Non-small cell lung cancer is one of the cancers with the highest incidence and mortality rate in the world, and precise prognostic models can guide clinical treatment plans. With the continuous upgrading of computer technology, deep learning as a breakthrough technology of artificial intelligence has shown good performance and great potential in the application of non-small cell lung cancer prognosis model. The research on the application of deep learning in survival and recurrence prediction, efficacy prediction, distant metastasis prediction, and complication prediction of non-small cell lung cancer has made some progress, and it shows a trend of multi-omics and multi-modal joint, but there are still shortcomings, which should be further explored in the future to strengthen model verification and solve practical problems in clinical practice.
With the advancement of thyroid tumor treatment concepts and the progress of standardized treatment processes nationwide, the 5-year survival rate of thyroid tumors in China has risen from 67.5% in 2003 to 84.3% in 2015. As China has been continuously enriching its treatment options for advanced thyroid cancer in recent years, gradually improving the standardized treatment system for early and intermediate thyroid cancer, enhancing multidisciplinary collaboration methods and concepts, and regularizing scientific statistics, the survival rate of thyroid tumors continues to improve. We still need to consider the future development direction and core driving force of China’s thyroid discipline, correctly view the “prosperous” stage of domestic thyroid discipline development, and actively review the future development direction of China’s thyroid discipline.
Currently, in precision cardiac surgery, there are still some pressing issues that need to be addressed. For example, cardiopulmonary bypass remains a critical factor in precise surgical treatment, and many core aspects still rely on the experience and subjective judgment of cardiopulmonary bypass specialists and surgeons, lacking precise data feedback. With the increasing elderly population and rising surgical complexity, precise feedback during cardiopulmonary bypass becomes crucial for improving surgical success rates and facilitating high-complexity procedures. Overcoming these key challenges requires not only a solid medical background but also close collaboration among multiple interdisciplinary fields. Establishing a multidisciplinary team encompassing professionals from the medical, information, software, and related industries can provide high-quality solutions to these challenges. This article shows several patents from a collaborative medical and electronic information team, illustrating how to identify unresolved technical issues and find corresponding solutions in the field of precision cardiac surgery while sharing experiences in applying for invention patents.
Objective To evaluate effects of three-dimensional (3D) visualized reconstruction technology on short-term benefits of different extent of resection in treating hepatic alveolar echinococcosis (HAE) as well as some disadvantages. Methods One hundred and fifty-two patients with HAE from January 2014 to December 2016 in the Department Liver Surgery, West China Hospital of Sichuan University were collected, there were 80 patients with ≥4 segments and 72 patients with ≤3 segments of liver resection among these patients, which were designed to 3D reconstruction group and non-3D reconstruction group according to the preference of patients. The imaging data, intraoperative and postoperative indicators were recorded and compared. Results The 3D visualized reconstructions were performed in the 79 patients with HAE, the average time of 3D visualized reconstruction was 19 min, of which 13 cases took more than 30 min and the longest reached 150 min. The preoperative predicted liver resection volume of the 79 patients underwent the 3D visualized reconstruction was (583.6±374.7) mL, the volume of intraoperative actual liver resection was (573.8±406.3) mL, the comparison of preoperative and intraoperative data indicated that both agreed reasonably well (P=0.640). Forty-one cases and 38 cases in the 80 patients with ≥4 segments and 72 patients with ≤3 segments of liverresection respectively were selected for the 3D visualized reconstruction. For the patients with ≥4 segments of liver resection, the operative time was shorter (P=0.021) and the blood loss was less (P=0.047) in the 3D reconstruction group as compared with the non-3D reconstruction group, the status of intraoperative blood transfusion had no significant difference between the 3D reconstruction group and the non-3D reconstruction group (P=0.766). For the patients with ≤3 segments of liver resection, the operative time, the blood loss, and the status of intraoperative blood transfusion had no significant differences between the 3D reconstruction group and the non-3D reconstruction group (P>0.05). For the patients with ≥4 segments or ≤3 segments of liver resection, the laboratory examination results within postoperative 3 d, complications within postoperative 90 d, and the postoperative hospitalization time had no significant differences between the 3D reconstruction group and the non-3D reconstruction group (P>0.05). Conclusion 3D visualized reconstruction technology contributes to patients with HAE ≥4 segments of liver resection, it could reduce intraoperative blood loss and shorten operation time, but it displays no remarkable benefits for ≤3 segments of liver resection.
In recent years, deep learning has provided a new method for cancer prognosis analysis. The literatures related to the application of deep learning in the prognosis of cancer are summarized and their advantages and disadvantages are analyzed, which can be provided for in-depth research. Based on this, this paper systematically reviewed the latest research progress of deep learning in the construction of cancer prognosis model, and made an analysis on the strengths and weaknesses of relevant methods. Firstly, the construction idea and performance evaluation index of deep learning cancer prognosis model were clarified. Secondly, the basic network structure was introduced, and the data type, data amount, and specific network structures and their merits and demerits were discussed. Then, the mainstream method of establishing deep learning cancer prognosis model was verified and the experimental results were analyzed. Finally, the challenges and future research directions in this field were summarized and expected. Compared with the previous models, the deep learning cancer prognosis model can better improve the prognosis prediction ability of cancer patients. In the future, we should continue to explore the research of deep learning in cancer recurrence rate, cancer treatment program and drug efficacy evaluation, and fully explore the application value and potential of deep learning in cancer prognosis model, so as to establish an efficient and accurate cancer prognosis model and realize the goal of precision medicine.
Along with the popularity of low-dose computed tomography lung cancer screening, an increasing number of early-stage lung cancers are detected. Radical lobectomy with systematic nodal dissection (SND) remains the standard-of-care for operable lung cancer patients. However, whether SND should be performed on non-metastatic lymph nodes remains controversy. Unnecessary lymph node dissection can increase the difficulty of surgery while also causing additional surgical damage. In addition, non-metastatic lymph nodes have been recently reported to play a key role in immunotherapy. How to reduce the surgical damage of mediastinal lymph node dissection for early-stage lung cancer patients is pivotal for modern concept of "minimally invasive surgery for lung cancer 3.0". The selective mediastinal lymph node dissection strategy aims to dissect lymph nodes with tumor metastasis while preserving normal mediastinal lymph nodes. Previous studies have shown that combination of specific tumor segment site, radiology and intraoperative frozen pathology characteristics can accurately predict the pattern of mediastinal lymph node metastasis. The personalized selective mediastinal lymph node dissection strategy formed from this has been successfully validated in a recent prospective clinical trial, providing an important basis for early-stage lung cancer patients to receive more personalized selective lymph node dissection with "precision surgery" strategies.
Laparoscopic Roux-en-Y gastric bypass (LRYGB) was recommended as the gold standard procedure for metabolic and bariatric surgery by the National Institutes of Health in the 1990s and then had been adopted till now, which could effectively control excess weight and treat metabolic diseases relevant to obesity in a long term. The current LRYGB procedure had been performed more than half a century of development and update, and is still constantly evolving. Standardized and precise surgical procedures are of great significance in ensuring treatment effect and reducing the incidence of complications. Thus, the author reviewed the development process of LRYGB, further understanding and emphasizing the importance of standardized and precise surgical procedures.
Lung cancer is one of the leading causes of cancer deaths worldwide. Many options including surgery, radiotherapy, chemotherapy, targeted therapy and immunotherapy have been applied in the treatment for lung cancer patients. However, how to develop individualized treatment plans for patients and accurately determine the prognosis of patients is still a very difficult clinical problem. In recent years, radiomics, as an emerging method for medical image analysis, has gradually received the attention from researchers. It is based on the assumption that medical images contain a vast amount of biological information about patients that is difficult to identify with naked eyes but can be accessed by computer. One of the most common uses of radiomics is the diagnosis and treatment of non-small cell lung cancer (NSCLC). In this review, we reviewed the current researches on chest CT-based radiomics in the diagnosis and treatment of NSCLC and provided a brief summary of the current state of research in this field, covering various aspects of qualitative diagnosis, efficacy prediction, and prognostic analysis of lung cancer. We also briefly described the main current technical limitations of this technology with the aim of gaining a broader understanding of its potential role in the diagnosis and treatment of NSCLC and advancing its development as a tool for individualized management of NSCLC patients.
Sepsis is a critical condition. The key factor affecting the survival of patient is whether standard treatment can be obtained timely. Because of the complexity of its pathogenesis and high heterogeneity, there is no special diagnosis method currently. Early identification is difficult. Delayed diagnosis and treatment is closely related to the mortality of patients. With the continuous updating of the guidelines, sepsis has been included in the “time window” disease, putting forward a great challenge to the early screening and evaluation of sepsis. This article aims to review the application of Sepsis-Related Organ Failure Assessment, sepsis biomarkers and artificial intelligence algorithms in early screening and evaluation of sepsis, so as to provide guidance tools for timely starting standardized treatment of sepsis.
Liddle syndrome and Gordon syndrome are two rare single-gene inherited hypertension diseases. In patients≤40 years, the prevalence of Liddle syndrome is about 1% and Gordon syndrome is uncertain all over the word, for which is often misdiagnosed and mistreated. The therapies of those diseases are targeted at gene mutation sites, as well as combined with modified lifestyle, and can achieve satisfactory diseases control. This paper reports a patient who is diagnosed with Liddle syndrome and Gordon syndrome at the same time. We aimed to consolidate and improve the diagnosis and accurate treatment of those two diseases by sharing, studying and discussing together with clinical doctors.