[ABSTRACT] SET domain-containing protein 2 (SETD 2), an epigenetic gene encoding a tri-methyltransferase of histone H3 lysine 36 (H3K36), has been found to be recurrently mutated in a variety of malignancies in the past few decades. SETD2 mutation was firstly identified in solid tumors including renal clear cell carcinoma, glioma and breast cancer, then recently found in multiple hematological malignancies. Increasing evidences have revealed that SETD2 played a pivotal role in regulating the functions of hematopoietic stem cells and the normal development of hematopoietic system. Inactivating mutations of SETD2 can promote the pathogenesis of myeloid, lymphoid leukemia and lymphoma as well as the development of therapeutic resistance. Further elucidation of the molecular mechanisms underlying SETD2-associated hematological malignancies and drug resistance is of great significance for the innovations of diagnosis and treatment methods. In this review, the progress of SETD2 in hematological malignancies are elaborated.

Objective:To explore CT and MRI features of the endolymphatic sac tumor (ELST).Methods:The CT and MRI morphology confirmed by surgical pathology for 19 patients with ELST were retrospectively analyzed from June 2011 to May 2019 in Eye & ENT Hospital of Fudan University. The features of CT and MRI included location, size, adjacent structures invasion, CT values, bone destruction, features of T 1WI and T 2WI, enhancement distribution characteristics, dynamic enhancement curve morphology, DWI signal characteristics. The ADC values of the lesions and ipsilateral medial pterygoid muscles were compared using a paired t test. Results:Nineteen ELST patients (one with bilateral diseases) were included. Totally 20 ears (right 9 and left 11) of 13 females and 6 males were studied. The masses with slightly high-density and obscure boundary were located around the vestibular aqueduct at the posterior edge of the petrosal bone. Bone destruction involved mastoid process of the middle ear (16 ears), jugular foramen (11 ears), semicircular canal (10 ears), facial nerve canal (7 ears) and internal auditory canal (9 ears). A large amount of residual bone could be found in the interior of nineteen masses. The CT value was (78.6±21.9) HU. The lesion showed central iso-intensity and peripheral hyperintensity on T 1WI and T 2WI in 16 ears, while no obvious hyperintensity on T 1WI in the other 4 ears. The hyperintensity on T 1WI was around the margin of the lesion in 10 ears, situated at lateral side in 5 ears and all over the lesion in 1 ear. Flow voids signals could be seen in 9 ears as well. Liquid-liquid plane was seen on T 2WI in 2 ears. The solid mass portion which showed iso-intensity on both T 1WI and T 2WI presented marked enhancement on contrast-enhanced T 1WI, while other part of the mass no enhancement. DWI of 14 ears illustrates no evidence of restricted diffusion, and the ADC value [(1.25±0.08)×10 -3 mm 2/s] was slightly higher than that of the medial pterygoid muscles ( t=4.437, P=0.001). The style of time-signal intensity curves of the dynamic contrast-enhanced MRI was rapidly ascending followed by descending curves in 2 ears. Conclusion:Imaging findings of ELST have some characteristics, including located around the vestibular aqueduct at the posterior edge of the petrosal bone, bone destruction, peripheral hyperintensity on T 1WI and no restricted diffusion, which is helpful for its diagnosis.

OBJECTIVE: To evaluate the application of decision tree method and Logistic regression in the prediction of acute myocardial infarction (AMI) events. METHODS: The clinical data of 295 patients, who underwent coronary angiography due to angina or chest pain with unidentified causes in Zhejiang provincial People's Hospital during October 2018 and April 2019, were retrospectively analyzed. Fifty five patients were identified as AMI. Logistic regression and decision tree methods were performed to establish predictive models for the occurrence of AMI, respectively; and the models created by decision tree analysis were divided into Logistic regression-independent model (Tree 1) and Logistic regression-dependent model (Tree 2). The performance of Logistic regression and decision tree models were compared using the area under the receiver operating characteristic (ROC) curve. RESULTS Logistic regression analysis showed that history of coronary artery disease, multi-vessel coronary artery disease, statin use and apolipoprotein (ApoA1) level were independent influencing factors of AMI events (all P<0.05). Logistic regression-independent decision tree model (Tree 1) showed that multi-vessel coronary artery disease was the root node, and history of coronary artery disease, ApoA1 level (the cutoff value:1.314 g/L) and anti-platelet drug use were descendant nodes. In Logistic regression-dependent decision tree model (Tree 2), multi-vessel coronary artery disease was still the root node, but only followed by two descendant nodes including history of coronary artery disease and ApoA1 level. The area under the curve (AUC) of ROC of Logistic regression model was 0.826, and AUCs of decision tree models were 0.765 and 0.726, respectively. AUC of Logistic regression model was significantly higher than that of Tree 2 (95% CI=0.041-0.145, Z=3.534, P<0.001), but was not higher than that of Tree 1 (95% CI=-0.014-0.121, Z=-1.173, P>0.05). CONCLUSIONS The predictive value for AMI event was comparable between Logistic regression-independent decision tree model and Logistic regression model, implying the data mining methods are feasible and effective in AMI prevention and control.