{"entity": "researcher", "timestamp": "2026-08-20T21:02:22.872Z", "family": "Eriksson", "given": "Lars E", "initials": "LE", "orcid": "0000-0001-5121-5325", "affiliations": ["Division of Innovative Care Research, Department of Learning, Informatics, Management and Ethics (LIME), Karolinska Institutet, SE-171 77, Solna, Sweden. lars.eriksson@ki.se.", "School of Health Sciences, City, University of London, Northampton Square, London, EC1V 0HB, United Kingdom. lars.eriksson@ki.se.", "Department of Infectious Diseases, Karolinska University Hospital, SE-141 86, Huddinge, Sweden. lars.eriksson@ki.se."], "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/researcher/a6583e7b1b0d4dc38d27eb8ad50f1add.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/researcher/a6583e7b1b0d4dc38d27eb8ad50f1add"}}, "publications": [{"entity": "publication", "iuid": "3113ee5c7c5e42c8a0831e62b2e2c8f6", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/3113ee5c7c5e42c8a0831e62b2e2c8f6.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/3113ee5c7c5e42c8a0831e62b2e2c8f6"}}, "title": "Early symptoms and sensations as predictors of lung cancer: a machine learning multivariate model.", "authors": [{"family": "Levitsky", "given": "Adrian", "initials": "A", "orcid": "0000-0003-4821-0691", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/56d2c32efba54cfe88679bc007c67854.json"}}, {"family": "Pernemalm", "given": "Maria", "initials": "M", "orcid": "0000-0003-4624-031X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/c34e0806a3d142019ae8e16de8d720ef.json"}}, {"family": "Bernhardson", "given": "Britt-Marie", "initials": "BM"}, {"family": "Forshed", "given": "Jenny", "initials": "J"}, {"family": "K\u00f6lbeck", "given": "Karl", "initials": "K"}, {"family": "Olin", "given": "Maria", "initials": "M"}, {"family": "Henriksson", "given": "Roger", "initials": "R"}, {"family": "Lehti\u00f6", "given": "Janne", "initials": "J", "orcid": "0000-0002-8100-9562", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/561efcf32e2648c8a10fee692fc4e908.json"}}, {"family": "Tishelman", "given": "Carol", "initials": "C"}, {"family": "Eriksson", "given": "Lars E", "initials": "LE", "orcid": "0000-0001-5121-5325", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a6583e7b1b0d4dc38d27eb8ad50f1add.json"}}], "type": "journal article", "published": "2019-11-11", "journal": {"title": "Sci Rep", "issn": "2045-2322", "volume": "9", "issue": "1", "pages": "16504", "issn-l": "2045-2322"}, "abstract": "The aim of this study was to identify a combination of early predictive symptoms/sensations attributable to primary lung cancer (LC). An interactive e-questionnaire comprised of pre-diagnostic descriptors of first symptoms/sensations was administered to patients referred for suspected LC. Respondents were included in the present analysis only if they later received a primary LC diagnosis or had no cancer; and inclusion of each descriptor required \u22654 observations. Fully-completed data from 506/670 individuals later diagnosed with primary LC (n = 311) or no cancer (n = 195) were modelled with orthogonal projections to latent structures (OPLS). After analysing 145/285 descriptors, meeting inclusion criteria, through randomised seven-fold cross-validation (six-fold training set: n = 433; test set: n = 73), 63 provided best LC prediction. The most-significant LC-positive descriptors included a cough that varied over the day, back pain/aches/discomfort, early satiety, appetite loss, and having less strength. Upon combining the descriptors with the background variables current smoking, a cold/flu or pneumonia within the past two years, female sex, older age, a history of COPD (positive LC-association); antibiotics within the past two years, and a history of pneumonia (negative LC-association); the resulting 70-variable model had accurate cross-validated test set performance: area under the ROC curve = 0.767 (descriptors only: 0.736/background predictors only: 0.652), sensitivity = 84.8% (73.9/76.1%, respectively), specificity = 55.6% (66.7/51.9%, respectively). In conclusion, accurate prediction of LC was found through 63 early symptoms/sensations and seven background factors. Further research and precision in this model may lead to a tool for referral and LC diagnostic decision-making.", "doi": "10.1038/s41598-019-52915-x", "pmid": "31712735", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC6848139"}, {"db": "pii", "key": "10.1038/s41598-019-52915-x"}], "notes": [], "created": "2026-08-20T09:04:42.059Z", "modified": "2026-08-20T09:04:42.195Z"}]}