A multicenter study on developing a prognostic model for severe fever with thrombocytopenia syndrome using machine learning

Frontiers in Microbiology, Год журнала: 2025, Номер 16

Опубликована: Март 19, 2025

Background Severe Fever with Thrombocytopenia Syndrome (SFTS) is a disease caused by infection the virus (SFTSV), novel Bunyavirus. Accurate prognostic assessment crucial for developing individualized prevention and treatment strategies. However, machine learning models SFTS are rare need further improvement clinical validation. Objective This study aims to develop validate an interpretable model based on (ML) methods enhance understanding of progression. Methods multicenter retrospective analyzed patient data from two provinces in China. The derivation cohort included 292 patients treated at Second Hospital Nanjing January 2022 December 2023, 7:3 split training internal external validation consisted 104 First Affiliated Wannan Medical College during same period. Twenty-four commonly available features were selected, Boruta algorithm identified 12 candidate predictors, ranked Z-scores, which progressively incorporated into 10 models. Model performance was assessed using area under receiver-operating-characteristic curve (AUC), accuracy, recall, F1 score. utility best-performing evaluated through decision analysis (DCA) net benefit. Robustness tested 10-fold cross-validation, feature importance explained SHapley Additive exPlanation (SHAP) both globally locally. Results Among models, XGBoost demonstrated best overall discriminatory ability. Considering AUC index simplicity, final 7 key constructed. showed high predictive accuracy outcomes (AUC = 0.911, 95% CI: 0.842–0.967) validations 0.891, 0.786–0.977). A tool this has been developed implemented Streamlit framework. Conclusion XGBoost-based shows translated tool. model's serve as valuable indicators early prognosis SFTS, warranting close attention healthcare professionals practice.

Язык: Английский

---

Erythrocytic indices of clinical blood analysis and reference intervals among men and women aged 18–45 years

Patient-Oriented Medicine and Pharmacy, Год журнала: 2025, Номер 2(4), С. 82 - 93

Опубликована: Фев. 3, 2025

Relevance. The determination of reference intervals (RI) in clinical blood analysis for erythrocytes and their specific parameters: mean corpuscular volume (MCV), hemoglobin (MCH), concentration (MCHC), red cell distribution width (RDW), allows us to use these parameters differential diagnostics various pathological conditions from variants norm. Objective. Calculate the RI erythrocyte a complete count patients certain age group (18– 45 years) with normal indicators iron homeostasis. ranges may vary depending on analytical systems diagnostic reagents used. Material methods. study included samples 158 healthy volunteers aged 18–45 years, whom 127 (80.4 %) were women 31 (19.6 men. data obtained «KDL-TEST» company database period 01.01.2023 01.01.2024. criteria inclusion were: 18 test results, homeostasis within laboratory, absence signs an inflammatory process based levels C-reactive protein (CRP). Analyses performed using hematological analyzer Mindray BC- 6800 (manufactured by Mindray, China) automatic biochemical model AU-5800 (Beckman Coulter, USA) IRON photometric colorimetric method CRP-latex immunoturbidimetric method. Results. studies revealed decrease upper limit cells (RBC) indices (RBC, HGB, HCT, MCV, MCH, MCHC, RDW-CV) compared Russian National Standard (2009), which amounted 4 % number cells, 5 hemoglobin, 2 hematocrit, 3.8 MCV 3.5 as well 4.2 MCHC; relation (2009) men 3.9 %, 4, 6 — 1.9 MCH MCHC 5.8 %. No significant differences found values parameters, between hematology analyzers BC-6800 Sysmex XE series (p >0.05). Conclusions. A some hemogram comparison are generally accepted statistically acceptable deviations, was found. automated did not significantly affect or parameters.

Язык: Английский

---

Extracting Data from Medical Records for Monitoring Diseases and Generating Medical Alerts

Romanian Journal of Military Medicine, Год журнала: 2024, Номер 127(6), С. 448 - 454

Опубликована: Июнь 20, 2024

Background: Automated data processing is creating and implementing technology that automatically processes data. This computer tool recommended for doctors because it supports their everyday work, assists in medical diagnosis, enhances patient care. The aim of this paper to propose an informatic can extract the values some parameters interest from blood test sheets order get alerts monitor chronic disease. Methods: An application, written Python, was developed Results: extracted glucose, triglycerides, HDL-cholesterol, total cholesterol, LDL-cholesterol (text-based file or graphic file, respectively), saved them a database, accessed represented form most recent these parameters; according metabolic syndrome criteria Framingham risk score were generated. Conclusions: contributes management process, saving precious time helping doctor detecting current future health problems.

Язык: Английский

---

Predicción Temprana del Dengue mediante Inteligencia Artificial: Un Enfoque basado en Análisis de Química Sanguínea Histórica

Estudios y Perspectivas Revista Científica y Académica, Год журнала: 2024, Номер 4(3), С. 2923 - 2936

Опубликована: Ноя. 25, 2024

El presente estudio se centra en el desarrollo de un sistema diagnóstico temprano del dengue mediante técnicas machine learning. Para ello, utiliza datos históricos recolectados Centro Salud la ciudad Tena. Esta investigación busca responder a necesidad contar con métodos diagnósticos más rápidos, accesibles y menos invasivos para dengue, especialmente regiones endémicas como nuestra. Se siguió una metodología basada Ciencia Diseño enfoque particular reducción dimensionalidad los datos. Además, implementaron ensamble Bagging Boosting mejorar robustez precisión modelos. Los resultados preliminares son promisorios. La combinación algoritmos ensamble, Boosting, mostró rendimiento superior detección alcanzando valor 0.6928. espera que, medida que profundice esta línea investigación, las herramientas desarrolladas contribuyan significativamente gestión salud pública dengue. Un preciso permitirá implementar intervenciones tempranas efectivas, reduciendo así morbilidad mortalidad asociadas enfermedad.

---

Smart medical report: efficient detection of common and rare diseases on common blood tests

Frontiers in Digital Health, Год журнала: 2024, Номер 6

Опубликована: Дек. 5, 2024

The integration of AI into healthcare is widely anticipated to revolutionize medical diagnostics, enabling earlier, more accurate disease detection and personalized care.

Язык: Английский

---