Teratomas of anterior mediastinum are rare. They are often slow growing, asymptomatic, and detected incidentally on chest imaging. Mycobacterium abscessus (M. abscessus) is an acid‐fast bacillus that is classified as a pathogenic “rapid growing” non‐tuberculous mycobacteria. It is an uncommon cause of human pathology, which may cause skin and soft tissue infection after skin injury following inoculation, minor trauma, and surgery. Here, we present an unusual case of benign cystic teratoma mimicking recurrent pleural effusion, which was subsequently complicated by M. abscessus infection following thoracotomy. Cystic teratoma is rare, but it needs to be considered whenever clinical and investigative work‐up fails to provide a convincing diagnosis. A combined clinical, radiological, surgical, and histopathological assessment is important to arrive at the correct diagnosis. Rapidly growing mycobacteria needs to be included in the differential diagnosis of patients with non‐resolving infected post‐thoracotomy wound and who do not respond to broad‐spectrum antibiotics.

The diagnosis of endobronchial tuberculosis (EBTB) is difficult as it is not well visualized radiologically, and bronchoscopy is not routinely performed for tuberculosis (TB) patients. Bronchoscopic characterization via endoscopic macroscopic features can speed up the diagnosis of EBTB and prompt immediate treatment. In this study, we identified the clinical and bronchoscopic morphology of 17 patients who were diagnosed with EBTB from 2018 to 2020. Demographics, radiological, microbiological and histopathological data were recorded. Endobronchial lesions were classified according to Chung classification. The diagnosis was made based on a histopathological examination (HPE) of endobronchial biopsy, and/or positive ‘Acid-fast bacilli’ (AFB) microscopy/Mycobacterium tuberculosis (MTB) culture on microbiological examination of bronchial alveolar lavage (BAL) and/or positive MTB culture on endobronchial biopsy specimens. Furthermore, EBTB was predominant in young women, age 20 to 49 years old, with a male to female ratio of 1 to 2. Underlying comorbidities were found in 53% of the patients. Cough, fever and weight loss were the main symptoms (23.5%). The indications for bronchoscopy are smear-negative TB and persistent consolidation on chest radiographs. Consolidation was the main radiological finding (53%). An active caseating lesion was the main EBTB endobronchial subtype (53%). The leading HPE finding was caseating granulomatous inflammation (47%). All patients showed good clinical response to TB treatment. Repeated bronchoscopy in six patients post TB treatment showed a complete resolution of the endobronchial lesion. EBTB bronchoscopic characterization is paramount to ensure correct diagnosis, immediate treatment and to prevent complication.

We report a case of a 34‐year‐old lady with past history of asthma and pulmonary tuberculosis, who presented 5 weeks pregnant with acute dyspnea. Her chest X‐ray showed left‐sided complete lung collapse and concomitant right‐sided pneumothorax. The pneumothorax was initially managed conservatively with a chest tube but due to its persistence despite suction, was subsequently changed to a PneumostatTM, with which she was later discharged. She had a normal echocardiography (ejection fraction [EF] 67%) at 5 weeks of gestation but developed pulmonary hypertension (EF 55%, pulmonary arterial pressure 40.7 mmHg) as the pregnancy progressed. She delivered a healthy baby at 35 weeks via elective lower section caesarean section with spinal anesthesia. We followed her up postnatally and noted the presence of left‐sided pulmonary embolism, hypoplastic left lung, and left pulmonary artery. The management of this complex case involved a multidisciplinary effort between general medical, respiratory, obstetric, and cardiothoracic teams.

The improved version of Boosted Decision Tree algorithm, named as Boosted Adaptive Apriori post-Pruned Decision Tree (Boosted AApoP-DT), was developed by referring to Adaptive Apriori (AA) properties and by using post-pruning technique. The post-pruning technique used is mainly the error-complexity pruning for the decision trees categorized under Classification and Regression Trees. This technique estimates the re-substitution, cross-validation and generalization error rates before and after the post-pruning. The novelty of the post-pruning technique applied is that it is augmented by AA properties and these depend on the data characteristics in the dataset(s) being accessed. This algorithm is then boosted by using AdaBoost ensemble method. After comparing and contrasting this developed algorithm with the algorithm without being augmented by AA, i.e. Boosted post-Pruned Decision Tree (Boosted poP-DT), and the classical boosted decision tree algorithm, i.e. Boosted DT, there is a stepwise improvement shown when comparison proceeds from Boosted DT to Boosted poP-DT and to Boosted AApoP-DT.

No abstract