RESUMO
ObjectivesThis study aims to develop a machine learning approach for automated severity assessment of COVID-19 patients based on clinical and imaging data. Materials and MethodsClinical data--demographics, signs, symptoms, comorbidities and blood test results--and chest CT scans of 346 patients from two hospitals in the Hubei province, China, were used to develop machine learning models for automated severity assessment of diagnosed COVID-19 cases. We compared the predictive power of clinical and imaging data by testing multiple machine learning models, and further explored the use of four oversampling methods to address the imbalance distribution issue. Features with the highest predictive power were identified using the SHAP framework. ResultsTargeting differentiation between mild and severe cases, logistic regression models achieved the best performance on clinical features (AUC:0.848, sensitivity:0.455, specificity:0.906), imaging features (AUC:0.926, sensitivity:0.818, specificity:0.901) and the combined features (AUC:0.950, sensitivity:0.764, specificity:0.919). The SMOTE oversampling method further improved the performance of the combined features to AUC of 0.960 (sensitivity:0.845, specificity:0.929). DiscussionImaging features had the strongest impact on the model output, while a combination of clinical and imaging features yielded the best performance overall. The identified predictive features were consistent with findings from previous studies. Oversampling yielded mixed results, although it achieved the best performance in our study. ConclusionsThis study indicates that clinical and imaging features can be used for automated severity assessment of COVID-19 patients and have the potential to assist with triaging COVID-19 patients and prioritizing care for patients at higher risk of severe cases.
RESUMO
Automatic severity assessment and progression prediction can facilitate admission, triage, and referral of COVID-19 patients. This study aims to explore the potential use of lung lesion features in the management of COVID-19, based on the assumption that lesion features may carry important diagnostic and prognostic information for quantifying infection severity and forecasting disease progression. A novel LesionEncoder framework is proposed to detect lesions in chest CT scans and to encode lesion features for automatic severity assessment and progression prediction. The LesionEncoder framework consists of a U-Net module for detecting lesions and extracting features from individual CT slices, and a recurrent neural network (RNN) module for learning the relationship between feature vectors and collectively classifying the sequence of feature vectors. Chest CT scans of two cohorts of COVID-19 patients from two hospitals in China were used for training and testing the proposed framework. When applied to assessing severity, this framework outperformed baseline methods achieving a sensitivity of 0.818, specificity of 0.952, accuracy of 0.940, and AUC of 0.903. It also outperformed the other tested methods in disease progression prediction with a sensitivity of 0.667, specificity of 0.838, accuracy of 0.829, and AUC of 0.736. The LesionEncoder framework demonstrates a strong potential for clinical application in current COVID-19 management, particularly in automatic severity assessment of COVID-19 patients. This framework also has a potential for other lesion-focused medical image analyses.
RESUMO
Objective To evaluate the feasibility of hand-assisted laparoscopic colorectal resection. Methods Clinical data of 21 cases of hand-assisted laparoscopic colorectal resection in this hospital from October 2003 to August 2004 were retrospectively reviewed. Results The hand-assisted laparoscopic resection was accomplished in 20 cases. The mean operation time was 144 min, the mean blood loss was 120 ml, the mean number of dissected lymph nodes was 8.5, and the mean time to intestinal function recovery, 69 h. Postoperative abdominal bleeding was found in 1 case, which was cured with conservative therapy. A conversion to open surgery was needed in 1 case. Conclusions Hand-assisted laparoscopic colorectal resection safe, feasible, and radical, with advantages of fewer complications and simplicity of performance.
RESUMO
Objective To explore the method and result of endoscopic thyroidectomy. Methods Thyroidectomy was performed endoscopically in 4 cases of thyroidoma. Results 4 patients underwent endoscopic thyroidectomy, whose operation time was 52,63,70,75 minutes respectively. An average blood loss during operation was 35ml and no complication occurred. They were discharged 4 days~5 days after operation. Conclusions The endoscopic thyroidectomy has the advantages of minimal invasion, less bleeding, less complication and quicker recovery.
RESUMO
Objective To access the clinical value of interstitial brachytherpay in patients with advanced carcinoma. Methods 6 patients(1 case of hepatic cancer,3 cases of prostate cancer,2 cases of local recurrence of rectal cancer)received interstitial high dose rate(Ir-192)brachytherpay with afterloading technique(6.0 Gy/day in 4 days) Tubes were inserted with laparoscopic guidance to minimize the risk of tube misplacement. Results The size of the tumors was reduced and the local control rate was encouraging(6/6). one patient with local recurrence of rectal cancer aquired CR,the ofher five cases acquired PR. Conclusions Interstitial tube insertion with laparoscopic guidance to treat advanced carcinoma in afterloading technique is a simple,minimally invasive,safe and economical method,especially fit for elder patients who intolerate or disagree to operation.
RESUMO
Objective To study the feasibility of endoscopic thyroidectomy with bipolar electrocoagulation. Methods Endoscopic partial thyroidectomy via precordial approach, mainly by using bipolar electrocoagulation and scissors, was accomplished in 21 patients with thyroid tumors with a diameter of 0.7~5.5 cm. Results The operation was accomplished endoscopically in 20 patients, whereas a conversion to open thyroidectomy was conducted in 1 patient. The mean incision length was 22 mm, the operation time was 69?47 min, and the blood loss was 55?41 ml. Postoperative analgesic treatment was required in 2 patients and no serious complications happened. Conclusions Endoscopic thyroidectomy with bipolar electrocoagulation is feasible in the absence of ultrasonic scalpel.