Background Associating a patient’s profile with the memories of prototypical patients built through previous repeat clinical experience is a key process in clinical judgment. We hypothesized that a similar process using a cognitive computing tool would be well suited for learning and recalling multidimensional attributes of speckle tracking echocardiography (STE) data sets derived from patients with known constrictive pericarditis (CP) and restrictive cardiomyopathy (RCM). Methods and Results Clinical and echocardiographic data of 50 patients with CP and 44 with RCM were used for developing an associative memory classifier (AMC) based machine learning algorithm. The STE data was normalized in reference to 47 controls with no structural heart disease, and the diagnostic area under the receiver operating characteristic curve (AUC) of the AMC was evaluated for differentiating CP from RCM. Using only STE variables, AMC achieved a diagnostic AUC of 89·2%, which improved to 96·2% with addition of 4 echocardiographic variables. In comparison, the AUC of early diastolic mitral annular velocity and left ventricular longitudinal strain were 82.1% and 63·7%, respectively. Furthermore, AMC demonstrated greater accuracy and shorter learning curves than other machine learning approaches with accuracy asymptotically approaching 90% after a training fraction of 0·3 and remaining flat at higher training fractions. Conclusions This study demonstrates feasibility of a cognitive machine learning approach for learning and recalling patterns observed during echocardiographic evaluations. Incorporation of machine learning algorithms in cardiac imaging may aid standardized assessments and support the quality of interpretations, particularly for novice readers with limited experience.

Vaccination plays an important role during the COVID-19 pandemic. Vaccine-induced thrombotic thrombocytopenia (VITT) is a major adverse effect that could be lethal. For cancer patients, cancer-related thromboembolism is another lethal complication. When cancer patients receive their COVID-19 vaccines, the following thromboembolic events will be more complicated. We presented a case recently diagnosed with pancreatic cancer, who had received the mRNA-1273 (Moderna) vaccination 12 days prior. Ischemic stroke and VITT were also diagnosed. We aggressively treated the patient with steroids, immunoglobulin, and plasma exchange. The titer of anti-platelet factor four and d-dimer level decreased, but the patient ultimately died. The complicated condition of VITT superimposed cancer-related thromboembolism was considered. To our knowledge, only one case of mRNA-1273 related VITT was reported, and this case study was the first to report a cancer patient who was diagnosed with VITT after mRNA-1273 vaccination. Therefore, when the need for vaccination among cancer patients increased under the current COVID-19 pandemic, the possible risk of VITT for cancer patients should be carefully managed. Further studies of the risk evaluation of the COVID-19 vaccine in cancer patients might be required in the future.

Abstract. Lung cancer is one of the leading causes of cancer-related mortality worldwide. Gastrointestinal metastasis from primary lung cancer is rare. Only a few reports have been published and the majority of described metastatic sites involved the small intestine. In the present study, we report the first case of primary lung adenocarcinoma with both gastric and colonic metastases. We also review the published literature of primary lung cancer with gastrointestinal metastasis.

Summary Chronic lymphocytic leukaemia (CLL) is the most common leukaemia in Western countries but very rare in Asia. Peripheral blood or bone marrow mononuclear cells obtained at initial diagnosis from 194 patients with CLL were analysed to determine the ethnic difference in genetic abnormalities. Mutated IGHV was detected in 71·2% of Taiwanese CLL and IGHV3‐23 was the most frequently used gene. Stereotyped BCR was present in 18·3% with subset 8 being the most frequent. All cases with subset 8 belonged to IGHV 4‐39 and were exclusively associated with un‐mutated IGHV and poor outcome. Mutation frequencies of SF3B1 (9·7%), NOTCH1 (8·6%), BIRC3 (1·1%), ATM (16·9%) or TP53 (8·1%), and frequencies of cytogenetic abnormalities including trisomy 12 (18·6%), del(17p) (10·4%), del(13q) (43·7%) and IGH translocation (10·1%) were comparable to those reported from Western countries, except del(11q) (6·9%) which was lower in our patients. Patients with un‐mutated IGHV, subset 8, disrupted TP53, trisomy 12, and SF3B1 mutations had a worse outcome compared to patients without these mutations. In conclusion, IGHV3‐23 usage, stereotyped subset 8 and lower frequency of del(11q) show an ethnicity‐dependent association in Taiwanese CLL patients.