Using machine learning to model older adult inpatient trajectories from electronic health records data

Publication: ScienceDirect

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

View publication

Factors Associated with Significant Weight Loss in Hospitalised Patients with COVID-19: A Retrospective Cohort Study in a Large Teaching Hospital

Publication: Nutrients

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


Summary

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

Unquantifiably low aldosterone concentrations are prevalent in hospitalised COVID-19 patients but may not be revealed by chemiluminescent immunoassay

Publication: Endocrine Connections

Martin Wiegand, David J Halsall, Sarah L Cowan, Kevin Taylor, Robert J B Goudie, Jacobus Preller, Mark Gurnell

26 August 2022


Summary

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

Difficulty and help with activities of daily living among older adults living alone during the COVID-19 pandemic: a multi-country population-based study

Publication: BMJ Geriatrics

Shanquan Chen, Linda A Jones, Shan Jiang, Huajie Jin, Dong Dong, Xi Chen, Dan Wang, Yun Zhang, Li Xiang, Anna Zhu, Rudolf N Cardinal

4 March 2022


Summary

Older adults who live alone and have difficulties in activities of daily living (ADLs) may have been more vulnerable during the COVID-19 pandemic. However, little is known about pandemic-related changes in ADL assistance (such as home care, domiciliary care) and its international variation.

Researchers examined international patterns and changes in provision of ADL assistance, and related these to country-level measures including national income and health service expenditure.

View publication

Validation of the 4C Deterioration Model for COVID-19 in a UK teaching hospital during Wave 2

Publication: The American Journal of the Medical Sciences

Sarah L. Cowan, Martin Wiegand, Jacobus Preller, Robert J.B. Goudie

August 23 2021


Summary

Using data extracted from CUH Epic on all patients admitted to CUH with COVID-19 between August 27, 2020 and April 16, 2021, researchers assessed the accuracy of the 4C Deterioration model (Gupta et al, Lancet Respir Med, 2021), a point-of-admission tool for predicting in-hospital clinical deterioration in these patients.

View publication

An atlas of mitochondrial DNA genotype-phenotype associations in the UK Biobank

Publication: Nature

Ekaterina Yonova-Doing, Claudia Calabrese, Aurora Gomez-Duran, Katherine Schon, Wei Wei, Savita Karthikeyan, Patrick F. Chinnery & Joanna M. M. Howson

17 May 2021


Summary

Mitochondrial DNA (mtDNA) variation in common diseases has been underexplored, partly due to a lack of genotype calling and quality-control procedures. Developing an at-scale workflow for mtDNA variant analyses, we show correlations between nuclear and mitochondrial genomic structures within subpopulations of Great Britain and establish a UK Biobank reference atlas of mtDNA–phenotype associations.

View publication

Metabolic traits and stroke risk in individuals of African ancestry: Mendelian randomization analysis

Publication: Stroke

Segun Fatumo , Ville Karhunen, Tinashe Chikowore, Toure Sounkou , Brenda Udosen, Chisom Ezenwa, Mariam Nakabuye, Opeyemi Soremekun, Iyas Daghlas, David K. Ryan, Amybel Taylor, Amy M. Mason, Scott M. Damrauer, Marijana Vujkovic, Keith L. Keene, Myriam Fornage, Marjo-Riitta Järvelin, Stephen Burgess, Dipender Gill,

3 June 2021


Summary

Metabolic traits affect ischemic stroke (IS) risk, but the degree to which this varies across different ethnic ancestries is not known. Our aim was to apply Mendelian randomization to investigate the causal effects of type 2 diabetes (T2D) liability and lipid traits on IS risk in African ancestry individuals, and to compare them to estimates obtained in European ancestry individuals

View publication

SCORE2 risk prediction algorithms: new models to estimate 10-year risk of cardiovascular disease in Europe

Publication: European Heart Journal

SCORE2 working group and ESC Cardiovascular risk collaboration

13 June 2021


Summary

The researchers analysed data from nearly 700,000 mainly middle-aged participants in 45 large-scale studies to develop risk prediction models (SCORE2) tailored for use in European countries.

The participants did not have previous history of CVD at the outset and 30,000 had a CVD event (heart attack or stroke) during the first 10 years of follow up.

These risk models were then statistically adapted or ‘recalibrated’ to more accurately estimate CVD risk for contemporary populations in four European risk regions, using data on population-specific CVD incidence rates and risk factor values from 10.8 million individuals. Read the full story

View publication

Anticholinergic burden in older adult inpatients: patterns from admission to discharge and associations with hospital outcomes

Publication: Sage Journals

Maria Herrero-Zazo, Rachel BerryEmma Bines, Debi BhattacharyaPhyo K. MyintVictoria L. Keevil

6 May 2021


Summary

Researchers describe how commonly medicines which block the chemical acetylcholine are prescribed to older adults admitted to hospital as an emergency and explore links between these medicines and death during or soon after hospital admission. Researchers use data collected as part of routine medical care at one university hospital to describe how often these medicines are prescribed in a large sample of older adults admitted to hospital as an emergency. They looked at the medicines patients are prescribed on admission to the hospital and also when they are later discharged.

View publication

Cardiovascular risk factors and lifestyle behaviours in relation to longevity: a Mendelian randomization study

Publication: Journal of Internal Medicine

S. van Oort, J. W. J. Beulens, A. J. van Ballegooijen, S. Burges,s S. C. Larsson

26 October 2020


Summary

The American Heart Association introduced the Life’s Simple 7 initiative to improve cardiovascular health by modifying cardiovascular risk factors and lifestyle behaviours. It is unclear whether these risk factors are causally associated with longevity.

This study aimed to investigate causal associations of Life’s Simple 7 modifiable risk factors, as well as sleep and education, with longevity using the two‐sample Mendelian randomization design.

Risk factors associated with a lower odds of longevity included the following: genetic liability to type 2 diabetes, genetically predicted systolic and diastolic blood pressure, body mass index, low‐density lipoprotein cholesterol and smoking initiation. Genetically increased high‐density lipoprotein cholesterol and educational level were associated with a higher odds of longevity. Fasting glucose and other lifestyle factors were not significantly associated with longevity.

Most of the Life’s Simple 7 modifiable risk factors are causally related to longevity. Prevention strategies should focus on modifying these risk factors and reducing education inequalities to improve cardiovascular health and longevity.

View publication

© Copyright - NIHR Cambridge Biomedical Research Centre 2025