Dr Ramin Nilforooshan

PhD Student

Academic and research departments

Faculty of Health and Medical Sciences.


Enshaeifar S, Barnaghi P, Skillman S, Markides A, Elsaleh T, Acton T, Nilforooshan R, Rostill H (2018) Internet of Things for Dementia Care,IEEE Internet Computing22(1)pp. 8-17 IEEE COMPUTER SOC
In this paper we discuss a technical design and an ongoing trial that is being conducted in the UK, called Technology Integrated Health Management (TIHM). TIHM uses Internet of Things (IoT) enabled solutions provided by various companies in a collaborative project. The IoT devices and solutions are integrated in a common platform that supports interoperable and open standards. A set of machine learning and data analytics algorithms generate notifications regarding the well-being of the patients. The information is monitored around the clock by a group of healthcare practitioners who take appropriate decisions according to the collected data and generated notifications. In this paper we discuss the design principles and the lessons that we have learned by co-designing this system with patients, their carers, clinicians, and also our industry partners. We discuss the technical design of TIHM and explain why user-centred and human-experience should be an integral part of the technological design.
Banerjee S, Farina N, Daley S, Grosvenor W, Hughes L, Hebditch M, Mackrell S, Nilforooshan R, Wyatt C, de Vries K, Haq I, Wright J (2016) How do we enhance undergraduate healthcare education in dementia? A review of the role of innovative approaches and development of the Time for Dementia Programme,International Journal of Geriatric Psychiatry32(1)pp. 68-75

Objectives Traditional healthcare education, delivered through a series of time-limited clinical placements, often fails to deliver an understanding of the experiences of those with long-term conditions, a growing issue for healthcare systems. Responses include longitudinal integrated clerkships and senior mentor programmes allowing students' longer placements, continuity of contact and opportunities to learn about chronic illness and patient experience. We review their development and delivery in dementia and present the Time for Dementia (TFD) Programme, a novel 2-year interdisciplinary educational programme.

Design The study design involves a scoping review of enhanced placements in dementia for healthcare professionals in training including longitudinal integrated clerkships and senior mentor programmes and a case study of the development of TFD and its evaluation.

Results Eight enhanced programmes in dementia were identified and seven in the USA. None were compulsory and all lasted 12 months. All reported positive impact from case study designs but data quality was weak. Building on these, TFD was developed in partnership between the Alzheimer's Society, universities and NHS and made a core part of the curriculum for medical, nursing and paramedic students. Students visit a person with dementia and their family in pairs for 2 h every 3 months for 2 years. They follow a semi-structured interaction guide focusing on experiences of illness and services and complete reflective appraisals.

Conclusions We need interprofessional undergraduate healthcare education that enables future healthcare professionals to be able to understand and manage the people with the long-term conditions who current systems often fail. TFD is designed to help address this need.

Rostill Helen, Nilforooshan Ramin, Morgan Amanda, Barnaghi Payam, Ream Emma, Chrysanthaki Theti (2018) Technology integrated health management for dementia,British Journal of Community Nursing23(10)pp. 502-508 Mark Allen Healthcare
Pioneering advances have been made in Internet of Things technologies (IoT) in healthcare. This article describes the development and testing of a bespoke IoT system for dementia care. TIHM for dementia is part of the NHS England National Test Bed Programme and has been trailing the deployment of network enabled devices combined with artificial intelligence to improve outcomes for people with dementia and their carers. TIHM uses machine learning and complex algorithms to detect and predict early signs of ill health. The premise is if changes in a person?s health or routine can be identified early on, support can be targeted at the point of need to prevent the development of more serious complications.
Enshaeifar Shirin, Zoha Ahmed, Skillman Severin, Markides Andreas, Acton Tom, Elsaleh Tarek, Kenny M., Rostill H., Nilforooshan Ramin, Barnaghi Payam (2019) Machine learning methods for detecting urinary tract infection and analysing daily living activities in people with dementia,PLOS One14(1)e0209909pp. 1-22 PLOS
Dementia is a neurological and cognitive condition that affects millions of people around the world. At any given time in the United Kingdom, 1 in 4 hospital beds are occupied by a person with dementia, while about 22% of these hospital admissions are due to preventable causes. In this paper we discuss using Internet of Things (IoT) technologies and in-home sensory devices in combination with machine learning techniques to monitor health and well-being of people with dementia. This will allow us to provide more effective and preventative care and reduce preventable hospital admissions. One of the unique aspects of this work is combining environmental data with physiological data collected via low cost in-home sensory devices to extract actionable information regarding the health and well-being of people with dementia in their own home environment. We have worked with clinicians to design our machine learning algorithms where we focused on developing solutions for real-world settings. In our solutions, we avoid generating too many alerts/alarms to prevent increasing the monitoring and support workload. We have designed an algorithm to detect Urinary Tract Infections (UTI) which is one of the top five reasons of hospital admissions for people with dementia (around 9% of hospital admissions for people with dementia in the UK). To develop the UTI detection algorithm, we have used a Non-negative Matrix Factorisation (NMF) technique to extract latent factors from raw observation and use them for clustering and identifying the possible UTI cases. In addition, we have designed an algorithm for detecting changes in activity patterns to identify early symptoms of cognitive decline or health decline in order to provide personalised and preventative care services. For this purpose, we have used an Isolation Forest (iForest) technique to create a holistic view of the daily activity patterns. This paper describes the algorithms and discusses the evaluation of the work using a large set of real-world data collected from a trial with people with dementia and their caregivers.
Manthorpe Jill, Samsi Kritika, Joly Louise, Crane Maureen, Gage Heather, Bowling Ann, Nilforooshan Ramin (2019) Service provision for older homeless people with memory problems: a mixed-methods study,Health Services and Delivery Research7(9)pp. 1-184 NIHR Journals Library


Early or timely recognition of dementia is a key policy goal of the National Dementia Strategy. However, older people who are homeless are not considered in this policy and practice imperative, despite their high risk of developing dementia.

Objectives and study design

This 24-month study was designed to (1) determine the prevalence of memory problems among hostel-dwelling homeless older people and the extent to which staff are aware of these problems; (2) identify help and support received, current care and support pathways; (3) explore quality of life among older homeless people with memory problems; (4) investigate service costs for older homeless people with memory problems, compared with services costs for those without; and (5) identify unmet needs or gaps in services.


Following two literature reviews to help study development, we recruited eight hostels ? four in London and four in North England. From these, we first interviewed 62 older homeless people, exploring current health, lifestyle and memory. Memory assessment was also conducted with these participants. Of these participants, 47 were included in the case study groups ? 23 had ?memory problems?, 17 had ?no memory problems? and 7 were ?borderline?. We interviewed 43 hostel staff who were participants? key workers. We went back 3 and 6 months later to ask further about residents? support, service costs and any unmet needs.


Overall, the general system of memory assessment for this group was found to be difficult to access and not patient-centred. Older people living in hostels are likely to have several long-term conditions including mental health needs, which remain largely unacknowledged. Participants frequently reported experiences of declining abilities and hostel staff were often undertaking substantial care for residents.


The hostels that were accessed were mainly in urban areas, and the needs of homeless people in rural areas were not specifically captured. For many residents, we were unable to access NHS data. Many hostel staff referred to this study as ?dementia? focused when introducing it to residents, which may have deterred recruitment.


To the best of our knowledge, no other study and no policy acknowledges hostels as ?dementia communities? or questions the appropriateness of hostel accommodation for people with dementia. Given the declining number of hostels in England, the limits of NHS engagement with this sector and growing homelessness, this group of people with dementia are under-recognised and excluded from other initiatives.

Future work

A longitudinal study could follow hostel dwellers and outcomes. Ways of improving clinical assessment, record-keeping and treatment could be investigated. A dementia diagnosis could trigger sustained care co-ordination for this vulnerable group.

Costa Catia, Frampas Cecile, Longman Katherine A., Palitsin Vladimir, Ismail Mahado, Sears Patrick, Nilforooshan Ramin, Bailey Melanie J. (2019) Paper spray screening and LC-MS confirmation for medication adherence testing: a two-step process,Rapid Communications in Mass Spectrometry Wiley

RATIONALE: Paper spray offers a rapid screening test without the need for sample preparation. The incomplete extraction of paper spray allows for further testing using more robust, selective and sensitive techniques such as liquid chromatography mass spectrometry (LC-MS). Here we develop a two-step process of paper spray followed by LC-MS to (1) rapidly screen a large number of samples and (2) confirm any disputed results. This demonstrates the applicability for testing medication adherence from a fingerprint.

METHODS: Following paper spray analysis, drugs of abuse samples were analysed using LC-MS. All analyses were completed using a Q Exactive" Plus Orbitrap" mass spectrometer. This two-step procedure was applied to fingerprints collected from patients on a maintained dose of the antipsychotic drug quetiapine.

RESULTS: The extraction efficiency of paper spray for two drugs of abuse and metabolites was found to be between 15-35% (analyte dependent). For short acquisition times, the extraction efficiency was found to vary between replicates by less than 30%, enabling subsequent analysis by LC-MS. This two-step process was then applied to fingerprints collected from two patients taking the antipsychotic drug quetiapine, which demonstrates how a negative screening result from paper spray can be resolved using LC-MS.

CONCLUSIONS: We have shown for the first time the sequential analysis of the same sample using paper spray and LC-MS, as well as the detection of an antipsychotic drug from a fingerprint. We propose that this workflow may also be applied to any type of sample compatible with paper spray, and will be especially convenient where only one sample is available for analysis.