{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T11:20:13Z","timestamp":1792495213792,"version":"4.5.0"},"reference-count":35,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T00:00:00Z","timestamp":1713571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Iron-deficiency anemia (IDA) is a common health problem worldwide, and up to 10% of adult patients with incidental IDA may have gastrointestinal cancer. A diagnosis of IDA can be established through a combination of laboratory tests, but it is often underrecognized until a patient becomes symptomatic. Based on advances in machine learning, we hypothesized that we could reduce the time to diagnosis by developing an IDA prediction model. Our goal was to develop 3 neural networks by using retrospective longitudinal outpatient laboratory data to predict the risk of IDA 3 to 6 months before traditional diagnosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed retrospective outpatient electronic health record data between 2009 and 2020 from an academic medical center in northern Texas. We included laboratory features from 30,603 patients to develop 3 types of neural networks: artificial neural networks, long short-term memory cells, and gated recurrent units. The classifiers were trained using the Adam Optimizer across 200 random training-validation splits. We calculated accuracy, area under the receiving operating characteristic curve, sensitivity, and specificity in the testing split.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Although all models demonstrated comparable performance, the gated recurrent unit model outperformed the other 2, achieving an accuracy of 0.83, an area under the receiving operating characteristic curve of 0.89, a sensitivity of 0.75, and a specificity of 0.85 across 200 epochs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our results showcase the feasibility of employing deep learning techniques for early prediction of IDA in the outpatient setting based on sequences of laboratory data, offering a substantial lead time for clinical intervention.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ajcp\/aqae031","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T01:57:47Z","timestamp":1709171867000},"page":"243-251","source":"Crossref","is-referenced-by-count":11,"title":["Early identification of patients at risk for iron-deficiency anemia using deep learning techniques"],"prefix":"10.1093","volume":"162","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9821-0123","authenticated-orcid":false,"given":"Nelly Estefanie","family":"Garduno-Rapp","sequence":"first","affiliation":[{"name":"Clinical Informatics Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yee Seng","family":"Ng","sequence":"additional","affiliation":[{"name":"Department of Radiology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jenny L","family":"Weon","sequence":"additional","affiliation":[{"name":"Clinical Informatics Center"},{"name":"Department of Pathology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sameh N","family":"Saleh","sequence":"additional","affiliation":[{"name":"Clinical Informatics Center"},{"name":"Clinical Informatics, Inova Health System , Falls Church, VA , US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9559-4646","authenticated-orcid":false,"given":"Christoph U","family":"Lehmann","sequence":"additional","affiliation":[{"name":"Clinical Informatics Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenlu","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Digestive and Liver Disease, University of Texas Southwestern Medical Center , Dallas, TX , US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Quinn","sequence":"additional","affiliation":[{"name":"Department of Pathology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,4,20]]},"reference":[{"issue":"5","key":"2024090305545403600_CIT0001","first-page":"671","article-title":"Iron deficiency anemia","volume":"75","author":"Killip","year":"2007","journal-title":"Am Fam Physician."},{"key":"2024090305545403600_CIT0002","first-page":"15","article-title":"Anemia epidemiology, pathophysiology, and etiology in low- and middle-income countries","volume-title":"Ann N Y Acad Sci.","author":"Chaparro","year":"2019"},{"key":"2024090305545403600_CIT0003","first-page":"113","article-title":"Cytosolic iron-sulfur assembly is evolutionarily tuned by a cancer-amplified ubiquitin ligase","volume-title":"Mol Cell.","author":"Weon","year":"2018"},{"key":"2024090305545403600_CIT0004","first-page":"1588S","article-title":"Iron assessment to protect the developing brain","volume-title":"Am J Clin Nutr.","author":"Georgieff","year":"2017"},{"key":"2024090305545403600_CIT0005","first-page":"2529","article-title":"Setting the stage for child health and development: prevention of iron deficiency in early infancy","volume-title":"J Nutr.","author":"Chaparro","year":"2008"},{"key":"2024090305545403600_CIT0006","first-page":"153","article-title":"Iron deficiency anaemia revisited","volume-title":"J Intern Med.","author":"Cappellini","year":"2020"},{"key":"2024090305545403600_CIT0007","first-page":"225","article-title":"Iron deficiency: a concise review","volume-title":"Am J Hematol.","author":"Umbreit","year":"2005"},{"key":"2024090305545403600_CIT0008","first-page":"741","article-title":"Optimal management of iron deficiency anemia due to poor dietary intake","volume-title":"Int J Gen Med","author":"Aspuru","year":"2011"},{"key":"2024090305545403600_CIT0009","first-page":"615","article-title":"A systematic analysis of global anemia burden from 1990 to 2010","volume-title":"Blood.","author":"Kassebaum","year":"2014"},{"key":"2024090305545403600_CIT0010","first-page":"e2034406","article-title":"Prevalence of appropriate testing for incident anemia in the US Department of Veterans Affairs","volume-title":"JAMA Netw Open.","author":"Read","year":"2021"},{"key":"2024090305545403600_CIT0011","first-page":"a011866","article-title":"Iron deficiency anemia: a common and curable disease","volume-title":"Cold Spring Harb Perspect Med","author":"Miller","year":"2013"},{"key":"2024090305545403600_CIT0012","first-page":"75","article-title":"Iron metabolism: iron deficiency and iron overload","volume-title":"Annu Rev Genomics Hum Genet.","author":"Andrews","year":"2000"},{"key":"2024090305545403600_CIT0013","first-page":"163","article-title":"Iron deficiency anemia in colorectal cancer patients: is preoperative intravenous iron infusion indicated? A narrative review","volume-title":"Cancer Diagn Progn.","author":"Chardalias","year":"2023"},{"key":"2024090305545403600_CIT0014","first-page":"e0119647","article-title":"Risk of cancer in patients with iron deficiency anemia: a nationwide population-based study","volume-title":"PLoS One.","author":"Hung","year":"2015"},{"key":"2024090305545403600_CIT0015","first-page":"370","article-title":"Pre-operative anaemia: prevalence, consequences and approaches to management","volume-title":"Blood Transfus","author":"Mu\u00f1oz","year":"2015"},{"key":"2024090305545403600_CIT0016","first-page":"e13721","article-title":"Iron deficiency anemia as a rare risk factor for recurrent pulmonary embolism and deep vein thrombosis","volume-title":"Cureus","author":"Ezeh","year":"2021"},{"key":"2024090305545403600_CIT0017","first-page":"1234","article-title":"Anaemia and cognitive performances in the elderly: a systematic review","volume-title":"Eur J Neurol.","author":"Andro","year":"2013"},{"key":"2024090305545403600_CIT0018","first-page":"1216","article-title":"Iron deficiency anemia, not iron deficiency, is associated with reduced attention in healthy young women","volume-title":"Nutrients","author":"Cook","year":"2017"},{"key":"2024090305545403600_CIT0019","first-page":"220","article-title":"Diagnostic errors in primary care pediatrics: Project RedDE","volume-title":"Acad Pediatr","author":"Rinke","year":"2018"},{"key":"2024090305545403600_CIT0020","first-page":"1068","article-title":"Iron deficiency across chronic inflammatory conditions: international expert opinion on definition, diagnosis, and management","volume-title":"Am J Hematol.","author":"Cappellini","year":"2017"},{"key":"2024090305545403600_CIT0021","first-page":"1585","article-title":"Guidelines on the diagnosis and treatment of iron deficiency across indications: a systematic review","volume-title":"Am J Clin Nutr.","author":"Peyrin-Biroulet","year":"2015"},{"key":"2024090305545403600_CIT0022","first-page":"2057","article-title":"Artificial intelligence models for predicting iron deficiency anemia and iron serum level based on accessible laboratory data","volume-title":"J Med Syst.","author":"Azarkhish","year":"2012"},{"key":"2024090305545403600_CIT0023","first-page":"3083","article-title":"Predictive model for positive video capsule endoscopy in iron deficiency anemia","volume-title":"Dig Dis Sci.","author":"Hamdeh","year":"2023"},{"key":"2024090305545403600_CIT0024","first-page":"100179","article-title":"Artificial intelligence: a powerful paradigm for scientific research","volume-title":"Innovation (Camb).","author":"Xu","year":"2021"},{"key":"2024090305545403600_CIT0025","first-page":"1798","article-title":"Representation learning: a review and new perspectives","volume-title":"IEEE Trans Pattern Anal Mach Intell.","author":"Bengio","year":"2013"},{"key":"2024090305545403600_CIT0026","first-page":"1256351","article-title":"Trends in using deep learning algorithms in biomedical prediction systems","volume-title":"Front Neurosci.","author":"Wang","year":"2023"},{"key":"2024090305545403600_CIT0027","article-title":"Recurrent neural networks (RNNs): a gentle introduction and overview","author":"Schmidt","journal-title":"ArXiv"},{"key":"2024090305545403600_CIT0028","first-page":"1527","article-title":"Cyclic gate recurrent neural networks for time series data with missing values","volume-title":"Neural Process Lett.","author":"Weerakody","year":"2023"},{"key":"2024090305545403600_CIT0029","first-page":"40","article-title":"Are GRU cells more specific and LSTM cells more sensitive in motive classification of text","volume-title":"Front Artif Intell","author":"Gruber","year":"2020"},{"key":"2024090305545403600_CIT0030","first-page":"265","article-title":"Building a prediction model for iron deficiency anemia among infants in Shanghai, China","volume-title":"Food Sci Nutr.","author":"Zhang","year":"2019"},{"key":"2024090305545403600_CIT0031","first-page":"1921","article-title":"Automated prediction of low ferritin concentrations using a machine learning algorithm","volume-title":"Clin Chem Lab Med.","author":"Kurstjens","year":"2022"},{"key":"2024090305545403600_CIT0032","first-page":"2","article-title":"Detection of iron deficiency anemia by medical images: a comparative study of machine learning algorithms","volume-title":"BioData Min","author":"Appiahene","year":"2023"},{"key":"2024090305545403600_CIT0033","first-page":"e12667","article-title":"Iron deficiency anemia detection using machine learning models: a comparative study of fingernails, palm and conjunctiva of the eye images","volume-title":"Engineering Reports.","author":"Williams Asare","year":"2023"},{"key":"2024090305545403600_CIT0034","first-page":"e262","article-title":"Big data and machine learning algorithms for health-care delivery","volume-title":"Lancet Oncol.","author":"Ngiam","year":"2019"},{"key":"2024090305545403600_CIT0035","first-page":"445","article-title":"A clinician\u2019s guide to running custom machine-learning models in an electronic health record environment","volume-title":"Mayo Clin Proc.","author":"Ryu","year":"2023"}],"container-title":["American Journal of Clinical Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ajcp\/article-pdf\/162\/3\/243\/58953985\/aqae031.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ajcp\/article-pdf\/162\/3\/243\/58953985\/aqae031.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T01:56:55Z","timestamp":1725328615000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ajcp\/article\/162\/3\/243\/7655355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,20]]},"references-count":35,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,4,20]]},"published-print":{"date-parts":[[2024,9,3]]}},"URL":"https:\/\/doi.org\/10.1093\/ajcp\/aqae031","relation":{},"ISSN":["0002-9173","1943-7722"],"issn-type":[{"value":"0002-9173","type":"print"},{"value":"1943-7722","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9]]},"published":{"date-parts":[[2024,4,20]]}}}