Distinguishing between dementia with Lewy bodies (DLB) and Alzheimer’s disease (AD) using mental health records: a classification approach
Wang Z, Ive J, Moylett S, Mueller C, Cardinal RN, Velupillai S, O’Brien J, Stewart R
1 November 2020
While Dementia with Lewy Bodies (DLB) is the second most common type of neurodegenerative dementia following Alzheimer’s Disease (AD), it is difficult to distinguish from AD.
Here the researchers propose a method for DLB detection by using mental health record (MHR) documents from a (3-month) period before a patient has been diagnosed with DLB or AD. The objective is to develop a model that could be clinically useful to differentiate between DLB and AD across datasets from different healthcare institutions.
The researchers cast this as a classification task using Convolutional Neural Network (CNN), an efficient neural model for text classification. They experiment with different representation models, and explore the features that contribute to model performances.
In addition, they apply temperature scaling, a simple but efficient model calibration method, to produce more reliable predictions. They believe the proposed method has important potential for clinical applications using routine healthcare records, and for generalising to other relevant clinical record datasets.
To the best of the team’s knowledge, this is the first attempt to distinguish DLB from AD using mental health records, and to improve the reliability of DLB predictions.View publication
Maria Herrero-Zazo, Tomas Fitzgerald, Vince Taylor, Helen Street, Afzal N. Chaudhry, John R. Bradley, Ewan Birney, Victoria L. Keevil
20 January 2023
- Time-series blood test & vital sign data from older inpatients were presented to HMM (Hidden Markov Models)
- Hidden clinically interpretable states were extracted, linked with diagnoses and death
- States modeled inpatient trajectories, differentiating risk from admission-discharge
- The clinical interpretation of HMM states helped explain how ML models organise data
Publication: Nature Nanotechnology
Filip Bošković, Jinbo Zhu, Ran Tivony, Alexander Ohmann, Kaikai Chen, Mohammed F. Alawami, Milan Đorđević, Niklas Ermann, Joana Pereira Dias, Michael Fairhead, Mark Howarth, Stephen Baker, Ulrich F. Keyser
16 January 2023
Respiratory infections are the major cause of death from infectious disease worldwide. Multiplexed diagnostic approaches are essential as many respiratory viruses have indistinguishable symptoms.
We created self-assembled DNA nanobait that can simultaneously identify multiple short RNA targets. The nanobait approach relies on specific target selection via toehold-mediated strand displacement and rapid read-out via nanopore sensing. Here, we show this platform can concurrently identify several common respiratory viruses, detecting a panel of short targets of viral nucleic acids from multiple viruses.
Our nanobait can be easily reprogrammed to discriminate viral variants, as we demonstrated for several key SARS-CoV-2 variants with single-nucleotide resolution. Lastly, we show that nanobait discriminates
between samples extracted from oropharyngeal swabs from negative and positive SARS-CoV-2 patients
Our system allows for multiplexed identification of native RNA molecules, providing a new scalable approach for diagnostics of multiple respiratory viruses in a single assay.View publication
Publication: Nature Medicine
Aideen B. Daly, Charlotte K. Boughton, Munachiso Nwokolo, Sara Hartnell, Malgorzata E. Wilinska, Alina Cezar, Mark L. Evans & Roman Hovorka
12 January 2023
Cambridge scientists have successfully trialled an artificial pancreas for use by patients living with type 2 diabetes. The device – powered by an algorithm developed at the University of Cambridge – doubled the amount of time patients were in the target range for glucose and halved the time spent experiencing high glucose levels. Read the full news story.View publication
Publication: British Journal of Psychiatry
Noham Wolpe, Shanquan Chen, Brian Kirkpatrick, Peter B. Jones, Christopher Jenkins, Rudolf N. Cardinal and Emilio Fernandez-Egea
10 January 2023
In a cohort of 187 people with schizophrenia treated with clozapine, we examined the relationship between clozapine, sedation, and aspects of symptoms: motivation/pleasure, and emotional expressivity. Clozapine was associated with increased sedation (a known side effect), and this sedation worsened motivation/pleasure; however, there was also a separate effect through which clozapine was directly associated with improved motivation/pleasure. These results highlight the important of addressing sedative side-effects of antipsychotic medications to improve quality of life.
Publication: PLoS Medicine
Shanquan Chen, Annabel C Price, Rudolf N Cardinal, Sinéad Moylett, Anne D Kershenbaum, James Fitzgerald, Christoph Mueller, Robert Stewart, John T O’Brien
6 December 2022
In an observational study of people who had dementia with Lewy bodies, use of cholinesterase inhibitors (a symptomatic treatment) was associated with shorter duration of hospital admissions and decreased risk of mortality.View publication
Dimitra Zannidi, Pinal S. Patel, Eleni Leventea, Jessica Paciepnik, Frances Dobson, Caroline Heyes, Robert J. B. Goudie, Linda M. Oude Griep, Jacobus Preller, and Lynsey N. Spillman,
8 October 2022
Previous research has shown that people hospitalised with COVID-19 are at risk of weight loss and malnutrition. This study looked at patients who experienced weight loss of 10% or more during their hospital admission to Cambridge University Hospitals NHS with COVID-19 during the first wave of the pandemic. Weight loss of 10% or more is considered a large amount to lose as it increases the chance of someone becoming more poorly and not surviving. Therefore, preventing weight loss may help patients to survive and recover. The study looked at risk factors for weight loss to help better recognise the patients that need more support to prevent weight loss.View publication
Publication: European Heart Journal
Paddy C Dempsey, Alex V Rowlands, Tessa Strain, Francesco Zaccardi, Nathan Dawkins, Cameron Razieh, Melanie J Davies, Kamlesh K Khunti, Charlotte L Edwardson, Katrien Wijndaele, Soren Brage, Tom Yates
27 October 2022
Increasing physical activity of any intensity is beneficial for health, but new research published in the European Heart Journal shows that there is a greater reduction in cardiovascular disease risk when more of that activity is of at least moderate intensity.View publication
Edward J. Needham,, Alexander L. Ren, Richard J. Digby, Emma J. Norton, Soraya Ebrahimi, Joanne G. Outtrim, Doris A. Chatfield, Anne E. Manktelow, Maya M. Leibowitz, Virginia F. J. Newcombe, Rainer Doffinger, Gabriela Barcenas-Morales, Claudia Fonseca, Michael J. Taussig, Rowan M. Burnstein, Romit J. Samanta, Cordelia Dunai, Nyarie Sithole, Nicholas J. Ashton, Henrik Zetterberg, Magnus Gisslén, Arden Edén,, Emelie Marklund, Peter J. M. Openshaw, Jake Dunning, Michael J. Griffiths, Jonathan Cavanagh, Gerome Breen, Sarosh R. Irani,, Anne Elmer, Nathalie Kingston,, Charlotte Summers,, John R. Bradley,, Leonie S. Taams, Benedict D. Michael, Edward T. Bullmore, Kenneth G. C. Smith, Paul A. Lyons, Alasdair J. Coles, David K. Menon and the Cambridge NeuroCOVID Group, the CITIID-NIHR COVID- BioResource Collaboration and Cambridge NIHR Clinical Research Facility
6 September 2022
COVID-19 is associated with neurological complications including stroke, delirium and encephalitis. Furthermore, a post-viral syndrome dominated by neuropsychiatric symptoms is common, and is seemingly unrelated to COVID-19 severity. The true frequency and underlying mechanisms of neurological injury are unknown, but exaggerated host inflammatory responses appear to be a key driver of COVID-19 severity.
Researchers investigated the dynamics of, and relationship between, serum markers of brain injury (neurofilament light [NfL], glial fibrillary acidic protein [GFAP] and total tau) and markers of dysregulated host response (autoantibody production and cytokine profiles) in 175 patients admitted with COVID-19 and 45 patients with influenza.View publication
Publication: Endocrine Connections
Martin Wiegand, David J Halsall, Sarah L Cowan, Kevin Taylor, Robert J B Goudie, Jacobus Preller, Mark Gurnell
26 August 2022
The renin-angiotensin-aldosterone system (RAAS) is of interest in understanding COVID-19. Using data extracted from CUH Epic, researchers observed profoundly low aldosterone levels (measured using gold-standard mass-spectrometry) in a large proportion of patients with COVID-19, which were not anticipated. The mechanism of this reduction remains obscure with no obvious correlation with obvious explanations. The profoundly low levels have likely not been detected previously since previous studies used immunoassays to measure aldosterone, in which there are high levels of interference in patients with COVID-19.View publication
Ben Carter, Victoria L. Keevil, Atul Anand, Christopher N. Osuafor, Robert J. B. Goudie, Jacobus Preller, Matthew Lowry, Sarah Clunie, Susan D. Shenkin, Kathryn McCarthy, Jonathan Hewitt and Terence J. Quinn
24 August 2022
Assessing frailty in hospital patients is important but it is not clear how best to assess it. Researchers compared two options: the modified Frailty Index [mFI] and the Clinical Frailty Scale [CFS], and assessed how useful each were for predicting death in older adults (≥65 years) in hospital with COVID-19. Our work suggests the CFS is better than mFI at predicting death in patients who have COVID-19.View publication
Publication: Science Translational Medicine
Ashwin V. Venkataraman, Ayla Mansurgaia, Rizzo Courtney, Bishop, Yvonne Lewis, Ece Kocagoncu, Anne Lingford-Hughes, Mickael Huibanjan Passchier, James B. Rowe, Hideo Tsukada, David J. Brooks, Laurent Martarello, Robert A. Comley, Laigao Chen, Adam J.Schwarz, Richard Hargreaves, Roger N. Gunn, Eugenii A. Rabiner and Paul M. Matthews
18 August 2022
Researchers explored whether widespread cell stress and mitochondrial dysfunction occur in patients with early Alzheimer’s DiseaseView publication
Publication: Nature Genetics
Foad J. Rouhani, Xueqing Zou, Petr Danecek, Cherif Badja, Tauanne Dias Amarante, Gene Koh, Qianxin Wu, Yasin Memari, Richard Durbin, Inigo Martincorena, Andrew R. Bassett, Daniel Gaffney & Serena Nik-Zainal
11 August 2022
DNA damage caused by factors such as ultraviolet radiation affect nearly three-quarters of all stem cell lines derived from human skin cells, say Cambridge researchers, who argue that whole genome sequencing is essential for confirming if cell lines are usable. Read the full news story.View publication
Joseph Cheriyan, Alexandra Roberts, Caleb Roberts, Martin J. Graves, Ilse Patterson,Rhys A. Slough,Rosemary Schroyer, Disala Fernando, Subramanya Kumar,Sarah Lee, Geoffrey J.M. Parker, Lea Sarov-Blat, Carmel McEniery, Jessica Middlemiss, Dennis Sprecher, Robert L. Janiczek
27 March 2022
Lung congestion is common in patients with heart failure. Enhanced MRI may be appropriate method for accurate measurement of lung fluid.View publication
Publication: The Journal of Clinical Endocrinology & Metabolism
Ulla Sovio, Gemma L Clayton, Emma Cook, Francesca Gaccioli, D Stephen Charnock-Jones, Deborah A Lawlor, Gordon C S Smith
18 April 2022
Currently in the UK, women are selected for diagnostic testing for Gestational Diabetes Mellitus (GDM) based on risk factors such as obesity. Researchers developed a new predictive test for GDM using metabolomic markers from maternal serum samples, measured at multiple stages of pregnancy. The test was developed using samples from the Pregnancy Outcome Prediction (POP) study and it was externally validated in maternal plasma samples from a demographically highly dissimilar Born in Bradford (BiB) study. Further assessment in the POP study suggested that the predictive ability of a model including the metabolomic markers was clearly better compared to using early pregnancy obesity alone.View publication
Natalie E Adams, Amirhossein Jafarian, Alistair Perry, Matthew Rouse, Alexander D Shaw, Alexander G Murley, Thomas E Cope, W Richard Bevan-Jones, Luca Passamonti, Duncan Street, Negin Holland, David Nesbitt, Laura E Hughes, Karl J Friston, James RoweNatalie E Adams, Amirhossein Jafarian, Alistair Perry, Matthew Rouse, Alexander D Shaw, Alexander G Murley, Thomas E Cope, W Richard Bevan-Jones, Luca Passamonti, Duncan Street, Negin Holland, David Nesbitt, Laura E Hughes, Karl J Friston, James Rowe
23 June 2022
Synaptic loss occurs early in many neurodegenerative diseases and contributes to cognitive impairment even in the absence of gross atrophy. Currently, for human disease there are few formal models to explain how cortical networks underlying cognition are affected by synaptic loss. Researchers advocate that biophysical models of neurophysiology offer both a bridge from clinical to preclinical models of pathology, and quantitative assays for experimental medicine.View publication
Publication: J Biomech Eng.
Aziz Tokgoz, Shuo Wang, Priya Sastry, Chang Sun, Nichola L. Figg, Yuan Huang, Martin R. Bennett, Sanjay Sinha, Jonathan H. Gillard, Michael P. F. Sutcliffe, Zhongzhao Teng
25 April 2022
Fiber structures and pathological features, e.g., inflammation and glycosaminoglycan (GAG) deposition, are the primary determinants of aortic mechanical properties which are associated with the development of an aneurysm. This study is designed to quantify the association of tissue ultimate strength and extensibility with the structural percentage of different components, in particular, GAG, and local fiber orientation.View publication
Publication: Nature Communications Biology
Irving L. M. H. Aye, Sungsam Gong, Giulia Avellino, Roberta Barbagallo, Francesca Gaccioli, Benjamin J. Jenkins, Albert Koulman, Andrew J. Murray, D. Stephen Charnock-Jones & Gordon C. S. Smith
15 June 2022
Placental function and dysfunction differ by sex but the mechanisms are unknown. Researchers show that sex differences in polyamine metabolism are associated with escape from X chromosome inactivation of the gene encoding spermine synthase (SMS).View publication
Publication: BMJ Open
Christian Philip Stickels, Ramesh Nadarajah, Chris P Gale, Houyuan Jiang, Kieran J Sharkey, Ben Gibbison, Nick Holliman, Sara Lombardo, Lars Schewe, Matteo Sommacal, Louise Sun, Jonathan Weir-McCall, Katherine Cheema, James H F Rudd, Mamas Mamas, Feryal Erhun
17 June 2022
An international team of researchers has modelled the impact that increasing treatment capacity and using a quicker, less invasive treatment option would have on waiting lists. Even in the best-case scenario, they found that the waiting list would take nearly a year to clear.
The traditional treatment for aortic stenosis involves replacing the narrowed valve, most commonly through open heart surgery (a surgical aortic valve replacement, SAVR). However, a newer keyhole procedure called a transcatheter aortic valve implantation (TAVI) is increasingly being used and is now recommended for patients aged 75 and over.
The researchers investigated the impact that increasing treatment capacity and converting a proportion of operations to the quicker TAVI procedure would have on the backlog. They looked at how long it would take to clear the backlog and found that the best and most achievable option involved a combination of increasing capacity by 20 per cent and converting 40 per cent of procedures from SAVR to TAVI. This would clear the backlog within 343 days with 784 deaths while people wait for treatment. Read the full story.View publication
Roma Siugzdaite, Danyal Akarca, Amy Johnson, Sofia Carozza, Alexander L Anwyl-Irvine, Stepheni Uh, Tess Smith, Giacomo Bignardi, Edwin Dalmaijer, Duncan E. Astle
10 June 2022
The quality of a child’s social and physical environment is a key influence on brain development, educational attainment and mental wellbeing. However, there still remains a mechanistic gap in our understanding of how environmental influences converge on changes in the brain’s developmental trajectory. In a sample of 145 children with structural diffusion tensor imaging data, researchers used generative network modelling to simulate the emergence of whole brain network organisation.View publication
Publication: The Lancet Diabetes and Endocrinology
Nick Wareham, Nita Forouhi
27 October 2021
Randomised trials of vitamin D supplementation for cardiovascular disease and all-cause mortality have generally reported null findings. However, generalisability of results to individuals with low vitamin D status is unclear. Researcgers aimed to characterise dose-response relationships between 25-hydroxyvitamin D (25[OH]D) concentrations and risk of coronary heart disease, stroke, and all-cause mortality in observational and Mendelian randomisation frameworks.View publication