Machine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test
Abstract Primary aldosteronism (PA) is associated with an increased risk of cardiometabolic diseases, especially in unilateral subtype. Despite its high prevalence, the case detection rate of PA is limited, partly because of no clinical models available in general practice to identify patients highl...
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/5f551589dde84025ab817db2193bc766 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:5f551589dde84025ab817db2193bc766 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:5f551589dde84025ab817db2193bc7662021-12-02T14:49:43ZMachine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test10.1038/s41598-021-88712-82045-2322https://doaj.org/article/5f551589dde84025ab817db2193bc7662021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88712-8https://doaj.org/toc/2045-2322Abstract Primary aldosteronism (PA) is associated with an increased risk of cardiometabolic diseases, especially in unilateral subtype. Despite its high prevalence, the case detection rate of PA is limited, partly because of no clinical models available in general practice to identify patients highly suspicious of unilateral subtype of PA, who should be referred to specialized centers. The aim of this retrospective cross-sectional study was to develop a predictive model for subtype diagnosis of PA based on machine learning methods using clinical data available in general practice. Overall, 91 patients with unilateral and 138 patients with bilateral PA were randomly assigned to the training and test cohorts. Four supervised machine learning classifiers; logistic regression, support vector machines, random forests (RF), and gradient boosting decision trees, were used to develop predictive models from 21 clinical variables. The accuracy and the area under the receiver operating characteristic curve (AUC) for predicting of subtype diagnosis of PA in the test cohort were compared among the optimized classifiers. Of the four classifiers, the accuracy and AUC were highest in RF, with 95.7% and 0.990, respectively. Serum potassium, plasma aldosterone, and serum sodium levels were highlighted as important variables in this model. For feature-selected RF with the three variables, the accuracy and AUC were 89.1% and 0.950, respectively. With an independent external PA cohort, we confirmed a similar accuracy for feature-selected RF (accuracy: 85.1%). Machine learning models developed using blood test can help predict subtype diagnosis of PA in general practice.Hiroki KanekoHironobu UmakoshiMasatoshi OgataNorio WadaNorifusa IwahashiTazuru FukumotoMaki Yokomoto-UmakoshiYui NakanoYayoi MatsudaTakashi MiyazawaRyuichi SakamotoYoshihiro OgawaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Hiroki Kaneko Hironobu Umakoshi Masatoshi Ogata Norio Wada Norifusa Iwahashi Tazuru Fukumoto Maki Yokomoto-Umakoshi Yui Nakano Yayoi Matsuda Takashi Miyazawa Ryuichi Sakamoto Yoshihiro Ogawa Machine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test |
| description |
Abstract Primary aldosteronism (PA) is associated with an increased risk of cardiometabolic diseases, especially in unilateral subtype. Despite its high prevalence, the case detection rate of PA is limited, partly because of no clinical models available in general practice to identify patients highly suspicious of unilateral subtype of PA, who should be referred to specialized centers. The aim of this retrospective cross-sectional study was to develop a predictive model for subtype diagnosis of PA based on machine learning methods using clinical data available in general practice. Overall, 91 patients with unilateral and 138 patients with bilateral PA were randomly assigned to the training and test cohorts. Four supervised machine learning classifiers; logistic regression, support vector machines, random forests (RF), and gradient boosting decision trees, were used to develop predictive models from 21 clinical variables. The accuracy and the area under the receiver operating characteristic curve (AUC) for predicting of subtype diagnosis of PA in the test cohort were compared among the optimized classifiers. Of the four classifiers, the accuracy and AUC were highest in RF, with 95.7% and 0.990, respectively. Serum potassium, plasma aldosterone, and serum sodium levels were highlighted as important variables in this model. For feature-selected RF with the three variables, the accuracy and AUC were 89.1% and 0.950, respectively. With an independent external PA cohort, we confirmed a similar accuracy for feature-selected RF (accuracy: 85.1%). Machine learning models developed using blood test can help predict subtype diagnosis of PA in general practice. |
| format |
article |
| author |
Hiroki Kaneko Hironobu Umakoshi Masatoshi Ogata Norio Wada Norifusa Iwahashi Tazuru Fukumoto Maki Yokomoto-Umakoshi Yui Nakano Yayoi Matsuda Takashi Miyazawa Ryuichi Sakamoto Yoshihiro Ogawa |
| author_facet |
Hiroki Kaneko Hironobu Umakoshi Masatoshi Ogata Norio Wada Norifusa Iwahashi Tazuru Fukumoto Maki Yokomoto-Umakoshi Yui Nakano Yayoi Matsuda Takashi Miyazawa Ryuichi Sakamoto Yoshihiro Ogawa |
| author_sort |
Hiroki Kaneko |
| title |
Machine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test |
| title_short |
Machine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test |
| title_full |
Machine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test |
| title_fullStr |
Machine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test |
| title_full_unstemmed |
Machine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test |
| title_sort |
machine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/5f551589dde84025ab817db2193bc766 |
| work_keys_str_mv |
AT hirokikaneko machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT hironobuumakoshi machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT masatoshiogata machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT noriowada machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT norifusaiwahashi machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT tazurufukumoto machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT makiyokomotoumakoshi machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT yuinakano machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT yayoimatsuda machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT takashimiyazawa machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT ryuichisakamoto machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest AT yoshihiroogawa machinelearningbasedmodelsforpredictionofsubtypediagnosisofprimaryaldosteronismusingbloodtest |
| _version_ |
1718389447896072192 |