人工智能在中医药领域的应用进展及现状思考

人工智能（Artificial Intelligence，AI）的蓬勃兴起为现代社会带来了前所未有的机遇，中医药是中华民族传承千年的文化瑰宝。随着人工智能技术不断在中医药领域的科技创新中崭露头角，二者的融合不断加深，人工智能在中医药领域的发展前景、争议挑战也引发了诸多思考。本文将从人工智能在中医药领域的应用入手，对人工智能辅助中医诊断、智能决策与数据挖掘、健康管理及中草药现代化研究等方面，就近年来国内外研究进展进行总结与分析，以期为AI视域下实现中医药现代化、智能化赋能。     

Correction: Thrombotic and bleeding events,mortality, and anticoagulant use among 546,656 hospitalized patients with COVID‑19 in the United States: a retrospective cohort study

Journal of Thrombosis and Thrombolysis -     

Role of surgical treatments in high-grade or advanced gastroenteropancreatic neuroendocrine neoplasms

Over the last 40 years, the incidence and prevalence of gastroenteropancreatic neuroendocrine neoplasms (GEP-NENs) have continued to increase. Compared to other epithelial neoplasms in the same organ, GEP-NENs exhibit indolent biological behavior, resulting in more chances to undergo surgery. However, the role of surgery in high-grade or advanced GEP-NENs is still controversial. Surgery is associated with survival improvement of well-differentiated high-grade GEP-NENs, whereas poorly differentiated GEP-NENs that may benefit from resection require careful selection based on Ki67 and other tissue biomarkers. Additionally, surgery also plays an important role in locally advanced and metastatic disease. For locally advanced GEP-NENs, isolated major vascular involvement is no longer an absolute contraindication. In the setting of metastatic GEP-NENs, radical intended surgery is recommended for patients with low-grade and resectable metastases. For unresectable metastatic disease, a variety of surgical approaches, including cytoreduction of liver metastasis, liver transplantation, and surgery after neoadjuvant treatment, show survival benefits. Primary tumor resection in GEP-NENs with unresectable metastatic disease is associated with symptom control, prolonged survival, and improved sensitivity toward systemic therapies. Although there is no established neoadjuvant or adjuvant strategy, increasing attention has been given to this emerging research area. Some studies have reported that neoadjuvant therapy effectively reduces tumor burden, improves the effectiveness of subsequent surgery, and decreases surgical complications.     

Measuring Psychological Inflexibility of Suicidal Thoughts: The Acceptance and Action Questionnaire for Suicidal Ideation (AAQ-SI)

Cognitive Therapy and Research - Despite interest in psychological inflexibility as a marker of suicide risk, no measure of psychological inflexibility specific to SI exists. The present study...     

PREDICT-GTN 1: Can we improve the FIGO scoring system in gestational trophoblastic neoplasia?

Gestational trophoblastic neoplasia (GTN) patients are treated according to the eight-variable International Federation of Gynaecology and Obstetrics (FIGO) scoring system, that aims to predict first-line single-agent chemotherapy resistance. FIGO is imperfect with one-third of low-risk patients developing disease resistance to first-line single-agent chemotherapy. We aimed to generate simplified models that improve upon FIGO. Logistic regression (LR) and multilayer perceptron (MLP) modelling (n = 4191) generated six models (M1-6). M1, all eight FIGO variables (scored data); M2, all eight FIGO variables (scored and raw data); M3, nonimaging variables (scored data); M4, nonimaging variables (scored and raw data); M5, imaging variables (scored data); and M6, pretreatment hCG (raw data) + imaging variables (scored data). Performance was compared to FIGO using true and false positive rates, positive and negative predictive values, diagnostic odds ratio, receiver operating characteristic (ROC) curves, Bland-Altman calibration plots, decision curve analysis and contingency tables. M1-6 were calibrated and outperformed FIGO on true positive rate and positive predictive value. Using LR and MLP, M1, M2 and M4 generated small improvements to the ROC curve and decision curve analysis. M3, M5 and M6 matched FIGO or performed less well. Compared to FIGO, most (excluding LR M4 and MLP M5) had significant discordance in patient classification (McNemar's test P < .05); 55-112 undertreated, 46-206 overtreated. Statistical modelling yielded only small gains over FIGO performance, arising through recategorisation of treatment-resistant patients, with a significant proportion of under/overtreatment as the available data have been used a priori to allocate primary chemotherapy. Streamlining FIGO should now be the focus.     

Effect of iron deficiency without anaemia on days alive and out of hospital in patients undergoing valvular heart surgery

Comprehensive evidence regarding the treatment of non-anaemic iron deficiency in patients undergoing valvular heart surgery is lacking. This study aimed to investigate the association between non-anaemic iron deficiency and postoperative outcomes in these patients. We retrospectively analysed 321 patients of which 180 (56%) had iron deficiency (defined as serum ferritin < 100 ng.ml^-1 or < 300 ng.ml^-1 with transferrin saturation < 20%). While the iron-deficient group had lower pre-operative haemoglobin levels than the non-iron deficient group (median (IQR [range]) 134 (127–141 [120–172]) g.l^-1, 143 (133–150 [120–179]) g.l^-1, p = 0.001), there was no between-group difference in allogeneic red blood cell transfusion. Median (IQR [range]) days alive and out of hospital at postoperative day 90 was 1 day shorter in the iron-deficient group (80 (77–82 [9–85]) days vs. 81 (79–83 [0–85]) days, p = 0.026). In multivariable analysis, only cardiopulmonary bypass duration (p = 0.032) and intra-operative allogeneic red blood cell transfusion (p = 0.011) were significantly associated with reduced days alive and out of hospital at postoperative day 90. Iron deficiency did not exert any adverse influence on secondary outcomes except length of hospital stay. Our findings indicate that non-anaemic iron deficiency alone is not associated with adverse effects in patients undergoing valvular heart surgery when it does not translate into an increased risk of allogeneic transfusion.     

Comprehensively evaluating cancer survival in children with birth defects: a population-based assessment

Cancer Causes & Control - Congenital malformations are strong risk factors for childhood cancer. Our objective was to determine whether cancer survival differs by birth defect status among...