Literature DB >> 34524677

Polycystic ovary syndrome: clinical and laboratory variables related to new phenotypes using machine-learning models.

A A Veloso1, K B Gomes2,3, I S Silva1, C N Ferreira4, L B X Costa5, M O Sóter6, L M L Carvalho5, J de C Albuquerque6, M F Sales5, A L Candido7, F M Reis8.   

Abstract

PURPOSE: Polycystic Ovary Syndrome (PCOS) is the most frequent endocrinopathy in women of reproductive age. Machine learning (ML) is the area of artificial intelligence with a focus on predictive computing algorithms. We aimed to define the most relevant clinical and laboratory variables related to PCOS diagnosis, and to stratify patients into different phenotypic groups (clusters) using ML algorithms.
METHODS: Variables from a database comparing 72 patients with PCOS and 73 healthy women were included. The BorutaShap method, followed by the Random Forest algorithm, was applied to prediction and clustering of PCOS.
RESULTS: Among the 58 variables investigated, the algorithm selected in decreasing order of importance: lipid accumulation product (LAP); abdominal circumference; thrombin activatable fibrinolysis inhibitor (TAFI) levels; body mass index (BMI); C-reactive protein (CRP), high-density lipoprotein cholesterol (HDL-c), follicle-stimulating hormone (FSH) and insulin levels; HOMA-IR value; age; prolactin, 17-OH progesterone and triglycerides levels; and family history of diabetes mellitus in first-degree relative as the variables associated to PCOS diagnosis. The combined use of these variables by the algorithm showed an accuracy of 86% and area under the ROC curve of 97%. Next, PCOS patients were gathered into two clusters in the first, the patients had higher BMI, abdominal circumference, LAP and HOMA-IR index, as well as CRP and insulin levels compared to the other cluster.
CONCLUSION: The developed algorithm could be applied to select more important clinical and biochemical variables related to PCOS and to classify into phenotypically different clusters. These results could guide more personalized and effective approaches to the treatment of PCOS.
© 2021. Italian Society of Endocrinology (SIE).

Entities:  

Keywords:  Machine learning; Phenotype; Polycystic Ovary Syndrome

Mesh:

Year:  2021        PMID: 34524677     DOI: 10.1007/s40618-021-01672-8

Source DB:  PubMed          Journal:  J Endocrinol Invest        ISSN: 0391-4097            Impact factor:   4.256


  34 in total

1.  Microparticles: Inflammatory and haemostatic biomarkers in Polycystic Ovary Syndrome.

Authors:  L M L Carvalho; C N Ferreira; M O Sóter; M F Sales; K F Rodrigues; S R Martins; A L Candido; F M Reis; I F O Silva; F M F Campos; K B Gomes
Journal:  Mol Cell Endocrinol       Date:  2017-01-11       Impact factor: 4.102

2.  The hallmark of pro- and anti-inflammatory cytokine ratios in women with polycystic ovary syndrome.

Authors:  Jéssica A G Tosatti; Mirelle O Sóter; Cláudia N Ferreira; Ieda de F O Silva; Ana L Cândido; Marinez O Sousa; Fernando M Reis; Karina B Gomes
Journal:  Cytokine       Date:  2020-07-06       Impact factor: 3.861

3.  Peripheral blood-derived cytokine gene polymorphisms and metabolic profile in women with polycystic ovary syndrome.

Authors:  Mirelle O Sóter; Cláudia N Ferreira; Mariana F Sales; Ana L Candido; Fernando M Reis; Kátia S Milagres; Carla Ronda; Ieda O Silva; Marinez O Sousa; Karina B Gomes
Journal:  Cytokine       Date:  2015-07-02       Impact factor: 3.861

Review 4.  Polycystic ovary syndrome (PCOS), an inflammatory, systemic, lifestyle endocrinopathy.

Authors:  Seema Patel
Journal:  J Steroid Biochem Mol Biol       Date:  2018-04-17       Impact factor: 4.292

Review 5.  The prevalence and phenotypic features of polycystic ovary syndrome: a systematic review and meta-analysis.

Authors:  Gurkan Bozdag; Sezcan Mumusoglu; Dila Zengin; Erdem Karabulut; Bulent Okan Yildiz
Journal:  Hum Reprod       Date:  2016-09-22       Impact factor: 6.918

6.  Haptoglobin levels, but not Hp1-Hp2 polymorphism, are associated with polycystic ovary syndrome.

Authors:  Laura M L Carvalho; Cláudia N Ferreira; Daisy K D de Oliveira; Kathryna F Rodrigues; Rita C F Duarte; Márcia F A Teixeira; Luana B Xavier; Ana Lúcia Candido; Fernando M Reis; Ieda F O Silva; Fernanda M F Campos; Karina B Gomes
Journal:  J Assist Reprod Genet       Date:  2017-09-13       Impact factor: 3.412

7.  The prevalence of polycystic ovary syndrome in a community sample assessed under contrasting diagnostic criteria.

Authors:  Wendy A March; Vivienne M Moore; Kristyn J Willson; David I W Phillips; Robert J Norman; Michael J Davies
Journal:  Hum Reprod       Date:  2009-11-12       Impact factor: 6.918

Review 8.  Polycystic Ovary Syndrome.

Authors:  Ricardo Azziz
Journal:  Obstet Gynecol       Date:  2018-08       Impact factor: 7.661

Review 9.  Polycystic Ovary Syndrome.

Authors:  Renate K Meier
Journal:  Nurs Clin North Am       Date:  2018-07-11       Impact factor: 1.208

10.  Serum C-reactive protein levels in normal-weight polycystic ovary syndrome.

Authors:  Ji Young Oh; Ji-Ah Lee; Hyejin Lee; Jee-Young Oh; Yeon-Ah Sung; Hyewon Chung
Journal:  Korean J Intern Med       Date:  2009-11-27       Impact factor: 2.884

View more
  1 in total

1.  Wavelet transformation can enhance computed tomography texture features: a multicenter radiomics study for grade assessment of COVID-19 pulmonary lesions.

Authors:  Zekun Jiang; Jin Yin; Peilun Han; Nan Chen; Qingbo Kang; Yue Qiu; Yiyue Li; Qicheng Lao; Miao Sun; Dan Yang; Shan Huang; Jiajun Qiu; Kang Li
Journal:  Quant Imaging Med Surg       Date:  2022-10
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.