Categories
Nevin Manimala Statistics

Ticagrelor monotherapy in patients at high bleeding risk undergoing percutaneous coronary intervention: TWILIGHT-HBR

Eur Heart J. 2021 Oct 18:ehab702. doi: 10.1093/eurheartj/ehab702. Online ahead of print.

ABSTRACT

AIMS: Patients at high bleeding risk (HBR) represent a prevalent subgroup among those undergoing percutaneous coronary intervention (PCI). Early aspirin discontinuation after a short course of dual antiplatelet therapy (DAPT) has emerged as a bleeding avoidance strategy. The aim of this study was to assess the effects of ticagrelor monotherapy after 3-month DAPT in a contemporary HBR population.

METHODS AND RESULTS: This prespecified analysis of the TWILIGHT trial evaluated the treatment effects of early aspirin withdrawal followed by ticagrelor monotherapy in HBR patients undergoing PCI with drug-eluting stents. After 3 months of ticagrelor plus aspirin, event-free patients were randomized to 12 months of aspirin or placebo in addition to ticagrelor. A total of 1064 (17.2%) met the Academic Research Consortium definition for HBR. Ticagrelor monotherapy reduced the incidence of the primary endpoint of Bleeding Academic Research Consortium (BARC) 2, 3, or 5 bleeding compared with ticagrelor plus aspirin in HBR (6.3% vs. 11.4%; hazard ratio (HR) 0.53, 95% confidence interval (CI) 0.35-0.82) and non-HBR patients (3.5% vs. 5.9%; HR 0.59, 95% CI 0.46-0.77) with similar relative (Pinteraction = 0.67) but a trend towards greater absolute risk reduction in the former [-5.1% vs. -2.3%; difference in absolute risk differences (ARDs) -2.8%, 95% CI -6.4% to 0.8%, P = 0.130]. A similar pattern was observed for more severe BARC 3 or 5 bleeding with a larger absolute risk reduction in HBR patients (-3.5% vs. -0.5%; difference in ARDs -3.0%, 95% CI -5.2% to -0.8%, P = 0.008). There was no significant difference in the key secondary endpoint of death, myocardial infarction, or stroke between treatment arms, irrespective of HBR status.

CONCLUSIONS: Among HBR patients undergoing PCI who completed 3-month DAPT without experiencing major adverse events, aspirin discontinuation followed by ticagrelor monotherapy significantly reduced bleeding without increasing ischaemic events, compared with ticagrelor plus aspirin. The absolute risk reduction in major bleeding was larger in HBR than non-HBR patients.

PMID:34662382 | DOI:10.1093/eurheartj/ehab702

Categories
Nevin Manimala Statistics

Pre-eclampsia and risk of early-childhood asthma: a register study with sibling comparison and an exploration of intermediate variables

Int J Epidemiol. 2021 Oct 18:dyab204. doi: 10.1093/ije/dyab204. Online ahead of print.

ABSTRACT

BACKGROUND: We aimed to study whether pre-eclampsia is associated with childhood asthma, allergic and non-allergic asthma, accounting for family factors and intermediate variables.

METHODS: The study population comprised 779 711 children born in 2005-2012, identified from Swedish national health registers (n = 14 823/7410 exposed to mild/moderate and severe pre-eclampsia, respectively). We used Cox regression to estimate the associations of mild/moderate and severe pre-eclampsia with incident asthma, before and after age 2 years. Cox regressions were controlled for familial factors using sibling comparisons, then stratified on high and low risk for intermediate variables: caesarean section, prematurity and small for gestational age. We used logistic regression for allergic and non-allergic prevalent asthma at 6 years as a measure of more established asthma.

RESULTS: The incidence of asthma in children was 7.7% (n = 60 239). The associations varied from adjusted hazard ratio (adjHR) 1.11, 95% confidence interval (CI): 1.00, 1.24 for mild/moderate pre-eclampsia and asthma at >2 years age, to adjHR 1.78, 95% CI: 1.64, 1.95 for severe pre-eclampsia and asthma at <2 years age. Sibling comparisons attenuated most estimates except for the association between severe pre-eclampsia and asthma at <2 years age (adjHR 1.45, 95% CI: 1.10, 1.90), which also remained when stratifying for the risk of intermediates. Mild/moderate and severe pre-eclampsia were associated with prevalent non-allergic (but not allergic) asthma at 6 years, with adjusted odds ratio (adjOR) 1.17, 95% CI: 1.00, 1.36 and adjOR 1.51, 95% CI: 1.23, 1.84, respectively.

CONCLUSIONS: We found evidence that severe, but not mild/moderate, pre-eclampsia is associated with asthma regardless of familial factors and confounders.

PMID:34662374 | DOI:10.1093/ije/dyab204

Categories
Nevin Manimala Statistics

Integrating diverse data sources to predict disease risk in dairy cattle – a machine learning approach

J Anim Sci. 2021 Oct 18:skab294. doi: 10.1093/jas/skab294. Online ahead of print.

ABSTRACT

Livestock farming is currently undergoing a digital revolution and becoming increasingly data-driven. Yet, such data often reside in disconnected silos making it impossible to leverage their full potential to improve animal well-being. Here, we introduce a precision livestock farming approach, bringing together information streams from a variety of life domains of dairy cattle to study whether including more and diverse data sources improves the quality of predictions for eight diseases and whether using more complex prediction algorithms can, to some extent, compensate for less diverse data. Using three machine learning approaches of varying complexity (from logistic regression to gradient boosted trees) trained on data from 5,828 animals in 165 herds in Austria, we show that the prediction of lameness, acute and chronic mastitis, anestrus, ovarian cysts, metritis, ketosis (hyperketonemia) and periparturient hypocalcemia (milk fever) from routinely available data gives encouraging results. For example, we can predict lameness with high sensitivity and specificity (F1=0.74). An analysis of the importance of individual variables to prediction performance shows that disease in dairy cattle is a product of the complex interplay between a multitude of life domains such as housing, nutrition or climate, that including more and diverse data sources increases prediction performance and that the re-use of existing data can create actionable information for preventive interventions. Our findings pave the way towards data-driven point-of-care interventions and demonstrate the added value of integrating all available data in the dairy industry to improve animal well-being and reduce disease risk.

PMID:34662372 | DOI:10.1093/jas/skab294

Categories
Nevin Manimala Statistics

Prediction of municipality-level winter wheat yield based on meteorological data using machine learning in Hokkaido, Japan

PLoS One. 2021 Oct 18;16(10):e0258677. doi: 10.1371/journal.pone.0258677. eCollection 2021.

ABSTRACT

This study analyzed meteorological constraints on winter wheat yield in the northern Japanese island, Hokkaido, and developed a machine learning model to predict municipality-level yields from meteorological data. Compared to most wheat producing areas, this island is characterized by wet climate owing to greater annual precipitation and abundant snowmelt water supply in spring. Based on yield statistics collected from 119 municipalities for 14 years (N = 1,516) and high-resolution surface meteorological data, correlation analyses showed that precipitation, daily minimum air temperature, and irradiance during the grain-filling period had significant effects on the yield throughout the island while the effect of snow depth in early winter and spring was dependent on sites. Using 10-d mean meteorological data within a certain period between seeding and harvest as predictor variables and one-year-leave-out cross-validation procedure, performance of machine learning models based on neural network (NN), random forest (RF), support vector machine regression (SVR), partial least squares regression (PLS), and cubist regression (CB) were compared to a multiple linear regression model (MLR) and a null model that returns an average yield of the municipality. The root mean square errors of PLS, SVR, and RF were 872, 982, and 1,024 kg ha-1 and were smaller than those of MLR (1,068 kg ha-1) and null model (1,035 kg ha-1). These models outperformed the controls in other metrics including Pearson’s correlation coefficient and Nash-Sutcliffe efficiency. Variable importance analysis on PLS indicated that minimum air temperature and precipitation during the grain-filling period had major roles in the prediction and excluding predictors in this period (i.e. yield forecast with a longer lead-time) decreased forecast performance of the models. These results were consistent with our understanding of meteorological impacts on wheat yield, suggesting usefulness of explainable machine learning in meteorological crop yield prediction under wet climate.

PMID:34662365 | DOI:10.1371/journal.pone.0258677

Categories
Nevin Manimala Statistics

A new framework based on features modeling and ensemble learning to predict query performance

PLoS One. 2021 Oct 18;16(10):e0258439. doi: 10.1371/journal.pone.0258439. eCollection 2021.

ABSTRACT

A query optimizer attempts to predict a performance metric based on the amount of time elapsed. Theoretically, this would necessitate the creation of a significant overhead on the core engine to provide the necessary query optimizing statistics. Machine learning is increasingly being used to improve query performance by incorporating regression models. To predict the response time for a query, most query performance approaches rely on DBMS optimizing statistics and the cost estimation of each operator in the query execution plan, which also focuses on resource utilization (CPU, I/O). Modeling query features is thus a critical step in developing a robust query performance prediction model. In this paper, we propose a new framework based on query feature modeling and ensemble learning to predict query performance and use this framework as a query performance predictor simulator to optimize the query features that influence query performance. In query feature modeling, we propose five dimensions used to model query features. The query features dimensions are syntax, hardware, software, data architecture, and historical performance logs. These features will be based on developing training datasets for the performance prediction model that employs the ensemble learning model. As a result, ensemble learning leverages the query performance prediction problem to deal with missing values. Handling overfitting via regularization. The section on experimental work will go over how to use the proposed framework in experimental work. The training dataset in this paper is made up of performance data logs from various real-world environments. The outcomes were compared to show the difference between the actual and expected performance of the proposed prediction model. Empirical work shows the effectiveness of the proposed approach compared to related work.

PMID:34662344 | DOI:10.1371/journal.pone.0258439

Categories
Nevin Manimala Statistics

Food biodiversity and total and cause-specific mortality in 9 European countries: An analysis of a prospective cohort study

PLoS Med. 2021 Oct 18;18(10):e1003834. doi: 10.1371/journal.pmed.1003834. Online ahead of print.

ABSTRACT

BACKGROUND: Food biodiversity, encompassing the variety of plants, animals, and other organisms consumed as food and drink, has intrinsic potential to underpin diverse, nutritious diets and improve Earth system resilience. Dietary species richness (DSR), which is recommended as a crosscutting measure of food biodiversity, has been positively associated with the micronutrient adequacy of diets in women and young children in low- and middle-income countries (LMICs). However, the relationships between DSR and major health outcomes have yet to be assessed in any population.

METHODS AND FINDINGS: We examined the associations between DSR and subsequent total and cause-specific mortality among 451,390 adults enrolled in the European Prospective Investigation into Cancer and Nutrition (EPIC) study (1992 to 2014, median follow-up: 17 years), free of cancer, diabetes, heart attack, or stroke at baseline. Usual dietary intakes were assessed at recruitment with country-specific dietary questionnaires (DQs). DSR of an individual’s yearly diet was calculated based on the absolute number of unique biological species in each (composite) food and drink. Associations were assessed by fitting multivariable-adjusted Cox proportional hazards regression models. In the EPIC cohort, 2 crops (common wheat and potato) and 2 animal species (cow and pig) accounted for approximately 45% of self-reported total dietary energy intake [median (P10-P90): 68 (40 to 83) species consumed per year]. Overall, higher DSR was inversely associated with all-cause mortality rate. Hazard ratios (HRs) and 95% confidence intervals (CIs) comparing total mortality in the second, third, fourth, and fifth (highest) quintiles (Qs) of DSR to the first (lowest) Q indicate significant inverse associations, after stratification by sex, age, and study center and adjustment for smoking status, educational level, marital status, physical activity, alcohol intake, and total energy intake, Mediterranean diet score, red and processed meat intake, and fiber intake [HR (95% CI): 0.91 (0.88 to 0.94), 0.80 (0.76 to 0.83), 0.69 (0.66 to 0.72), and 0.63 (0.59 to 0.66), respectively; PWald < 0.001 for trend]. Absolute death rates among participants in the highest and lowest fifth of DSR were 65.4 and 69.3 cases/10,000 person-years, respectively. Significant inverse associations were also observed between DSR and deaths due to cancer, heart disease, digestive disease, and respiratory disease. An important study limitation is that our findings were based on an observational cohort using self-reported dietary data obtained through single baseline food frequency questionnaires (FFQs); thus, exposure misclassification and residual confounding cannot be ruled out.

CONCLUSIONS: In this large Pan-European cohort, higher DSR was inversely associated with total and cause-specific mortality, independent of sociodemographic, lifestyle, and other known dietary risk factors. Our findings support the potential of food (species) biodiversity as a guiding principle of sustainable dietary recommendations and food-based dietary guidelines.

PMID:34662340 | DOI:10.1371/journal.pmed.1003834

Categories
Nevin Manimala Statistics

Correction: Person-Generated Health Data in Women’s Health: Protocol for a Scoping Review

JMIR Res Protoc. 2021 Oct 18;10(10):e34211. doi: 10.2196/34211.

ABSTRACT

[This corrects the article DOI: 10.2196/26110.].

PMID:34662288 | DOI:10.2196/34211

Categories
Nevin Manimala Statistics

Machine Learning for Medical Coding in Healthcare Surveys

Vital Health Stat 1. 2021 Oct;(189):1-29.

ABSTRACT

Objectives Medical coding, or the translation of healthcare information into numeric codes, is expensive and time intensive. This exploratory study evaluates the use of machine learning classifiers to perform automated medical coding for large statistical healthcare surveys.

PMID:34662269

Categories
Nevin Manimala Statistics

Influence of drinking water quality on the formation of corrosion scales in lead-bearing drinking water distribution systems

J Environ Sci Health A Tox Hazard Subst Environ Eng. 2021 Oct 18:1-12. doi: 10.1080/10934529.2021.1989938. Online ahead of print.

ABSTRACT

Lead in drinking water occurs in drinking water distribution systems (DWDS) where lead pipes are used as service lines. Using data gathered from 4 different Canadian cities, we link drinking water quality to composition of corrosion scales obtained on exhumed lead pipes servicing those municipalities. The data presented encompasses a 10-year span and a detailed layer profile analysis of the solids present in lead bearing service lines; where different layers within the corrosion scale formed inside lead pipes are identified and thoroughly characterized. The results obtained clearly show that the corrosion layers in direct contact with drinking water are rich in lead oxides phases and aluminosilicates. In contrast, lead carbonates are the main phases present on corrosion scales in direct contact with the metallic lead pipe. This heterogeneity on phase distribution is correlated to the radial distance from the corrosion scales to the water/solid interphase and water quality servicing those municipalities. Statistical analysis suggests that dissolved Al, Mn, Cu, Ni, and As accumulate on the corrosion scales with preferential accumulation of specific elements heavily dependent on distinct municipality water quality.

PMID:34662261 | DOI:10.1080/10934529.2021.1989938

Categories
Nevin Manimala Statistics

Modified FOLFIRINOX Versus CISGEM Chemotherapy for Patients With Advanced Biliary Tract Cancer (PRODIGE 38 AMEBICA): A Randomized Phase II Study

J Clin Oncol. 2021 Oct 18:JCO2100679. doi: 10.1200/JCO.21.00679. Online ahead of print.

ABSTRACT

PURPOSE: Whether triplet chemotherapy is superior to doublet chemotherapy in advanced biliary tract cancer (BTC) is unknown.

METHODS: In this open-label, randomized phase II-III study, patients with locally advanced or metastatic BTC and an Eastern Cooperative Oncology Group performance status of 0 or 1 were randomly assigned (1:1) to receive oxaliplatin, irinotecan, and infusional fluorouracil (mFOLFIRINOX), or cisplatin and gemcitabine (CISGEM) for a maximum of 6 months. We report the results of the phase II part, where the primary end point was the 6-month progression-free survival (PFS) rate among the patients who received at least one dose of treatment (modified intention-to-treat population) according to Response Evaluation Criteria in Solid Tumors version 1.1 (statistical assumptions: 6-month PFS rate ≥ 59%, 73% expected).

RESULTS: A total of 191 patients (modified intention-to-treat population, 185: mFOLFIRINOX, 92; CISGEM, 93) were randomly assigned in 43 French centers. After a median follow-up of 21 months, the 6-month PFS rate was 44.6% (90% CI, 35.7 to 53.7) in the mFOLFIRINOX arm and 47.3% (90% CI, 38.4 to 56.3) in the CISGEM arm. Median PFS was 6.2 months (95% CI, 5.5 to 7.8) in the mFOLFIRINOX arm and 7.4 months (95% CI, 5.6 to 8.7) in the CISGEM arm. Median overall survival was 11.7 months (95% CI, 9.5 to 14.2) in the mFOLFIRINOX arm and 13.8 months (95% CI, 10.9 to 16.1) in the CISGEM arm. Adverse events ≥ grade 3 occurred in 72.8% of patients in the mFOLFIRINOX arm and 72.0% of patients in the CISGEM arm (toxic deaths: mFOLFIRINOX arm, two; CISGEM arm, one).

CONCLUSION: mFOLFIRINOX triplet chemotherapy did not meet the primary study end point. CISGEM doublet chemotherapy remains the first-line standard in advanced BTC.

PMID:34662180 | DOI:10.1200/JCO.21.00679