RESUMO
The demand for Janus Kinase-2 (JAK2) testing has been disproportionate to the low yield of positive results, which highlights the need for more discerning test strategies. The aim of this study is to introduce an artificial intelligence application as a more rational approach for testing JAK2 mutations in cases of erythrocytosis. Test results were sourced from samples sent to a tertiary hospital's genetic laboratory between 2017 and 2023, meeting 2016 World Health Organization criteria for JAK2V617F mutation testing. The JAK2 Somatic Mutation Screening Kit was used for genetic testing. Machine learning models were trained and tested using Python programming language. Out of 458 cases, JAK2V617F mutation was identified in 13.3%. There were significant differences in complete blood count parameters between mutation carriers and non-carriers. Various models were trained with data, with the random forest (RF) model demonstrating superior precision, recall, F1-score, accuracy, and area under the receiver operating characteristic, all reaching 100%. Gradient boosting (GB) model also showed high scores. When compared with existing algorithms, the RF and GB models displayed superior performance. The RF and GB models outperformed other methods in accurately identifying and classifying erythrocytosis cases, offering potential reductions in unnecessary testing and costs.
Assuntos
Inteligência Artificial , Policitemia , Humanos , Aprendizado de Máquina , Algoritmos , Hemoglobinas , Janus Quinase 2/genéticaRESUMO
PURPOSE: To determine the association between fetal fraction (FF) levels in cell-free fetal DNA (cffDNA) testing and adverse pregnancy outcomes. METHODS: This retrospective cohort study, conducted at a single center, involved 2063 pregnant women with normal 1st and 2nd trimester non-invasive prenatal test (NIPT) results between 2016 and 2021. Pregnancy outcomes were examined by determining the < 4% and < 5th percentile (3.6%) cut-off values for low fetal fraction (LFF). Pregnancy outcomes were also examined by dividing the FF into population-based quartiles. Adverse pregnancy outcomes were pregnancy-induced hypertensive diseases (PIHD), gestational diabetes mellitus (GDM), spontaneous preterm birth (PTB), intrahepatic cholestasis of pregnancy (ICP), small for gestational age (SGA), large for gestational age (LGA), low birth weight (LBW), macrosomia, and 1st and 5th minutes low APGAR scores (< 7). RESULTS: PIHD was significantly higher in LFF (< 4% and < 5th percentile) cases (p = 0.015 and p < 0.001, respectively). However, in population-based quartiles of FF, PIHD did not differ significantly between groups. Composite adverse maternal outcomes were significantly higher in the FF < 4% group (p = 0.042). When analyzes were adjusted for maternal age, BMI, and gestational age at NIPT, significance was maintained at < 4%, < 5th percentile LFF for PIHD, and < 4% LFF for composite adverse maternal outcomes. However, there was no significant relationship between LFF with GDM, ICP and PTB. Additionally, there was no significant association between low APGAR scores, SGA, LGA, LBW, macrosomia, and LFF concerning neonatal outcomes. CONCLUSION: Our study showed that LFF in pregnant women with normal NIPT results may be a predictor of subsequent PIHD.