Lung cancer is one of the tumors with the highest incidence rate and mortality rate in the world. It is also the malignant tumor with the fastest growing number of patients, which seriously threatens human life. How to improve the accuracy of diagnosis and treatment of lung cancer and the survival prognosis is particularly important. Machine learning is a multi-disciplinary interdisciplinary specialty, covering the knowledge of probability theory, statistics, approximate theory and complex algorithm. It uses computer as a tool and is committed to simulating human learning methods, and divides the existing content into knowledge structures to effectively improve learning efficiency and being able to integrate computer science and statistics into medical problems. Through the introduction of algorithm to absorb the input data, and the application of computer analysis to predict the output value within the acceptable accuracy range, identify the patterns and trends in the data, and finally learn from previous experience, the development of this technology brings a new direction for the diagnosis and treatment of lung cancer. This article will review the performance and application prospects of different types of machine learning algorithms in the clinical diagnosis and survival prognosis analysis of lung cancer.
Objective To explore the correlative factors affecting the compl ications resulting from cement leakage after percutaneous kyphoplasty (PKP) in the treatment of osteoporotic vertebral body compression fractures (OVCF). Methods From February 2005 to October 2008, 71 patients with OVCF were treated by PKP and were retrospectively analyzed. There were 16 males and 55 females, and the average age was 71.5 years (range, 52-91 years). The average duration of disease was 5.7 months (range, 1-11 months). A total of 171 vertebra were involved in fracture including 19 cases of single vertebral fractures, 21 cases of double vertebral fractures, 20 cases of three vertebral fractures, and 11 cases of more than three vertebral fractures. All the treated vertebra were divided into acute (86 vertebra) or subacute (85 vertebra) state based on changes in MRI signal intensity. There was no radiculopathy or myelopathy. The average injected cement volumewas 4.6 mL (range, 1.5-6.5 mL). The treatment efficacy was assessed by observing the change in anterior and middle vertebral column height, Cobb angle, visual analogue scale (VAS) and Oswestry functional score at preoperation, 3 days after operation and last follow-up. The patients were divided into cement leakage group and no cement leakage group. All the compl ications were recorded, and then the correlative factors affecting the compl ications were analyzed. Results All the cases had rapid and significant improvement in back pain following PKP. All patients were followed up for 14 months (range, 7-18 months). There was no cement extravasation resulting in radiculopathy or myelopathy. Four patients (5.63%) had lung-related compl ications. During the follow-up, 9 recurrence vertebral fractures were observed in 6 patients (8.45%). The anterior and middle vertebral column height, Cobb angle, VAS and Oswestry score were significantly improved when compared with preoperation (P lt; 0.05). Cement leakage occurred in 17 (9.94%) vertebral bodies; of 17 cases, the cement leaked into the paravertebral space in 7 cases, intervertebral space in 6 cases, channel of needl ing insertion in 3 cases, and spinal canal in 1 case. Univariate analysis showed statistically significant differences (P lt; 0.05) in preoperative anterior and middle vertebral column height, injected cement volume and vertebral body wall incompetence between the cement leakage group and no cement leakage group. There were no significant differences (P gt; 0.05) in preoperative Cobb angle, freshness of vertebral fracture, location of operative vertebrae and operative approach between the two groups. Multiple logistic regression analysis showed that the injected cement volume [odds ratio (OR)=3.105, 95% confidence interval (CI)=1.674-5.759, P lt; 0.01] and vertebral body wall incompetence (OR=11.960, 95%CI=3.512-40.729, P lt; 0.01) were the predominant variable associated with the compl ications resulted fromcement leakage. Conclusion The injected cement volume and vertebral body wall incompetence were the factors affecting the compl ications. The improvement of surgical technique is the capital factor that may reduce the compl ications in the PKP.