• Title/Summary/Keyword: Tree Tomography

Search Result 33, Processing Time 0.02 seconds

Prediction Model for unfavorable Outcome in Spontaneous Intracerebral Hemorrhage Based on Machine Learning

  • Shengli Li;Jianan Zhang;Xiaoqun Hou;Yongyi Wang;Tong Li;Zhiming Xu;Feng Chen;Yong Zhou;Weimin Wang;Mingxing Liu
    • Journal of Korean Neurosurgical Society
    • /
    • v.67 no.1
    • /
    • pp.94-102
    • /
    • 2024
  • Objective : The spontaneous intracerebral hemorrhage (ICH) remains a significant cause of mortality and morbidity throughout the world. The purpose of this retrospective study is to develop multiple models for predicting ICH outcomes using machine learning (ML). Methods : Between January 2014 and October 2021, we included ICH patients identified by computed tomography or magnetic resonance imaging and treated with surgery. At the 6-month check-up, outcomes were assessed using the modified Rankin Scale. In this study, four ML models, including Support Vector Machine (SVM), Decision Tree C5.0, Artificial Neural Network, Logistic Regression were used to build ICH prediction models. In order to evaluate the reliability and the ML models, we calculated the area under the receiver operating characteristic curve (AUC), specificity, sensitivity, accuracy, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR). Results : We identified 71 patients who had favorable outcomes and 156 who had unfavorable outcomes. The results showed that the SVM model achieved the best comprehensive prediction efficiency. For the SVM model, the AUC, accuracy, specificity, sensitivity, PLR, NLR, and DOR were 0.91, 0.92, 0.92, 0.93, 11.63, 0.076, and 153.03, respectively. For the SVM model, we found the importance value of time to operating room (TOR) was higher significantly than other variables. Conclusion : The analysis of clinical reliability showed that the SVM model achieved the best comprehensive prediction efficiency and the importance value of TOR was higher significantly than other variables.

Imaging Findings of Pneumothorax Caused by Bronchial Cartilage Hypoplasia in a Dog (개에서 기관지 연골 저형성에 의해 발생한 기흉의 영상학적 진단 증례)

  • Kim, Su-yeon;Kim, Seong-soo;Lee, Jeo-soon;Yun, Soo-kyung;Oh, Hyun-jung;Shon, Jung-min;Kim, Bo-eun;Kim, Wan-hee;Yoon, Jung-hee;Choi, Min-cheol
    • Journal of Veterinary Clinics
    • /
    • v.32 no.5
    • /
    • pp.469-472
    • /
    • 2015
  • A 10-year-old, castrated poodle dog presented with a cough for 2 weeks, and the cough initially developed since very young age. On radiographs, pneumothorax was noticed by characteristics of radiolucent area without pulmonary markings along the thoracic wall and diaphragm, retracted lung lobes from the thoracic wall and severely decreased volume of the left cranial lung lobe with disconnected bronchus. Computed tomography (CT) findings identified several pulmonary air-filled cysts and collapsed lung with abnormal shape and non-tapered end of bronchus, bronchioles at the accessory lobe and left cranial lobe. Also, pneumothorax, pneumomediastinum and subcutaneous emphysema were found. Imaging diagnosis was the spontaneous pneumothorax caused by ruptured emphysematous bullae associated with congenital bronchial cartilage abnormality or bronchial tree malformation. On surgery, hypoplasia of the left cranial lobe, right middle lobe, and accessory lobe with a bulla where air was leaking was identified. The accessory lobe was partially resected and bronchial cartilage hypoplasia was confirmed by histopathologic examination.

Clinical and Radiographic Characteristics of 12 Patients with Mycobacterium abscessus Pulmonary Disease (Mycobacterium abscessus 폐질환 환자 12명의 임상적, 방사선학적 특징)

  • Koh, Won-Jung;Kwon, O Jung;Kang, Eun Hae;Jeon, Ik Soo;Pyun, Yu Jang;Ham, Hyoung Suk;Suh, Gee Young;Chung, Man Pyo;Kim, Hojoong;Han, Daehee;Kim, Tae Sung;Lee, Kyung Soo
    • Tuberculosis and Respiratory Diseases
    • /
    • v.54 no.1
    • /
    • pp.45-56
    • /
    • 2003
  • Background : Mycobacterium abscessus is the most common respiratory pathogen in rapidly growing mycobacteria and is resistant to all of the first-line antituberculosis drugs. This report describes the clinical and radiographic characteristics in patients with pulmonary disease caused by M. abscessus. Materials and Methods : Twelve patients with pulmonary disease caused by M. abscessus who fulfilled the 1997 American Thoracic Society diagnostic criteria for a nontuberculous mycobacterial pulmonary infection were observed over a five-and-a-half year period. The clinical characteristics and chest radiographic findings were analyzed, retrospectively. Results : The patients were predominantly female(11/12, 92%) and nonsmokers(12/12, 100%). Coughing (10/12, 83%), sputum(10/12, 83%) and hemoptysis(10/12, 83%) were the common symptoms and they had prolonged periods from the onset of symptoms to the diagnosis of their disease(median 6.5 years). Eleven (92%) patients had a previous history of being treated for pulmonary tuberculosis. The sputum specimens were acid-fast bacilli smear-positive in all patients. All patients were administered antituberculosis drugs. Six (50%) patients were treated with second-line antituberculosis drugs on account of persistent smear-positive sputum specimens. The chest radiographs showed that reticulonodular opacities(11/12, 92%) were the most common pattern of abnormality, followed by cavitary lesions(5/12, 42%). The computed tomography findings suggested bronchiolitis from the centrilobular nodules with a tree-in-bud appearances(9/10, 90%) and bronchiectasis (9/10, 90%) were the most common, followed by well-defined nodules smaller than 10-mm in diameter(7/10, 70%). Conclusions : M. abscessus pulmonary disease should be recognized as a cause of chronic mycobacterial lung disease, and respiratory isolates should be assessed carefully.