance DSS has been developed as a supplementary and supportive tool for non-expert physicians faced with the challenge of addressing vestibular disorders. The current study will assess the effectiveness of the EMBalance Decision Support System (DSS) for diagnosis and management of balance disorders in a feasibility/proof of concept study. Patients who present with balance related symptoms (specifically vertigo or dizziness exacerbated by head movements) in primary care, will be seen by a non-specialist doctor either with or without the support of the DSS, on a ratio 1:1. Non-specialist doctors in each participating country are defined as follow: UK: General Practitioners Germany: Neurology residents Belgium & Greece: ENT residents Overseeing experts in each participating country are defined as follow: UK: Consultant in audiovestibular medicine (AVM) Germany: Neurologist Belgium & Greece: ENT specialist with >10 years expertise in AVM/Neuro-otology It is anticipated 100 participants will be recruited to each of the two treatment groups, giving a total of 200 participants across Europe. Each participating site in Greece, Belgium, Germany and United Kingdom will recruit 50 patients. Allocation will be performed based on randomisation tables that are produced in advance for each centre. Statistical data analysis will be performed by the National and Kapodistrian University of Athens. The statistical analysis has been developed by the National and Kapodistrian University of Athens and reviewed by the Institute of Communication and Computer Science (Greece). Quality and ethical assurance are supervised by the Trial Steering Committee (TSC) and Trial Management Group (TMG)

Patients allocated to +DSS group will receive the following intervention: V1: appointment with a non-specialist doctor with the support of the DSS V2: appointment with an overseeing expert V3: DSS Customised Vestibular Physiotherapy V4: follow-up visit with the overseeing expert

Patients allocated to -DSS group will receive the following intervention: V1: appointment with a non-specialist doctor without the support of the DSS V2: appointment with an overseeing expert V3: Standard Physiotherapy Practice V4: follow-up visit with the overseeing expert

The EMBalance DSS is a program which summarises and structures clinical information. The structuring of medical information is based on algorithms that have been developed and are employed via the DSS platform. The non-specialist doctors who use the DSS will be asked to exercise their clinical judgement in order to come up with a diagnosis or management plan. The DSS use has the following characteristics: Doctors can pace the process anyway they see fit (e.g. by switching from history taking to examination, stopping at any point, or going back to medical history) or by stopping the process entirely. Although the EMBalance platform will propose 2-3 diagnosis (with probability estimation for each), doctors will be asked to either choose one of these or discard and choose their own.

After the initial appointment with the non-specialist doctor, all patients will be invited to attend a specialist neuro-otology clinic where they will be seen by an overseeing expert in order to undergo a "Gold Standard" diagnostic process, and determine the management plan appropriate to the diagnosis, which will be compared to the management plan previously advised by the non-specialist doctor. The overseeing expert will review investigations carried out, results assessed by the non-specialist doctor.

Customised vestibular exercise programme suggested by the DSS. Such exercises are based on the eye, head, and postural exercises that provoke a patient's symptoms. Adaptation exercises incorporating gaze fixation and head movements and postural exercises are prescribed to promote recovery of the vestibule-ocular reflex (VOR) and vestibulo-spinal reflex function. Up to 5 exercises will be practised by the patient at home for approximately 1-2 minutes each, twice daily initially at a slow speed which gradually increases as symptoms improve. Patients presenting vestibular migraine will perform a maximum of three exercises. These exercises will be chosen by the DSS from a range of established exercises and chosen according to the patient's symptoms when performing the exercise/type of movement.

Patient will be referred to a local physiotherapy service by his/her non-specialist doctor within 18 weeks from referral. Standard vestibular rehabilitation practice consists of a customised exercise programme, this is service dependent and tailored for patient's symptoms. The rehabilitation programme might include lifestyle advice and education, sometimes accompanied by a leaflet.

Agreement between the diagnosis established by the non-specialist doctors (using the DSS and not using DSS) and the "Gold Standard" as determined by an overseeing expert and according to current evidence based guidelines for the diagnosis/management of these disorders.

Agreement between the management plan established by the non-specialist doctors (using the DSS and not using DSS) and the "Gold Standard" as recommended by an overseeing expert and according to current evidence based guidelines for the diagnosis/management of these disorders.

Inclusion Criteria: Be capable of understanding the information provided Absence of dementia/uncontrolled psychiatric disorder Vertigo or chronic dizziness exacerbated by head movements (<12 months) Sub-acute presentation of dizziness (up to 3 months) without presenting to emergency services Exclusion Criteria: Subjects with learning disability or dementia Patients with uncontrolled psychiatric disorders Pregnant and breastfeeding women Patients' incapable or unwilling to give informed consent. Patients with acute vestibular disorders (present at Accident and Emergency).

Colledge NR, Wilson JA, Macintyre CC, MacLennan WJ. The prevalence and characteristics of dizziness in an elderly community. Age Ageing. 1994 Mar;23(2):117-20. doi: 10.1093/ageing/23.2.117.

Royal College of Physicians, Hearing and Balance Disorders, Report of a working party (2007) Available at: https://www.rcplondon.ac.uk/sites/default/files/documents/hearing-and-balance-disorders.pdf. [Accessed 29 September 2008]

Pavlou M, Davies RA, Bronstein AM. The assessment of increased sensitivity to visual stimuli in patients with chronic dizziness. J Vestib Res. 2006;16(4-5):223-31.

Neuhauser HK, Radtke A, von Brevern M, Lezius F, Feldmann M, Lempert T. Burden of dizziness and vertigo in the community. Arch Intern Med. 2008 Oct 27;168(19):2118-24. doi: 10.1001/archinte.168.19.2118. Erratum In: Arch Intern Med. 2009 Jan 12;169(1):89.

Scuffham P, Chaplin S, Legood R. Incidence and costs of unintentional falls in older people in the United Kingdom. J Epidemiol Community Health. 2003 Sep;57(9):740-4. doi: 10.1136/jech.57.9.740.

Keen, P. & Morton, M. S. (1978). Decision Support Systems: An Organizational Perspective, Addison-Wesley

Eom, S. & Kim, E. A survey of decision support system applications. Journal of the Operational Research Society. 2006, 57(15): 1264-1278

Garg AX, Adhikari NK, McDonald H, Rosas-Arellano MP, Devereaux PJ, Beyene J, Sam J, Haynes RB. Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: a systematic review. JAMA. 2005 Mar 9;293(10):1223-38. doi: 10.1001/jama.293.10.1223.

Bamiou DE, Kikidis D, Bibas T, Koohi N, Macdonald N, Maurer C, Wuyts FL, Ihtijarevic B, Celis L, Mucci V, Maes L, Van Rompaey V, Van de Heyning P, Nazareth I, Exarchos TP, Fotiadis D, Koutsouris D, Luxon LM. Diagnostic accuracy and usability of the EMBalance decision support system for vestibular disorders in primary care: proof of concept randomised controlled study results. J Neurol. 2022 May;269(5):2584-2598. doi: 10.1007/s00415-021-10829-7. Epub 2021 Oct 20.

Rammazzo L, Kikidis D, Anwer A, Macdonald N, Kyrodimos E, Maurer C, Wuyts F, Luxon L, Bibas A, Bamiou DE. EMBalance - validation of a decision support system in the early diagnostic evaluation and management plan formulation of balance disorders in primary care: study protocol of a feasibility randomised controlled trial. Trials. 2016 Sep 5;17(1):435. doi: 10.1186/s13063-016-1568-x.