Meta-lasso: new insight on infection prediction after minimally invasive surgery.

Surgical site infection (SSI) after minimally invasive lung cancer surgery constitutes an important factor influencing the direct and indirect economic implications, patient prognosis, and the 5-year survival rate for early-stage lung cancer patients. In the realm of predictive healthcare, machine learning algorithms have been instrumental in anticipating various surgical outcomes, including SSI. However, accurately predicting infection after minimally invasive surgery remains a clinical challenge due to the multitude of physiological and surgical factors associated with it. Furthermore, clinical patient data, in addition to being high-dimensional, often exists the long-tail problem, posing difficulties for traditional machine learning algorithms in effectively processing such data. Based on this insight, we propose a novel approach called meta-lasso for infection prediction following minimally invasive surgery. Our approach leverages the sparse learning algorithm lasso regression to select informative features and introduces a meta-learning framework to mitigate bias towards the dominant class. We conducted a retrospective cohort study on patients who had undergone minimally invasive surgery for lung cancer at Shanghai Chest Hospital between 2018 and 2020. The evaluation encompassed key performance metrics, including sensitivity, specificity, precision (PPV), negative predictive value (NPV), and accuracy. Our approach has surpassed the performance of logistic regression, random forest, Naive Bayes classifier, gradient boosting decision tree, ANN, and lasso regression, with sensitivity at 0.798, specificity at 0.779, precision at 0.789, NPV at 0.798, and accuracy at 0.788 and has greatly improved the classification performance of the inferior class.

Comparing the influence of big data resources on medical knowledge recall for staff with and without medical collaboration platform.

BACKGROUND: This study aims to examine how big data resources affect the recall of prior medical knowledge by healthcare professionals, and how this differs in environments with and without remote consultation platforms. METHOD: This study investigated two distinct categories of medical institutions, namely 132 medical institutions with platforms, and 176 medical institutions without the platforms. Big data resources are categorized into two levels-medical institutional level and public level-and three types, namely data, technology, and services. The data are analyzed using SmartPLS2. RESULTS: (1) In both scenarios, shared big data resources at the public level have a significant direct impact on the recall of prior medical knowledge. However, there is a significant difference in the direct impact of big data resources at the institutional level in both scenarios. (2) In institutions with platforms, for the three big data resources (the medical big data assets and big data deployment technical capacity at the medical institutional level, and policies of medical big data at the public level) without direct impacts, there exist three indirect pathways. (3) In institutions without platforms, for the two big data resources (the service capability and big data technical capacity at the medical institutional level) without direct impacts, there exist three indirect pathways. CONCLUSIONS: The different interactions between big data, technology, and services, as well as between different levels of big data resources, affect the way clinical doctors recall relevant medical knowledge. These interaction patterns vary between institutions with and without platforms. This study provides a reference for governments and institutions to design big data environments for improving clinical capabilities.

Development of a Nomogram for Predicting Surgical Site Infection in Patients with Resected Lung Neoplasm Undergoing Minimally Invasive Surgery.

Background: Predictive models are necessary to target high-risk populations and provide precision interventions for patients with lung neoplasm who suffer from surgical site infections (SSI). Patients and Methods: This case control study included patients with lung neoplasm who underwent minimally invasive surgeries (MIS). Logistic regression was used to generate the prediction model of SSI, and a nomogram was created. A receiver operator characteristic (ROC) curve was used to examine the predictive value of the model. Results: A total of 151 patients with SSI were included, and 604 patients were randomly selected among the patients without SSI (ratio 4:1). Male gender (odds ratio [OR], 2.55; 95% confidence interval [CI], 1.57-4.15; p < 0.001), age >60 years (OR, 2.10; 95% CI, 1.29-3.44, p = 0.003), operation time >60 minutes (all categories, p < 0.05), treatments for diabetes mellitus (OR, 2.96; 95% CI, 1.75-4.98l; p < 0.001), and best forced expiratory volume in 1 second (FEV1)/forced vital capacity (FVC; OR, 0.96; 95% CI, 0.94-0.99; p = 0.008) were independently associated with SSI. The model based on these variables showed an area under the curve (AUC) of 0.813 for predicting SSI. Conclusions: A nomogram predictive model was successfully established for predicting SSI in patients receiving MIS, with good predictive value.

Is adherence to the Chinese Dietary Guidelines associated with better self-reported health? The Chinese Dietary Guidelines Adherence Score.

BACKGROUND AND OBJECTIVES: Poor adherence to dietary guidelines is related to physical and mental disorders, as reflected in self-reported health statuses. This study evaluates the association between diet quality and selfreported health within the Shanghai Diet and Health Study. METHODS AND STUDY DESIGN: We used Chinese Dietary Guidelines Adherence scores to assess diet quality in a cross-sectional study of 4487 subjects above 15 years of age, who completed three-day 24h diet recalls and responded to self-reported health questionnaires. A composite health score was calculated based on Item Response Theory, using the Rasch model. Multiple linearregression models were evaluated to assess the relationship between self-reported health status and diet quality. RESULTS: Based on the various adherence scores, we divided our sample into fifths. Based on these divisions and with the exception of a single instance, our results show a significant trend: self-reported health declines with declining adherence to official dietary guidelines. This trend was even significant when controlling for a large number of potential confounders. CONCLUSIONS: This study shows that consumption of a healthy and balanced diet, as reflected in adherence to the Chinese Dietary Guidelines, is related to increased levels of overall health among Shanghai residents.

Potential impact of B lineage mismatch on trivalent influenza vaccine effectiveness during the 2015-2016 influenza season among nursery school children in Suzhou, China.

BACKGROUND: We actively followed a cohort of nursery school children in Suzhou, China to assess the impact of vaccination with trivalent influenza vaccine on the prevention of influenza like illness (ILI). METHODS: We enrolled children aged 36 to 72 months from 13 nursery schools in Suzhou starting two weeks after vaccination during October 2015-February 2016. Every school-day, teachers reported the names of students with ILI to study clinicians, who collected the student's nasopharyngeal swab or throat swab, either at a study clinic or the child's home. Swabs were sent to the Suzhou Center for Disease Control and Prevention's laboratory for influenza testing by RT-PCR. RESULTS: In total, 3278 children were enrolled; 83 (3%) were lost to follow-up, while 3195 (vaccinated: 1492, unvaccinated: 1703) were followed for 24 weeks. During the study, 40 samples tested positive; 17 in the vaccinated (B Victoria: 12; A(H1N1)pdm09: 5) and 23 in the unvaccinated group (B Victoria: 10; B Yamagata: 2; A(H1N1)pdm09: 11). The VE estimates were: 16% overall (95%CI:-58%,56%), 48% (-47%,84%) for influenza A(H1N1)pdm09, 43% (-650%,98%) for influenza B Yamagata, and -37% (-227%,42%) for influenza B Victoria. Data were analyzed by vaccinated and unvaccinated groups based on enrollees' vaccination records. CONCLUSIONS: The VE for A(H1N1)pdm09 was moderate but not significant. Mismatching of B lineage may have compromised trivalent influenza vaccine effectiveness during the 2015-2016 influenza season among nursery school children in Suzhou, China. Additional larger studies are warranted to inform policy related to quadrivalent influenza vaccine licensure in China in the future.

Seasonal influenza vaccine effectiveness against medically attended influenza illness among children aged 6-59 months, October 2011-September 2012: A matched test-negative case-control study in Suzhou, China.

BACKGROUND: Seasonal influenza infections among young children in China lead to substantial numbers of hospitalizations and financial burden. This study assessed the seasonal influenza vaccine effectiveness (VE) against laboratory confirmed medically attended influenza illness among children in Suzhou, China, from October 2011-September 2012. METHODS: We conducted a test-negative case-control study among children aged 6-59 months who sought care at Soochow University Affiliated Children's Hospital (SCH) from October 2011-September 2012. A case was defined as a child with influenza-like illness (ILI) or severe acute respiratory infection (SARI) with an influenza-positive nasopharyngeal swab by rRT-PCR. Controls were selected from children presenting with ILI or SARI without laboratory confirmed influenza. We conducted 1:1 matching by age and admission date. Vaccination status was verified from the citywide immunization system database. VE was calculated with conditional logistic regression: (1-OR)×100%. RESULT: During the study period, 2634 children aged 6-59 months presented to SCH with ILI (1975) or SARI (659) and were tested for influenza. The vaccination records were available for 69% (1829; ILI: 1354, SARI: 475). Among those, 23% (427) tested positive for influenza, and were included as cases. Among influenza positive cases, the vaccination rates were 3.2% for SARI and 4.5% for ILI. Among controls, the vaccination rates were 13% for SARI, and 11% for ILI. The overall VE against lab-confirmed medically attended influenza virus infection was 67% (95% CI: 41-82). The VE for SARI was 75% (95% CI: 11-93) and for ILI was 64% (95% CI: 31-82). CONCLUSIONS: The seasonal influenza vaccine was effective against medically attended lab-confirmed influenza infection in children aged 6-59 months in Suzhou, China in the 2011-12 influenza season. Increasing seasonal influenza vaccination among young children in Suzhou may decrease medically attended influenza-associated ILI and SARI cases in this population.

The spatial analysis on hemorrhagic fever with renal syndrome in Jiangsu province, China based on geographic information system.

BACKGROUND: Hemorrhagic fever with renal syndrome (HFRS) is endemic in mainland China, accounting for 90% of total reported cases worldwide, and Jiangsu is one of the most severely affected provinces. In this study, the authors conducted GIS-based spatial analyses in order to determine the spatial distribution of the HFRS cases, identify key areas and explore risk factors for public health planning and resource allocation. METHODS: Interpolation maps by inverse distance weighting were produced to detect the spatial distribution of HFRS cases in Jiangsu from 2001 to 2011. Spatio-temporal clustering was applied to identify clusters at the county level. Spatial correlation analysis was conducted to detect influencing factors of HFRS in Jiangsu. RESULTS: HFRS cases in Jiangsu from 2001 to 2011 were mapped and the results suggested that cases in Jiangsu were not distributed randomly. Cases were mainly distributed in northeastern and southwestern Jiangsu, especially in Dafeng and Sihong counties. It was notable that prior to this study, Sihong county had rarely been reported as a high-risk area of HFRS. With the maximum spatial size of 50% of the total population and the maximum temporal size of 50% of the total population, spatio-temporal clustering showed that there was one most likely cluster (LLR = 624.52, P<0.0001, RR = 8.19) and one second-most likely cluster (LLR = 553.97, P<0.0001, RR = 8.25), and both of these clusters appeared from 2001 to 2004. Spatial correlation analysis showed that the incidence of HFRS in Jiangsu was influenced by distances to highways, railways, rivers and lakes. CONCLUSION: The application of GIS together with spatial interpolation, spatio-temporal clustering and spatial correlation analysis can effectively identify high-risk areas and factors influencing HFRS incidence to lay a foundation for researching its pathogenesis.

Spatio-temporal trends and risk factors for Shigella from 2001 to 2011 in Jiangsu Province, People's Republic of China.

OBJECTIVE: This study aimed to describe the spatial and temporal trends of Shigella incidence rates in Jiangsu Province, People's Republic of China. It also intended to explore complex risk modes facilitating Shigella transmission. METHODS: County-level incidence rates were obtained for analysis using geographic information system (GIS) tools. Trend surface and incidence maps were established to describe geographic distributions. Spatio-temporal cluster analysis and autocorrelation analysis were used for detecting clusters. Based on the number of monthly Shigella cases, an autoregressive integrated moving average (ARIMA) model successfully established a time series model. A spatial correlation analysis and a case-control study were conducted to identify risk factors contributing to Shigella transmissions. RESULTS: The far southwestern and northwestern areas of Jiangsu were the most infected. A cluster was detected in southwestern Jiangsu (LLR = 11674.74, P<0.001). The time series model was established as ARIMA (1, 12, 0), which predicted well for cases from August to December, 2011. Highways and water sources potentially caused spatial variation in Shigella development in Jiangsu. The case-control study confirmed not washing hands before dinner (OR = 3.64) and not having access to a safe water source (OR = 2.04) as the main causes of Shigella in Jiangsu Province. CONCLUSION: Improvement of sanitation and hygiene should be strengthened in economically developed counties, while access to a safe water supply in impoverished areas should be increased at the same time.

Spatial analyses of typhoid fever in Jiangsu province, People's Republic of China.

An analysis of the geographical distribution of typhoid incidence rates, based on various statistical approaches such as trend surface, spatial autocorrelation, spatial correlation and spatial regression, was carried out at the county level in Jiangsu province, People's Republic of China. Temperature, moisture content, proximity to water bodies and the normalized difference vegetation index in the autumn were the four underlying factors found to contribute the most to the development of the epidemic. Typhoid infection was most severe in the south-eastern region of Jiangsu and a significant hotspot with high positive autocorrelation was detected in Taicang county in the south-east of the province. To improve the typhoid situation, intervention efforts should be concentrated in the south-eastern region of the province, targeting the hotspot and include reduction of lake pollution.

Geographical information systems-based spatial analysis and implications for syphilis interventions in Jiangsu province, People's Republic of China.

Spatial distribution rules and risk factors for syphilis were studied in Jiangsu province, People's Republic of China during 2005 and 2009. Trend surface analysis, spatial autocorrelation analysis and spatio-temporal clustering were applied with the incidence rates of the various counties in the province to determine spatial distribution rules and risk factors. Syphilis was found to be most severe in the southern region of the province where many counties could be shown to be hotspots with positive autocorrelation. Clusters were detected in the south-western region of Jiangsu with the county-level city of Yixing as the centre. Temperature, distance from railways and highways, and the normalised difference vegetation index were determined as supporting variables with regard to the transmission of the disease by both univariate and multivariate spatial correlation analyses. Interventions, including health education and awareness campaigns, should be strengthened throughout the province targeting the south-western areas, especially the clusters and hotspots detected in order to improve the situation.

Spatial distribution of HIV/AIDS in Yunnan province, People's Republic of China.

Risk maps for the geographical distribution of human immunodeficiency virus (HIV) and the acquired immune deficiency syndrome (AIDS) are needed for the direction of HIV prevention interventions. Our study, based on county-level data on the numbers of HIV/AIDS patients in the Yunnan province, People's Republic of China, applied trend surface analysis and spatial autocorrelation analysis to demonstrate the geographical distribution of HIV-positive patients in the province. The case load of HIV was found to be most severe in the central-west region of the province. While Kunming county was shown to be negatively correlated with its surrounding counties, many high-burden counties are surrounded by other counties with similar case numbers. We conclude that intervention efforts in Yunnan province should concentrate on the western and northeast regions, targeting the hotspots of infection.

[Study on the spatial distribution of AIDS based on geographic information system in Jiangsu province].

OBJECTIVE: To analyze the spatial distribution of AIDS in every city of Jiangsu province, trying to describe the geographic characteristics of AIDS and to develop a prediction model. METHODS: Numbers of patients in Jiangsu province were collected, to establish the database for the geographic information system, then setting up a 'risk map' of the disease. Spatial, autocorrelation. Linear spatial analyses were used to study the patients' numbers. RESULTS: (1) Results from the autocorrelation analysis showed that the distribution of AIDS was clustered at some places and was at random on the whole. The results also indicated that the distribution of AIDS in Nanjing was of negative correlation, while that in Suzhou and Wuxi were of positive correlation but in Tongshan, Wujiang, Pukou, Nanjing, Lishui, Wuxi and Suzhou showed seven locations of clusters with significantly higher numbers of patients. (2) The trend of 'surface analysis map' indicated that the disease was more severe in the southern than in the northern parts of Jiangsu province. (3) Ordinary Least Squares method was finally used in the linear spatial regression and the results were: t = -1.045 103 (P = 0.299 904); t = -1.443 668 (P = 0.153 714) respectively. CONCLUSION: According to the feature spatial distribution of the disease, effective measures should be taken to prevent and to keep the prevalence of AIDS under control.