OBJECTIVES: This study aimed to provide a personalized surgical recommendation that enables more confidence in advising patients to pursue surgical treatment.
METHODS: We enrolled 328 patients with uPA harboring KCNJ5 mutations (n = 158) or not (n = 170) who had undergone adrenalectomy. Eighty-seven features were collected, including demographics, various blood and urine test results, and clinical comorbidities. We designed 2 versions of the prediction model: one for institutes with complete blood tests (full version), and the other for institutes that may not be equipped with comprehensive testing facilities (condensed version).
RESULTS: The results show that in the full version, the Light Gradient Boosting Machine outperformed other classifiers, achieving area under the curve and accuracy values of 0.905 and 0.864, respectively. The Light Gradient Boosting Machine also showed excellent performance in the condensed version, achieving area under the curve and accuracy values of 0.867 and 0.803, respectively.
CONCLUSIONS: We simplified the preoperative diagnosis of KCNJ5 mutations successfully using machine learning. The proposed lightweight tool that requires only baseline characteristics and blood/urine test results can be widely applied and can aid personalized prediction during preoperative counseling for patients with uPA.
METHODS: MiRNA profiling was conducted on plasma samples from 18 patients with primary aldosteronism taken during adrenal venous sampling on an Illumina MiSeq platform. Bioinformatics and machine learning identified 9 miRNAs for validation by reverse transcription real-time quantitative polymerase chain reaction. Validation was performed on a cohort consisting of 108 patients with known subdifferentiation. A 30-patient subset of the validation cohort involved both adrenal venous sampling and peripheral, the rest only peripheral samples. A neural network model was used for feature selection and comparison between adrenal venous sampling and peripheral samples, while a deep-learning model was used for classification.
RESULTS: Our model identified 10 miRNA combinations achieving >85% accuracy in distinguishing unilateral primary aldosteronism and bilateral adrenal hyperplasia on a 30-sample subset, while also confirming the suitability of peripheral samples for analysis. The best model, involving 6 miRNAs, achieved an area under curve of 87.1%. Deep learning resulted in 100% accuracy on the subset and 90.9% sensitivity and 81.8% specificity on all 108 samples, with an area under curve of 86.7%.
CONCLUSIONS: Machine learning analysis of circulating miRNAs offers a minimally invasive alternative for primary aldosteronism lateralization. Early identification of bilateral adrenal hyperplasia could expedite treatment initiation without the need for further localization, benefiting both patients and health care providers.