The traditional diagnosis of neuropsychiatric disorders mainly depends on the subjective evaluation of specialists,neuropsychological test,biochemical examination and other methods,which lacks objective,accurate and intelligent biomarkers.With the rapid development of neuroimaging and artificial intelligence technology,unsupervised learning has been widely used in the auxiliary diagnosis of neuropsychiatric disorders for it has the advantages of independence of external labels,high model generalization,and automatic feature extraction.Compared with the traditional supervised learning methods,unsupervised learning is more capable of achieving objective,accurate and intelligent diagnosis of neuropsychiatric disorders.Herein an overview on the applications of unsupervised learning in the auxiliary diagnosis of neuropsychiatric disorders is provided,summarizing the findings of unsupervised learning in Alzheimer's disease,schizophrenia,major depressive disorder,and autism spectrum disorder,and discussing the research challenges such as insufficient image processing capability,small sample size,insufficient biochemical index data.The corporation with neural network,multi-site large sample size,and deep fusion of multidimensional data are the development trends of unsupervised learning method.

BACKGROUNDAs a novel device-based approach targeting the renal sympathetic nerves, percutaneous renal denervation (RDN) has been shown to be effective and safe for reducing blood pressure. However, while considerable data on RDN have been obtained from Western populations, there is limited findings from East Asian populations. The purpose of this study was to evaluate one-year outcomes of RDN for the treatment of resistant hypertension in Chinese patients.

METHODSBetween February and August 2012, 14 patients (mean age 39 ± 8 years, 10 males) with resistant hypertension underwent successful RDN at the Fuwai Hospital. All 14 patients were followed up at 1, 3, 6 and 12 months post-procedure. Blood pressure, use of antihypertensive agents, renal function, and complications were investigated.

RESULTSBaseline values included mean office blood pressure of 164/103 ± 14/10 mmHg, mean 3.9 ± 0.6 anti-hypertensive agents, and an estimated glomerular filtration rate of (79 ± 19) ml × min(-1)×1.73 m(-2). Office blood pressure after the procedure was reduced by -14/-10, -17/-11, -21/-12, and -24/-14 mmHg at 1, 3, 6, and 12 months respectively, and the reduction of the number of antihypertensive agents at the above corresponding time points was -1.3, -1.5, -1.7 and -1.8 respectively (all P < 0.001). The mean reduction of 24-hour ambulatory blood pressure was similar to the reduction of office blood pressure at the four corresponding time points. Renal function did not significantly change at any time point (all P > 0.05). No clinical complications were observed at 12-month follow-up.

CONCLUSIONThis study showed that RDN seems to be effective in reducing blood pressure of Chinese patients with resistant hypertension, with minimal adverse events at 12-month follow-up.

Adult ; Antihypertensive Agents ; therapeutic use ; Blood Pressure ; drug effects ; Female ; Glomerular Filtration Rate ; physiology ; Humans ; Hypertension ; drug therapy ; Male ; Middle Aged