Laboratory medicine最新文献

Development and evaluation of a prognostic model for patients with sepsis based on laboratory indicators. 基于实验室指标的脓毒症患者预后模型的开发和评估。

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag076

Meiyan Shu, Jianfang Lou, Qiuxia Ge

{"title":"Development and evaluation of a prognostic model for patients with sepsis based on laboratory indicators.","authors":"Meiyan Shu, Jianfang Lou, Qiuxia Ge","doi":"10.1093/labmed/lmag076","DOIUrl":"https://doi.org/10.1093/labmed/lmag076","url":null,"abstract":"Introduction: Early risk stratification in sepsis remains challenging due to disease heterogeneity. We developed a nomogram based on admission laboratory results to facilitate early triage and personalized care.Methods: We analyzed 162 patients with sepsis admitted between January 2023 and December 2024 (48 with a poor prognosis, 114 who improved). Demographic data, clinical scores (Sequential Organ Failure Assessment, Glasgow Coma Scale), and 24‑hour admission laboratory parameters were collected. Least absolute shrinkage and selection operator (LASSO) regression was applied for feature selection, followed by nomogram construction. Model performance was assessed by receiver operating characteristic curves, calibration plots, and concordance index.Results: LASSO regression identified the Sequential Organ Failure Assessment score (odds ratio [OR], 1.271 [95% CI, 1.153-1.402), Glasgow Coma Scale score (OR, 0.807 [95% CI, 0.745-0.875]), serum urea nitrogen (OR, 1.097 [95% CI, 1.054-1.142]), and interleukin 6 (OR, 1.001 [95% CI, 1.000-1.001]) as independent predictors of poor prognosis in patients with sepsis. The nomogram showed concordance indices of 0.806 (95% CI, 0.716-0.896) in the training set and 0.889 (95% CI, 0.766-1.000) in the testing set. Sensitivity and specificity were 85.0% and 68.8% (training) and 87.9% and 86.7% (testing), respectively. Calibration curves demonstrated good agreement between predicted and observed outcomes.Discussion: The LASSO‑based nomogram exhibited discriminative ability for sepsis prognosis. It may serve as a practical tool for early risk stratification, supporting timely optimization of therapeutic strategies and improving patient outcomes.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149149822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Construction of a new reflex fluorescence platelet count confirmation model based on red blood cell and platelet parameters. 基于红细胞和血小板参数的反射荧光血小板计数确认新模型的建立。

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag070

Wenjun Zhu, Zijian Zhang, Jinan Jiang, Huimin Chong, Shaoli Deng, Jinmi Li

{"title":"Construction of a new reflex fluorescence platelet count confirmation model based on red blood cell and platelet parameters.","authors":"Wenjun Zhu, Zijian Zhang, Jinan Jiang, Huimin Chong, Shaoli Deng, Jinmi Li","doi":"10.1093/labmed/lmag070","DOIUrl":"https://doi.org/10.1093/labmed/lmag070","url":null,"abstract":"Introduction: We sought to clarify the interference of red blood cell (RBC) and platelet (PLT) parameters on PLT count by impedance method results and establish an intelligent reflex fluorescence PLT count (PLT-F) confirmation model using PLT-F as the reference to quantify the model's clinical efficacy.Methods: A retrospective analysis was performed on routine blood data from 11 283 patients (June 2023 to February 2024) at our hospital. Patients were stratified into a training set (n = 7898) and verification set (n = 3385) using Laboman AI, version 1.0-312, software (Shanghai Hyson Meikang Medical Electronics Co Ltd). A decision tree algorithm was employed to construct a new model that integrates RBC and PLT parameters for reflex PLT-F confirmation, and the model's effectiveness was evaluated.Results: The combined 3-factor model achieved optimal performance for PLT-F reflex confirmation. Its overall false-negative proportion, release rate, total effective rate, and negative predictive value reached 2.9%, 55.2%, 71.1%, and 94.7%, respectively, in the training set, with matching values of 4.2%, 52.4%, 66.1%, and 91.9%, respectively, in the validation set.Discussion: This study established a novel reflex PLT-F confirmation model based on RBC and PLT parameters. The model achieved a 52.4% sample release rate, with a corresponding overall false-negative proportion of 4.2% in the validation set, presenting a clear trade-off between laboratory operational efficiency and diagnostic safety.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149120941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Frequency of anti-ɑ-fodrin antibodies in adult patients with active celiac disease. 成人活动性乳糜泻患者抗-fodrin抗体的频率。

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag080

Amani Ifaoui, Moez Frikha, Sarra Melayah, Mariam Ghozzi

{"title":"Frequency of anti-ɑ-fodrin antibodies in adult patients with active celiac disease.","authors":"Amani Ifaoui, Moez Frikha, Sarra Melayah, Mariam Ghozzi","doi":"10.1093/labmed/lmag080","DOIUrl":"https://doi.org/10.1093/labmed/lmag080","url":null,"abstract":"Introduction: Sjögren disease and celiac disease share autoimmune pathogenesis, and their association is well established. Anti-ɑ-fodrin antibodies (AFAs) are recognized markers of Sjögren disease, yet their prevalence in celiac disease has not been assessed. We sought to determine the frequency of AFAs (immunoglobulin A [IgA] and IgG) in adult patients with active celiac disease and compare it with that of a healthy control group.Methods: A total of 81 adult patients with active celiac disease confirmed by serology and duodenal biopsy were retrospectively included. A total of 90 age-matched and sex-matched healthy blood donors served as controls. The AFAs IgA and IgG were detected by enzyme-linked immunosorbent assay.Results: We detected AFAs (IgA or IgG) in 33 of 81 (40.74%) of patients with celiac disease vs 7 of 90 (7.78%) control individuals (P < 10-6; odds ratio, 8.15). Immunoglobulin A was the predominant isotype (39.51% vs 4.44%, P < 10-6; odds ratio, 14.04).Discussion: Anti-ɑ-fodrin antibodies are considerably more prevalent in active celiac disease than in healthy control individuals. Because clinical signs of Sjögren disease were absent in our patients, the specificity of AFAs for the disease requires reevaluation. Long-term follow-up of seropositive patients is warranted to determine whether they may develop Sjögren disease.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149225615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The relationship between D-dimer and the risk for adverse outcomes in patients with heart failure. d -二聚体与心力衰竭患者不良结局风险的关系。

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag072

Xiaoxi He, Ruiping Zheng, Ruigui Zheng

{"title":"The relationship between D-dimer and the risk for adverse outcomes in patients with heart failure.","authors":"Xiaoxi He, Ruiping Zheng, Ruigui Zheng","doi":"10.1093/labmed/lmag072","DOIUrl":"https://doi.org/10.1093/labmed/lmag072","url":null,"abstract":"Introduction: Insufficient evidence exists for the association between serum dimerized plasmin fragment D (D-dimer), a biomarker for screening thromboembolic diseases, and adverse outcomes in patients with heart failure (HF).We investigated the association between serum D-dimer and the risk of readmission and all-cause mortality in patients with HF.Methods: We enrolled 1575 patients hospitalized with HF in China between 2016 and 2019. We explored the smooth curve of the nonlinear relationship between serum D-dimer and adverse outcomes. Logistic regression and saturation threshold analyses were also conducted.Results: Smooth curve analysis revealed an inverted U-shaped association between serum D-dimer concentrations and 6-month all-cause mortality. The turning point for serum D-dimer concentration in patients with HF in the highest 6-month mortality risk group was 7.6 mg/L. Among patients with a D-dimer concentration below 7.6 mg/L, each 1-mg/L increase in D-dimer concentration independently contributed to a 20% higher risk for all-cause mortality, independent of other clinical covariates. Regarding readmission risk, smooth curve analysis supported an obvious relationship between serum D-dimer and 6-month readmission risk. Surprisingly, each 1-mg/L increase in D-dimer concentration was independently associated with a 4% lower risk for readmission within 6 months.Discussion: Elevated serum D-dimer concentrations have a strong association with increased risk for 6-month mortality, providing evidence for early risk stratification in HF prognosis.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149120923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Measles (rubeola) virus qualitative real-time reverse transcription-polymerase chain reaction assay: development and clinical validation on an automated workflow. 麻疹（风疹）病毒定性实时逆转录-聚合酶链反应测定：自动化工作流程的开发和临床验证。

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag075

Lan Yu, Li Chen, Kevin Dumas, Nickolas Weyandt, Michael Meyers, Pei Irwin, Jennifer L Eitson, John W Schoggins, Jason Y Park

{"title":"Measles (rubeola) virus qualitative real-time reverse transcription-polymerase chain reaction assay: development and clinical validation on an automated workflow.","authors":"Lan Yu, Li Chen, Kevin Dumas, Nickolas Weyandt, Michael Meyers, Pei Irwin, Jennifer L Eitson, John W Schoggins, Jason Y Park","doi":"10.1093/labmed/lmag075","DOIUrl":"https://doi.org/10.1093/labmed/lmag075","url":null,"abstract":"Introduction: Detection of Measles virus (MeV) RNA is an important method for confirming infection. This study described the clinical validation of a qualitative real-time reverse transcriptase-polymerase chain reaction (RT-PCR) assay for MeV detection.Methods: A real-time RT-PCR assay was developed and validated using primers and probes previously reported in the literature. The assay was evaluated using reference materials, cultured virus, and previously tested clinical throat swab samples. An automated workflow was established for RNA extraction, RT-PCR amplification, and result reporting using robotic platforms and a real-time PCR instrument. The assay targets the measles nucleoprotein (N) and hemagglutinin (H) genes, with human RNase P gene used as an internal control.Results: The MeV RT-PCR assay has a limit of detection of 500 genome copies per milliliter. The assay was tested against 85 different samples: 50 positive clinical samples and reference materials and 35 negative clinical samples or reference materials. All expected results were correctly identified, giving 100% sensitivity (50/50) and specificity (35/35). The assay showed 100% interassay and intra-assay reproducibility. No cross-reactivity was observed with other respiratory viruses or common bacterial and fungal pathogens.Discussion: This automated measles RT-PCR assay demonstrated high accuracy, sensitivity, specificity, and reproducibility.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149149066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development and internal validation of a diagnostic prediction model for advanced liver fibrosis based on routine laboratory indicators. 基于常规实验室指标的晚期肝纤维化诊断预测模型的开发和内部验证。

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag053

Junjie Deng, Wen Song, Yuyu Ma, Bin Fan, Xiumin Ma, Yumei Liu

{"title":"Development and internal validation of a diagnostic prediction model for advanced liver fibrosis based on routine laboratory indicators.","authors":"Junjie Deng, Wen Song, Yuyu Ma, Bin Fan, Xiumin Ma, Yumei Liu","doi":"10.1093/labmed/lmag053","DOIUrl":"https://doi.org/10.1093/labmed/lmag053","url":null,"abstract":"Introduction: Advanced liver fibrosis is a clinically important stage of chronic liver disease. We developed and internally validated an interpretable model based on routine laboratory tests and benchmarked it against the aspartate aminotransferase to platelet ratio index (APRI) and 4-factor fibrosis index (FIB-4).Methods: This single-center, retrospective, diagnostic prediction study included 1853 inpatients, of whom 988 had report-defined F3 to F4 fibrosis. Primary validation used 10 repeated, stratified 7:3 outer resamples, with preprocessing, least absolute shrinkage and selection operator selection, and model refitting restricted to each development subset. Discrimination, calibration, decision curves, precision recall performance, and linear SHapley Additive exPlanations values were evaluated.Results: The leakage-aware pipeline achieved a mean (SD) validation area under the curve of 0.800 (0.015), accuracy of 0.753, sensitivity of 0.775, and specificity of 0.729. The final logistic model included platelet count, total bile acids, C3 and C4, red blood cell count, lymphocyte count, and albumin level. In the representative test set, its area under the curve was 0.809 (95% CI, 0.772-0.845) compared with 0.815 for APRI and 0.821 for FIB-4; neither paired difference was statistically significant after Holm adjustment.Discussion: The model showed moderate discrimination and interpretable output but was not superior to APRI or FIB-4. External validation is required before clinical implementation.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149149695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Flow cytometry in the diagnosis and monitoring of lymphoma based on urine samples: a case report. 流式细胞术在基于尿液样本的淋巴瘤诊断和监测中的应用：1例报告。

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag077

Shuaiyan Wang, Yanping Luo, Hongmei Mo

{"title":"Flow cytometry in the diagnosis and monitoring of lymphoma based on urine samples: a case report.","authors":"Shuaiyan Wang, Yanping Luo, Hongmei Mo","doi":"10.1093/labmed/lmag077","DOIUrl":"https://doi.org/10.1093/labmed/lmag077","url":null,"abstract":"Introduction: Diffuse large B-cell lymphoma rarely presents primarily with urinary symptoms, making noninvasive diagnosis challenging. We report a case in which urine flow cytometry substantially aided diagnosis and monitoring.Methods: A 67-year-old man presenting with gross hematuria and painful urination underwent cystoscopy with biopsy and urine flow cytometry. B-cell immunophenotyping was performed using a targeted CD marker panel, and residual disease was tracked longitudinally after chemotherapy.Results: Histopathology suggested aggressive B-cell lymphoma. Urine flow cytometry identified an abnormal mature B-cell population (20.36% of nucleated cells) expressing CD45, CD19, CD20, CD10, FMC7, and λ, confirming a CD5-negative/CD10-positive phenotype. Following treatment with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone, the percentage of abnormal urinary B cells declined to 0.41% at 2 weeks, 0.18% at 1 month, and 0% at 3 months, coinciding with partial clinical remission.Discussion: Urine flow cytometry is a highly accessible, noninvasive, and effective tool. It provides critical diagnostic value and quantitative monitoring utility for hematologic malignancies involving the urinary tract and should complement-not replace-histopathology and urine cytology.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149187132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analytical discrepancy in platelet counting in MYH9-related disease: a case report. myh9相关疾病血小板计数差异分析1例

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag078

Marco De Girolamo, Anna Marrocchi, Francesca Vitone, Margherita Scapaticci, Monica Bovara, Tommaso Paolo Papillo, Rita Mancini

{"title":"Analytical discrepancy in platelet counting in MYH9-related disease: a case report.","authors":"Marco De Girolamo, Anna Marrocchi, Francesca Vitone, Margherita Scapaticci, Monica Bovara, Tommaso Paolo Papillo, Rita Mancini","doi":"10.1093/labmed/lmag078","DOIUrl":"10.1093/labmed/lmag078","url":null,"abstract":"Introduction: MYH9-related disease (MYH9-RD) is a rare autosomal dominant disorder characterized by congenital macrothrombocytopenia, with giant platelets and variable extrahematologic manifestations. It is frequently underdiagnosed and misclassified as immune thrombocytopenia.Methods: A 31-year-old pregnant woman undergoing routine first-trimester testing was shown to have severe thrombocytopenia (platelet count = 5.000 × 10³/µL) by impedance counting.Results: Platelet histograms and scattergrams generated on a Sysmex XN-10 hematology analyzer suggested giant platelets, while fluorescence counting using a Sysmex XN-20 hematology analyzer yielded a higher platelet count (19.000 × 10³/µL), considered a more plausible estimate in the presence of giant platelets. Peripheral blood smear examination excluded platelet clumping and demonstrated numerous giant platelets and basophilic neutrophilic inclusions, subsequently interpreted as Döhle-like bodies. Further medical history revealed a previous diagnosis of MYH9-RD. Longitudinal evaluation showed persistently low but stable platelet counts, no kidney involvement, and mild liver enzyme elevation.Discussion: This case highlights the diagnostic value of integrating automated hematology data with peripheral blood smear examination in inherited macrothrombocytopenias. Platelet counts in the presence of giant platelets may be underestimated by impedance-based analyzers because of size-dependent misclassification, whereas fluorescence-based counting may provide a more reliable estimate. Recognition of characteristic morphologic features, including Döhle-like bodies, is essential for identifying MYH9-RD and distinguishing it from immune thrombocytopenia, thereby avoiding inappropriate diagnostic and therapeutic interventions.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13671753/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149198730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Vitamin B12 biomarker patterns and kidney function in US adults: National Health and Nutrition Examination Survey 2011-2012. 美国成年人维生素B12生物标志物模式和肾功能：2011-2012年全国健康与营养检查调查

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag082

Ashley M Foulkrod, Elliott V Rebello, Thomas A Beltran, Erica L Gigas, Carlos J Maldonado

{"title":"Vitamin B12 biomarker patterns and kidney function in US adults: National Health and Nutrition Examination Survey 2011-2012.","authors":"Ashley M Foulkrod, Elliott V Rebello, Thomas A Beltran, Erica L Gigas, Carlos J Maldonado","doi":"10.1093/labmed/lmag082","DOIUrl":"https://doi.org/10.1093/labmed/lmag082","url":null,"abstract":"Introduction: Total serum vitamin B12 levels may not align with biomarkers of circulating active vitamin B12 or intracellular vitamin B12-dependent metabolism. We estimated the population prevalence of marker-defined discordance among US adults and examined the influence of kidney function.Methods: We analyzed National Health and Nutrition Examination Survey 2011-2012 data from 4318 adults with total vitamin B12, holotranscobalamin (holoTC), and methylmalonic acid (MMA) measurements and positive holoTC subsample weights. Low total vitamin B12 was defined as a level less than 200 pg/mL (148 pmol/L), low holoTC as a level less than 35 pmol/L, and elevated MMA as a level greater than 300 nmol/L. Analyses incorporated survey weights, strata, and primary sampling units.Results: Low total vitamin B12 was present in 1.7% of adults compared with low holoTC in 4.7% of adults and elevated MMA in 6.5% of adults. Overall, 9.7% of adults had low holoTC or elevated MMA. Among these adults, 60.6% had total vitamin B12 levels greater than 300 pg/mL. In a secondary integrated analysis, 2.2% (95% CI, 1.5%-2.9%) had a 3-marker combined vitamin B12 indicator less than -0.5. Methylmalonic acid-based discordance increased with declining estimated glomerular filtration rate.Discussion: Marker-defined low holoTC or elevated MMA was more common than low total vitamin B12. Methylmalonic acid should be interpreted in the context of kidney function.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149229675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Routine laboratory panels classify internal medicine ICD-10 code groups: comparison with frontier large language models and laboratory-only specialist assessment. 常规实验室小组对内科ICD-10代码组进行分类：与前沿大语言模型和仅实验室专家评估的比较。

IF 1

Laboratory medicine Pub Date : 2026-10-05 DOI: 10.1093/labmed/lmag074

Yusuf Yesil, Alpay Medetalibeyoglu, Evin Ademoglu

{"title":"Routine laboratory panels classify internal medicine ICD-10 code groups: comparison with frontier large language models and laboratory-only specialist assessment.","authors":"Yusuf Yesil, Alpay Medetalibeyoglu, Evin Ademoglu","doi":"10.1093/labmed/lmag074","DOIUrl":"https://doi.org/10.1093/labmed/lmag074","url":null,"abstract":"Introduction: Routine laboratory panels are nearly universal, but the panels' joint information is underused. We evaluated contemporaneous classification of International Statistical Classification of Diseases, Tenth Revision (ICD-10) code groups from same-encounter laboratory results.Methods: We developed 17 eXtreme Gradient Boosting (XGBoost) classifiers in 242 648 adult internal medicine encounters using age, sex, and results from 34 assays, with ICD-10 codes used only as outcomes. Stratified 10-fold cross-validation assessed discrimination, calibration, and decision curve performance. Leakage-free recalibration and fold-specific thresholds targeted 95% specificity. Using an 80-patient temporal holdout cohort, we compared the model with 3 large language models accessed through an application programming interface and findings from 1 specialist physician.Results: The mean cross-validated area under the curve (AUC) was 0.893. With identical preprocessing, the mean AUC was 0.892 for XGBoost and 0.809 for logistic regression. Recalibration changed the mean intercept and slope to -0.002 and 0.999, respectively, and the Brier score from 0.099 to 0.044. The holdout micro-averaged AUC was 0.880 vs 0.729 to 0.739 for language models; paired differences were 0.141 to 0.151 (all P < .005). Matched-specificity sensitivity differences favored the model but were imprecise.Discussion: Routine panels contain substantial information about contemporaneous ICD-10 coding, supporting prospective multicenter evaluation rather than a diagnostic claim.","PeriodicalId":94124,"journal":{"name":"Laboratory medicine","volume":"57 6","pages":""},"PeriodicalIF":1.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149120989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0