Development and validation of an interpretable Markov-embedded multilabel model for predicting risks of multiple postoperative complications among surgical inpatients: a multicenter prospective cohort study.

BACKGROUND: When they encounter various highly related postoperative complications, existing risk evaluation tools that focus on single or any complications are inadequate in clinical practice. This seriously hinders complication management because of the lack of a quantitative basis. An interpretable multilabel model framework that predicts multiple complications simultaneously is urgently needed. MATERIALS AND METHODS: The authors included 50 325 inpatients from a large multicenter cohort (2014-2017). The authors separated patients from one hospital for external validation and randomly split the remaining patients into training and internal validation sets. A MARKov-EmbeDded (MARKED) multilabel model was proposed, and three models were trained for comparison: binary relevance, a fully connected network (FULLNET), and a deep neural network. Performance was mainly evaluated using the area under the receiver operating characteristic curve (AUC). The authors interpreted the model using Shapley Additive Explanations. Complication-specific risk and risk source inference were provided at the individual level. RESULTS: There were 26 292, 6574, and 17 459 inpatients in the training, internal validation, and external validation sets, respectively. For the external validation set, MARKED achieved the highest average AUC (0.818, 95% CI: 0.771-0.864) across eight outcomes [compared with binary relevance, 0.799 (0.748-0.849), FULLNET, 0.806 (0.756-0.856), and deep neural network, 0.815 (0.765-0.866)]. Specifically, the AUCs of MARKED were above 0.9 for cardiac complications [0.927 (0.894-0.960)], neurological complications [0.905 (0.870-0.941)], and mortality [0.902 (0.867-0.937)]. Serum albumin, surgical specialties, emergency case, American Society of Anesthesiologists score, age, and sex were the six most important preoperative variables. The interaction between complications contributed more than the preoperative variables, and formed a hierarchical chain of risk factors, mild complications, and severe complications. CONCLUSION: The authors demonstrated the advantage of MARKED in terms of performance and interpretability. The authors expect that the identification of high-risk patients and the inference of the risk source for specific complications will be valuable for clinical decision-making.

Nationwide gastric cancer prevention in China, 2021-2035: a decision analysis on effect, affordability and cost-effectiveness optimisation.

OBJECTIVE: To project future trajectories of the gastric cancer (GC) burden in China under different scenarios of GC prevention and identify strategies to improve affordability and cost-effectiveness. DESIGN: Using a cohort of Chinese men and women born during 1951-1980, we assumed that different prevention strategies were conducted, including eradication of Helicobacter pylori (Hp) and endoscopy screening (one-time, annual, biennial, triennial or stratified according to personal risk). We performed a literature search to identify up-to-date data and populate a Markov model to project the number of new GC cases and deaths during 2021-2035, as well as resource requirements and quality-adjusted life-years (QALYs). We examined the impacts of general (among the whole population) and targeted (high-risk population) prevention. RESULTS: During 2021-2035, 10.0 million new GC cases and 5.6 million GC deaths would occur, with 7.6%-35.5% and 6.9%-44.5%, respectively, being avoidable through various prevention strategies. Relative to the status quo, Hp eradication was a cost-saving strategy. General annual screening dominated other screening strategies, but cost more than CNY 70 000 per QALY gained (willingness-to-pay) compared with Hp eradication. Among endoscopy strategies, targeted screening resulted in 44%-49% lower cost per QALY gained over the status quo than general screening. Among high-risk population, tailoring the screening frequency according to personal risk could reduce endoscopy-related resources by 22% compared with biennial screening and by 55% compared with annual screening, CONCLUSION: Our findings provide important input for future decision-making and investment, highlighting the need and feasibility for China to include GC prevention in its national health plans.

Population-based projections of blood supply and demand, China, 2017-2036.

OBJECTIVE: To estimate the long-term effect of the changing demography in China on blood supply and demand. METHODS: We developed a predictive model to estimate blood supply and demand during 2017-2036 in mainland China and in 31 province-level regions. Model parameters were obtained from World Population Prospects, China statistical yearbook 2016, China's report on blood safety and records from a large tertiary hospital. Our main assumptions were stable age-specific per capita blood supply and demand over time. FINDINGS: We estimated that the change in demographic structure between 2016 (baseline year) and 2036 would result in a 16.0% decrease in blood supply (from 43.2 million units of 200 mL to 36.3 million units) and a 33.1% increase in demand (from 43.2 million units to 57.5 million units). In 2036, there would be an estimated shortage of 21.2 million units. An annual increase in supply between 0.9% and 1.8% is required to maintain a balance in blood supply and demand. This increase is not enough for every region as regional differences will increase, e.g. a blood demand/supply ratio ≥ 1.45 by 2036 is predicted in regions with large populations older than 65 years. Sensitivity analyses showed that increasing donations by 4.0% annually by people aged 18-34 years or decreasing the overall blood discard rate from 5.0% to 2.0% would not offset but help reduce the blood shortage. CONCLUSION: Multidimensional strategies and tailored, coordinated actions are needed to deal with growing pressures on blood services because of China's ageing population.

Cost-effectiveness comparison of routine transfusion with restrictive and liberal transfusion strategies for surgical patients in China.

BACKGROUND AND OBJECTIVES: A health industry standard recommending restrictive transfusion is to be in effect in China in April 2019. We aim to explore its potential economic and clinical impacts among surgical patients. MATERIALS AND METHODS: A decision tree model was applied to compare cost-effectiveness of current routine transfusion in China, a restrictive (transfusion at Hb < 8 g/dl or ischaemic symptoms) and a liberal (transfusion at Hb < 10 g/dl) strategy. Parameters were estimated from empirical data of 25 227 surgical inpatients aged ≥30 years in a multicenter study and supplemented by meta-analysis when necessary. Results are shown for cardio-cerebral-vascular (CCV) surgery and non-CCV (orthopaedics, general, thoracic) surgery separately. RESULTS: Per 10 000 patients in routine, restrictive, liberal transfusion scenarios, total spending (transfusion and length of stay related) was 7·67, 7·58 and 9·39 million CNY (1 CNY × 0.157 = 1 US dollar) for CCV surgery and 6·35, 6·70 and 8·09 million CNY for non-CCV surgery; infectious and severe complications numbered 354, 290, and 290 (CCV) and 315, 286, and 330 (non-CCV), respectively. Acceptability curves showed high probabilities for restrictive strategy to be cost-effective across a wide range of willingness-to-pay values. Such findings were mostly consistent in sensitivity and subgroup analyses except for patients with cardiac problems. CONCLUSION: We showed strong rationale, succeeding previous findings only in cardiac or joint procedures, to comply with the new standard as restrictive transfusion has high potential to save blood, secure safety, and is cost-effective for a wide spectrum of surgical patients. Experiences should be further summarized to pave the way towards individualized transfusion.

Effect of a risk-stratified intervention strategy on surgical complications: experience from a multicentre prospective study in China.

OBJECTIVES: To develop a risk-stratified intervention strategy and evaluate its effect on reducing surgical complications. DESIGN: A multicentre prospective study with preintervention and postintervention stages: period I (January to June 2015) to develop the intervention strategy and period II (January to June 2016) to evaluate its effectiveness. SETTING: Four academic/teaching hospitals representing major Chinese administrative and economic regions. PARTICIPANTS: All surgical (elective and emergent) inpatients aged ≥14 years with a minimum hospital stay of 24 hours, who underwent a surgical procedure requiring an anesthesiologist. INTERVENTIONS: Targeted complications were grouped into three categories (common, specific, serious) according to their incidence pattern, severity and preventability. The corresponding expert consensus-generated interventions, which focused on both regulating medical practices and managing inherent patient-related risks, were implemented in a patient-tailored way via an electronic checklist system. PRIMARY AND SECONDARY OUTCOMES: Primary outcomes were (1) in-hospital death/confirmed death within 30 days after discharge and (2) complications during hospitalisation. Secondary outcome was length of stay (LOS). RESULTS: We included 51 030 patients in this analysis (eligibility rate 87.7%): 23 413 during period I, 27 617 during period II. Patients' characteristics were comparable during the two periods. After adjustment, the mean number of overall complications per 100 patients decreased from 8.84 to 7.56 (relative change 14.5%; P<0.0001). Specifically, complication rates decreased from 3.96 to 3.65 (7.8%) for common complications (P=0.0677), from 0.50 to 0.36 (28.0%) for specific complications (P=0.0153) and from 3.64 to 2.88 (20.9%) for serious complications (P<0.0001). From period I to period II, there was a decreasing trend for mortality (from 0.64 to 0.53; P=0.1031) and median LOS (by 1 day; P=0.8293), without statistical significance. CONCLUSIONS: Implementing a risk-stratified intervention strategy may be a target-sensitive, convenient means to improve surgical outcomes.

Challenges and research opportunities for lung cancer screening in China.

Following publication of the results of the National Lung Screening Trial in the United States, a randomized controlled trial in Italy (ITALUNG) and two simulation studies in China reported similar findings in 2017 favoring lung cancer screening with low-dose computed tomography among smokers. With such advances in lung cancer screening, worldwide interest has gradually shifted from evaluating whether refining lung cancer screening protocols is effective in preventing deaths. However, there are several practical problems to be resolved, including the balance of enrollment criteria and cost effectiveness, precise measurements to reduce false positive findings, risk-based optimization of screening frequency, challenges associated with cancer heterogeneity, strategies to combine image screening with novel biomarkers, dynamic monitoring of the natural history of cancer, accurate identification and diagnosis of cases among huge populations, and the impact of tobacco control policy and environment protection. As one in three individuals with lung cancer worldwide resides in China, these questions pose great challenges as well as research opportunities for population screening programs in China.

Mortality outcomes of low-dose computed tomography screening for lung cancer in urban China: a decision analysis and implications for practice.

BACKGROUND: Mortality outcomes in trials of low-dose computed tomography (CT) screening for lung cancer are inconsistent. This study aimed to evaluate whether CT screening in urban areas of China could reduce lung cancer mortality and to investigate the factors that associate with the screening effect. METHODS: A decision tree model with three scenarios (low-dose CT screening, chest X-ray screening, and no screening) was developed to compare screening results in a simulated Chinese urban cohort (100,000 smokers aged 45-80 years). Data of participant characteristics were obtained from national registries and epidemiological surveys for estimating lung cancer prevalence. The selection of other tree variables such as sensitivities and specificities of low-dose CT and chest X-ray screening were based on literature research. Differences in lung cancer mortality (primary outcome), false diagnoses, and deaths due to false diagnosis were calculated. Sensitivity analyses were performed to identify the factors that associate with the screening results and to ascertain worst and optimal screening effects considering possible ranges of the variables. RESULTS: Among the 100,000 subjects, there were 448, 541, and 591 lung cancer deaths in the low-dose CT, chest X-ray, and no screening scenarios, respectively (17.2% reduction in low-dose CT screening over chest X-ray screening and 24.2% over no screening). The costs of the two screening scenarios were 9387 and 2497 false diagnoses and 7 and 2 deaths due to false diagnosis among the 100,000 persons, respectively. The factors that most influenced death reduction with low-dose CT screening over no screening were lung cancer prevalence in the screened cohort, low-dose CT sensitivity, and proportion of early-stage cancers among low-dose CT detected lung cancers. Considering all possibilities, reduction in deaths (relative numbers) with low-dose CT screening in the worst and optimal cases were 16 (5.4%) and 288 (40.2%) over no screening, respectively. CONCLUSIONS: In terms of mortality outcomes, our findings favor conducting low-dose CT screening in urban China. However, approaches to reducing false diagnoses and optimizing important screening conditions such as enrollment criteria for screening are highly needed.

Who are the preferential targets for intervention programs related to the female condom among sex workers in southern China?

The authors used a cluster analysis approach to investigate which female sex workers (FSW) are preferential targets for female condom (FC) intervention programs in southern China. Cross-sectional 6-month (N = 316) and 12-month (N = 217) postintervention surveys of FSW were analyzed. Based on FC attitudes and beliefs, initially suggesting FC use to a partner, practicing insertion, total times ever used, and willingness to use in the future, cluster analysis apportioned women into two clusters, with 50.6% and 58.1% of participants in the likely future FC users group at 6 months and 12 months, respectively. Likely future FC users tended to be from boarding houses, older, currently or previously married, experienced with childbirth, with current multiple sex partners, longer history of sex work, and more unprotected sexual encounters. Focusing FC programs on sectors of the community with more FSW who are likely to use FC may be more cost-effective for enhancing FC acceptability and usage.