ABSTRACT
BackgroundBeing complex and highly heterogeneous with regard to the etiology and clinical manifestations of depression， neuroimaging studies make a breakthrough for exploring the biological subtypes of depression， while the current data-driven approach for the identification of subtyping depression using structural magnetic resonance imaging （MRI） data is insufficient. ObjectiveTo explore the biological subtypes of depression using diffusion tensor imaging （DTI） and machine learning methods. MethodsA total of 127 patients with depression who attended Beijing Anding Hospital from September 2017 to August 2021 and met the Diagnostic and Statistical Manual of Mental Disorders， fourth edition （DSM-IV） diagnostic criteria were included， and another 80 healthy individuals matched for gender and age were recruited through advertisements in surrounding communities during the same period. DTI findings， demographic characteristics and clinical data were collected from all participants. Tract-based spatial statistics （TBSS） and the Johns Hopkins University （JHU） white matter probability maps were used to extract fractional anisotropy （FA） values of white matter tracts. A semi-supervised machine learning technique was used to identify the subtypes， and the FA values for whole brain white matter of patients and controls were compared. ResultsPatients with depression were classified into two biological subtypes. FA values in multiple tracts including corpus callosum and corona radiata of subtype I patients were smaller than those of healthy controls （P<0.01， FDR corrected）， and FA values in middle cerebellar peduncle， left superior cerebellar peduncle and left cerebral peduncle of subtype II patients were larger than those of healthy controls （P<0.01， FDR-corrected）. Baseline Hamilton Depression Scale-17 item （HAMD-17） score yielded no statistical difference between subtype I and subtype II patients （P>0.05）， while subtype I patients scored lower on HAMD-17 than subtype II patients after 12 weeks of treatment （t=2.410， P<0.05）. ConclusionDepression patients exhibit two biological subtypes with distinct patterns of white matter damage. Furthermore， the subtypes respond differently to the medication treatment. ［Funded by the National Key Research and Development Program of China （number， 2016YFC1307200）， the Scientific Research and Cultivation Program of Beijing Municipal Hospitals （number，PX2023066）， Beijing Anding Hospital， Capital Medical University （number，YJ201904， YJ201911）； www.chictr.org.cn number： ChiCTR-OOC-17012566］
ABSTRACT
Background: Breast cancer is a major public health issue and it is the leading cause of cancer related death in females worldwide. New insights in the cancer treatment led to considerable improvement in the survival of cancer patients. But metastasis remain an area were all sorts of conventional treatments fails and it is the cause of death of most carcinoma breast patients. In this study we aim to establish a possible link to local recurrence and distant metastasis with different biological subtypes of breast cancer.Methods: One hundred and eighty patients of carcinoma breast patients of carcinoma breast who presented with local recurrence or distant metastasis in the period of January 2018 to March 2019 in Government Medical College, Thiruvananthapuram were included in this study. These data were collected from the hospital records.Results: Local recurrence was most seen in triple negative (50%) subtype followed by HER2 (32.1%) enriched. Local recurrence was least among luminal A (13.8%) with a p value of 0.001. Bone metastasis was the most common type of metastasis and was most seen in luminal A (p=0.001). Triple negative had the maximum CNS metastasis with a p value of 0.003. Liver metastasis was seen mostly in luminal B (26.2%) and A (20.7%) and lung metastasis in triple negative (13.5%) and HER2/neu (10.7%). However, there was no significant association for lung or liver metastasis to any subtype.Conclusions: Biological subtypes of breast cancer classified by immunohistochemical expression of ER, PR, HER2, Ki 67 show different clinicopathological features, recurrence pattern, and survival outcomes.