Sarah Ennis

Prof. Sarah Ennis

orcid

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 March 2020 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
ISI. S. Stafford
I. S. Stafford
MKM. Kellermann
M. Kellermann
EME. Mossotto
E. Mossotto
RBR. M. Beattie
R. M. Beattie
BMB. D. MacArthur
B. D. MacArthur
SESarah Ennis
Sarah Ennis
Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included “machine learning” or “artificial intelligence” and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.

28 April 2012 in Gut
Verified
Journal Article
Open access
PDF file
KCKatja Christodoulou
Katja Christodoulou
AWAnthony E Wiskin
Anthony E Wiskin
JGJane Gibson
Jane Gibson
WTWilliam Tapper
William Tapper
CWClaire Willis
Claire Willis
SESarah Ennis
Sarah Ennis
Background: Multiple genes have been implicated by association studies in altering inflammatory bowel disease (IBD) predisposition. Paediatric patients often manifest more extensive disease and a particularly severe disease course. It is likely that genetic predisposition plays a more substantial role in this group. Objective: To identify the spectrum of rare and novel variation in known IBD susceptibility genes using exome sequencing analysis in eight individual cases of childhood onset severe disease. Design: DNA samples from the eight patients underwent targeted exome capture and sequencing. Data were processed through an analytical pipeline to align sequence reads, conduct quality checks, and identify and annotate variants where patient sequence differed from the reference sequence. For each patient, the entire complement of rare variation within strongly associated candidate genes was catalogued. Results: Across the panel of 169 known IBD susceptibility genes, approximately 300 variants in 104 genes were found. Excluding splicing and HLA -class variants, 58 variants across 39 of these genes were classified as rare, with an alternative allele frequency of <5%, of which 17 were novel. Only two patients with early onset Crohn's disease exhibited rare deleterious variations within NOD2 : the previously described R702W variant was the sole NOD2 variant in one patient, while the second patient also carried the L1007 frameshift insertion. Both patients harboured other potentially damaging mutations in the GSDMB , ERAP2 and SEC16A genes. The two patients severely affected with ulcerative colitis exhibited a distinct profile: both carried potentially detrimental variation in the BACH2 and IL10 genes not seen in other patients. Conclusion: For each of the eight individuals studied, all non-synonymous, truncating and frameshift mutations across all known IBD genes were identified. A unique profile of rare and potentially damaging variants was evident for each patient with this complex disease.

27 September 2013 in Genome Medicine
Verified
Journal Article
Open access
PDF file
RPReuben J Pengelly
Reuben J Pengelly
JGJane Gibson
Jane Gibson
GAGaia Andreoletti
Gaia Andreoletti
ACAndrew Collins
Andrew Collins
CMChristopher J Mattocks
Christopher J Mattocks
SESarah Ennis
Sarah Ennis
Whole-exome sequencing provides a cost-effective means to sequence protein coding regions within the genome, which are significantly enriched for etiological variants. We describe a panel of single nucleotide polymorphisms (SNPs) to facilitate the validation of data provenance in whole-exome sequencing studies. This is particularly significant where multiple processing steps necessitate transfer of sample custody between clinical, laboratory and bioinformatics facilities. SNPs captured by all commonly used exome enrichment kits were identified, and filtered for possible confounding properties. The optimised panel provides a simple, yet powerful, method for the assignment of intrinsic, highly discriminatory identifiers to genetic samples.

30 October 2018 in BMC Nephrology
Verified
Journal Article
Open access
PDF file
CGChristine Gast
Christine Gast
AMAnthony Marinaki
Anthony Marinaki
MAMonica Arenas-Hernandez
Monica Arenas-Hernandez
SCSara Campbell
Sara Campbell
ESEleanor Seaby
Eleanor Seaby
GVG. Venkat-Raman
G. Venkat-Raman
Autosomal dominant tubulointerstitial kidney disease (ADTKD) caused by mutations in the UMOD gene (ADTKD-UMOD) is considered rare and often remains unrecognised. We aimed to establish the prevalence of genetic kidney diseases, ADTKD and ADTKD-UMOD in adult chronic kidney disease (CKD) patients, and to investigate characteristic features. We sent questionnaires on family history to all patients with CKD stages 3–5 in our tertiary renal centre to identify patients with inherited renal disease. Details on clinical and family history were obtained from patient interviews and clinical records. Sanger sequencing of the UMOD gene was performed from blood or saliva samples. 2027 of 3770 sent questionnaires were returned. 459 patients reported a family history, which was consistent with inherited kidney disease in 217 patients. 182 non-responders with inherited kidney diseases were identified through a database search. Of these 399 individuals, 252 had autosomal dominant polycystic kidney disease (ADPKD), 28 had ADTKD, 25 had Alports, and 44 were unknown, resulting in 11% of CKD 3–5 patients and 19% of end-stage renal disease patients with genetic kidney diseases. Of the unknown, 40 were genotyped, of whom 31 had findings consistent with ADTKD. 30% of unknowns and 39% of unknowns with ADTKD had UMOD mutations. Altogether, 35 individuals from 18 families were found to have ten distinct UMOD mutations (three novel), making up 1% of patients with CKD 3–5, 2% of patients with end-stage renal disease, 9% of inherited kidney diseases and 56% with ADTKD. ADTKD-UMOD was the most common genetic kidney disease after ADPKD with a population prevalence of 9 per million. Less proteinuria and haematuria, but not hyperuricaemia or gout were predictive of ADTKD-UMOD. The main limitations of the study are the single-centre design and a predominantly Caucasian population. The prevalence of genetic kidney diseases and ADTKD-UMOD is significantly higher than previously described. Clinical features poorly predicted ADTKD-UMOD, highlighting the need for genetic testing guided by family history alone.

25 August 2022 in Journal of Crohn's and Colitis
Verified
Journal Article
Open access
PDF file
JAJames J Ashton
James J Ashton
ESEleanor G Seaby
Eleanor G Seaby
RBR Mark Beattie
R Mark Beattie
SESarah Ennis
Sarah Ennis
Studies of Crohn’s disease have consistently implicated NOD2 as the most important gene in disease pathogenesis since first being identified in 2001. Thereafter, genome-wide association, next-generation sequencing and functional analyses have all confirmed a key role for NOD2, but despite this, NOD2 also has significant unresolved complexity. More recent studies have reinvigorated an early hypothesis that NOD2 may be a single-gene cause of disease, and the distinct ileal stricturing phenotype seen with NOD2-related disease presents an opportunity for personalized diagnosis, disease prediction and targeted therapy. The genomics of NOD2 has much that remains unknown, including the role of rare variation, phasing of variants across the haplotype block and the role of variation in the NOD2-regulatory regions. Here, we discuss the evidence and the unmet needs of NOD2 research, based on recently published evidence, and suggest methods that may meet these requirements.

14 June 2022 in Inflammatory Bowel Diseases
Verified
Journal Article
Open access
PDF file
ISImogen S Stafford
Imogen S Stafford
MGMark M Gosink
Mark M Gosink
EMEnrico Mossotto
Enrico Mossotto
SESarah Ennis
Sarah Ennis
MHManfred Hauben
Manfred Hauben
Background: Inflammatory bowel disease (IBD) is a gastrointestinal chronic disease with an unpredictable disease course. Computational methods such as machine learning (ML) have the potential to stratify IBD patients for the provision of individualized care. The use of ML methods for IBD was surveyed, with an additional focus on how the field has changed over time.Methods: On May 6, 2021, a systematic review was conducted through a search of MEDLINE and Embase databases, with the search structure (“machine learning” OR “artificial intelligence”) AND (“Crohn* Disease” OR “Ulcerative Colitis” OR “Inflammatory Bowel Disease”). Exclusion criteria included studies not written in English, no human patient data, publication before 2001, studies that were not peer reviewed, nonautoimmune disease comorbidity research, and record types that were not primary research.Results: Seventy-eight (of 409) records met the inclusion criteria. Random forest methods were most prevalent, and there was an increase in neural networks, mainly applied to imaging data sets. The main applications of ML to clinical tasks were diagnosis (18 of 78), disease course (22 of 78), and disease severity (16 of 78). The median sample size was 263. Clinical and microbiome-related data sets were most popular. Five percent of studies used an external data set after training and testing for additional model validation.Discussion: Availability of longitudinal and deep phenotyping data could lead to better modeling. Machine learning pipelines that consider imbalanced data and that feature selection only on training data will generate more generalizable models. Machine learning models are increasingly being applied to more complex clinical tasks for specific phenotypes, indicating progress towards personalized medicine for IBD.