{"doi":"10.1177/10406387221096781","title":"Use of machine-learning algorithms to aid in the early detection of leptospirosis in dogs","abstract":"<jats:p>Leptospirosis is a life-threatening, zoonotic disease with various clinical presentations, including renal injury, hepatic injury, pancreatitis, and pulmonary hemorrhage. With prompt recognition of the disease and treatment, 90% of infected dogs have a positive outcome. Therefore, rapid, early diagnosis of leptospirosis is crucial. Testing for Leptospira-specific serum antibodies using the microscopic agglutination test (MAT) lacks sensitivity early in the disease process, and diagnosis can take &gt;2 wk because of the need to demonstrate a rise in titer. We applied machine-learning algorithms to clinical variables from the first day of hospitalization to create machine-learning prediction models (MLMs). The models incorporated patient signalment, clinicopathologic data (CBC, serum chemistry profile, and urinalysis = blood work [BW] model), with or without a MAT titer obtained at patient intake (=BW + MAT model). The models were trained with data from 91 dogs with confirmed leptospirosis and 322 dogs without leptospirosis. Once trained, the models were tested with a cohort of dogs not included in the model training (9 leptospirosis-positive and 44 leptospirosis-negative dogs), and performance was assessed. Both models predicted leptospirosis in the test set with 100% sensitivity (95% CI: 70.1–100%). Specificity was 90.9% (95% CI: 78.8–96.4%) and 93.2% (95% CI: 81.8–97.7%) for the BW and BW + MAT models, respectively. Our MLMs outperformed traditional acute serologic screening and can provide accurate early screening for the probable diagnosis of leptospirosis in dogs.</jats:p>","journal":"Journal of Veterinary Diagnostic Investigation","year":2022,"id":617967,"datarank":0.4636563680037475,"base_score":3.091042453358316,"endowment":3.091042453358316,"self_citation_contribution":0.4636563680037475,"citation_network_contribution":0.0,"self_endowment_contribution":0.4636563680037475,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":21,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1593888,"name":"Shaofeng Deng","orcid":"0000-0002-7269-393X","position":1,"is_corresponding":false},{"id":1305420,"name":"Junda Sheng","orcid":null,"position":2,"is_corresponding":false},{"id":1593889,"name":"Jamie Sebastian","orcid":null,"position":3,"is_corresponding":false},{"id":677843,"name":"Zhe Wang","orcid":"0000-0001-9232-3699","position":4,"is_corresponding":false},{"id":1593890,"name":"Sara N. Huebner","orcid":null,"position":5,"is_corresponding":false},{"id":1593891,"name":"Louise A. Wenke","orcid":null,"position":6,"is_corresponding":false},{"id":951377,"name":"Sarah R. Michalak","orcid":"0000-0002-9575-1303","position":7,"is_corresponding":false},{"id":973798,"name":"Thomas Strohmer","orcid":"0000-0003-2029-3317","position":8,"is_corresponding":false},{"id":536167,"name":"Jane E. Sykes","orcid":"0000-0002-6814-9835","position":9,"is_corresponding":false},{"id":881980,"name":"Krystle L. Reagan","orcid":"0000-0003-3426-6352","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Use of machine-learning algorithms to aid in the early detection of leptospirosis in dogs","abstract":"<jats:p>Leptospirosis is a life-threatening, zoonotic disease with various clinical presentations, including renal injury, hepatic injury, pancreatitis, and pulmonary hemorrhage. With prompt recognition of the disease and treatment, 90% of infected dogs have a positive outcome. Therefore, rapid, early diagnosis of leptospirosis is crucial. Testing for Leptospira-specific serum antibodies using the microscopic agglutination test (MAT) lacks sensitivity early in the disease process, and diagnosis can take &gt;2 wk because of the need to demonstrate a rise in titer. We applied machine-learning algorithms to clinical variables from the first day of hospitalization to create machine-learning prediction models (MLMs). The models incorporated patient signalment, clinicopathologic data (CBC, serum chemistry profile, and urinalysis = blood work [BW] model), with or without a MAT titer obtained at patient intake (=BW + MAT model). The models were trained with data from 91 dogs with confirmed leptospirosis and 322 dogs without leptospirosis. Once trained, the models were tested with a cohort of dogs not included in the model training (9 leptospirosis-positive and 44 leptospirosis-negative dogs), and performance was assessed. Both models predicted leptospirosis in the test set with 100% sensitivity (95% CI: 70.1–100%). Specificity was 90.9% (95% CI: 78.8–96.4%) and 93.2% (95% CI: 81.8–97.7%) for the BW and BW + MAT models, respectively. Our MLMs outperformed traditional acute serologic screening and can provide accurate early screening for the probable diagnosis of leptospirosis in dogs.</jats:p>","is_dataset_classified":null,"base_score":3.091042453358316,"endowment":3.091042453358316,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"35603565","pmcid":"PMC9266510","openalex_id":"https://openalex.org/W4281255420","authors":[],"funders":[{"funder_name":"national science foundation","grant_id":"NSF-DMS-1737943, NSF DMS-2027248, and NSF CCF-193","title":null},{"funder_name":"National Science Foundation","grant_id":"2027248","title":"ATD: A Mathematical Framework for Generating Synthetic Data"},{"funder_name":"National Science Foundation","grant_id":"1737943","title":"ATD: Multimode Machine Learning and Deep GeoNetworks for Anomaly Detection"}],"total_grants":3,"fwci":3.2735,"citation_percentile":0.91778056,"influential_citations":0,"citation_trend":[{"year":2023,"count":6},{"year":2024,"count":4},{"year":2025,"count":9},{"year":2026,"count":2}],"oa_status":"hybrid","license":"cc-by","oa_locations":[{"url":"https://doi.org/10.1177/10406387221096781","host_type":"journal"},{"url":"https://doi.org/10.1177/10406387221096781","host_type":"publisher"},{"url":"https://journals.sagepub.com/doi/pdf/10.1177/10406387221096781","host_type":"publisher"},{"url":"https://journals.sagepub.com/doi/full-xml/10.1177/10406387221096781","host_type":"publisher"},{"url":"https://pubmed.ncbi.nlm.nih.gov/35603565","host_type":"repository"},{"url":"https://escholarship.org/uc/item/0481k543","host_type":"repository"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9266510","host_type":"repository"},{"url":"https://europepmc.org/articles/PMC9266510","host_type":"Europe_PMC"},{"url":"https://europepmc.org/articles/PMC9266510?pdf=render","host_type":"Europe_PMC"},{"url":"http://dx.doi.org/10.1177/10406387221096781","host_type":""},{"url":"https://escholarship.org/content/qt0481k543/qt0481k543.pdf","host_type":""},{"url":"https://doi.org/https://doi.org/10.1177/10406387221096781","host_type":""}],"fields_of_study":["Leptospirosis research and findings","Viral Infections and Vectors","Yersinia bacterium, plague, ectoparasites research","0403 veterinary science","04 agricultural and veterinary sciences","Agglutination Tests","Algorithms","Animals","Antibodies, Bacterial","Dog Diseases","Dogs","Early Diagnosis","Humans","Leptospira","Leptospirosis","Machine Learning"],"mesh_terms":["Machine Learning","Agglutination Tests","Algorithms","Animals","Antibodies, Bacterial","Dog Diseases","Dogs","Humans","Leptospira","Leptospirosis","Early Diagnosis"],"keywords":["Leptospirosis","Artificial intelligence","Machine learning","Computer science","Medicine","Algorithm","Virology","Infection","Kidney","Leptospira","Dogs","Veterinary sciences","Veterinary and Food Sciences","Antibodies","Agglutination Tests","Behavioral and Social Science","Animals","Humans","Full Scientific Reports","Dog Diseases","Agricultural","screening and diagnosis","Prevention","Bacterial","600","Antibodies, Bacterial","4.1 Discovery and preclinical testing of markers and technologies","Detection","Good Health and Well Being","Early Diagnosis","Digestive Diseases","Zoology","Algorithms","4.2 Evaluation of markers and technologies"],"sdg_mappings":[{"sdg_number":3,"sdg_label":"3. Good health"},{"sdg_number":0,"sdg_label":"Good health and well-being"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-03T03:06:13.903827Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}