Predictive Value of Genetic Risk Scores in the Development of Colorectal Adenomas.

INTRODUCTION: Unlike colorectal cancer (CRC), few studies have explored the predictive value of genetic risk scores (GRS) in the development of colorectal adenomas (CRA), either alone or in combination with other demographic and clinical factors. METHODS: In this study, genomic DNA from 613 Spanish Caucasian patients with CRA and 829 polyp-free individuals was genotyped for 88 single-nucleotide polymorphisms (SNPs) associated with CRC risk using the MassArray™ (Sequenom) platform. After applying a multivariate logistic regression model, five SNPs were selected to calculate the GRS. Regression models adjusted by sex, age, family history of CRC, chronic use of NSAIDs, low-dose ASA, and consumption of tobacco were built in order to study the association between GRS and CRA risk. We evaluated the discriminatory capacity using the area under the receiver operating characteristic curve (AUC). The interactions between demographic information and GRS were also analyzed. RESULTS: Significant associations between high GRS values and risk of CRA for analyzed models were observed. In particular, patients with higher GRS values had 2.3-2.6-fold increase in risk of CRA compared to patients with middle values. Combining sex and age with the GRS significantly increased the discriminatory accuracy of the univariate model with GRS alone. The best model achieved an AUC value of 0.665 (95% CI: 0.63-0.69). The GRS showed a different behavior depending on sex and age. CONCLUSION: Our findings showed that, besides sex and age, GRS is an important risk factor for development of CRA and may be useful for CRC risk stratification and adaptation of screening programs.

Changes in severity, mortality, and virus genome among a Spanish cohort of patients hospitalized with SARS-CoV-2.

Comparing pandemic waves could aid in understanding the evolution of COVID-19. The objective of the present study was to compare the characteristics and outcomes of patients hospitalized for COVID-19 in different pandemic waves in terms of severity and mortality. We performed an observational retrospective cohort study of 5,220 patients hospitalized with SARS-CoV-2 infection from February to September 2020 in Aragon, Spain. We compared ICU admissions and 30-day mortality, clinical characteristics, and risk factors of the first and second waves of COVID-19. The SARS-CoV-2 genome was also analyzed in 236 samples. Patients in the first wave (n = 2,547) were older (median age 74 years [IQR 60-86] vs. 70 years [53-85]; p < 0.001) and had worse clinical and analytical parameters related to severe COVID-19 than patients in the second wave (n = 2,673). The probability of ICU admission at 30 days was 16% and 10% (p < 0.001) and the cumulative 30-day mortality rates 38% and 32% in the first and second wave, respectively (p = 0.007). Survival differences were observed among patients aged 60 to 80 years. We also found some variability among death risk factors and the viral genome between waves. Therefore, the two analyzed COVID-19 pandemic waves were different in terms of disease severity and mortality.

Evidence-Based Selection on the Appropriate FIT Cut-Off Point in CRC Screening Programs in the COVID Pandemic.

Background: The COVID pandemic has forced the closure of many colorectal cancer (CRC) screening programs. Resuming these programs is a priority, but fewer colonoscopies may be available. We developed an evidence-based tool for decision-making in CRC screening programs, based on a fecal hemoglobin immunological test (FIT), to optimize the strategy for screening a population for CRC. Methods: We retrospectively analyzed data collected at a regional CRC screening program between February/2014 and November/2018. We investigated two different scenarios: not modifying vs. modifying the FIT cut-off value. We estimated program outcomes in the two scenarios by evaluating the numbers of cancers and adenomas missed or not diagnosed in due time (delayed). Results: The current FIT cut-off (20-µg hemoglobin/g feces) led to 6,606 colonoscopies per 100,000 people invited annually. Without modifying this FIT cut-off value, when the optimal number of individuals invited for colonoscopies was reduced by 10-40%, a high number of CRCs and high-risk adenomas (34-135 and 73-288/100.000-people invited, respectively) will be undetected every year. When the FIT cut-off value was increased to where the colonoscopy demand matched the colonoscopy availability, the number of missed lesions per year was remarkably reduced (9-36 and 29-145/100.000 people, respectively). Moreover, the unmodified FIT scenario outcome was improved by prioritizing the selection process based on sex (males) and age, rather than randomly reducing the number invited. Conclusions: Assuming a mismatch between the availability and demand for annual colonoscopies, increasing the FIT cut-off point was more effective than randomly reducing the number of people invited. Using specific risk factors to prioritize access to colonoscopies should be also considered.

A Clinical Decision Web to Predict ICU Admission or Death for Patients Hospitalised with COVID-19 Using Machine Learning Algorithms.

The purpose of the study was to build a predictive model for estimating the risk of ICU admission or mortality among patients hospitalized with COVID-19 and provide a user-friendly tool to assist clinicians in the decision-making process. The study cohort comprised 3623 patients with confirmed COVID-19 who were hospitalized in the SALUD hospital network of Aragon (Spain), which includes 23 hospitals, between February 2020 and January 2021, a period that includes several pandemic waves. Up to 165 variables were analysed, including demographics, comorbidity, chronic drugs, vital signs, and laboratory data. To build the predictive models, different techniques and machine learning (ML) algorithms were explored: multilayer perceptron, random forest, and extreme gradient boosting (XGBoost). A reduction dimensionality procedure was used to minimize the features to 20, ensuring feasible use of the tool in practice. Our model was validated both internally and externally. We also assessed its calibration and provide an analysis of the optimal cut-off points depending on the metric to be optimized. The best performing algorithm was XGBoost. The final model achieved good discrimination for the external validation set (AUC = 0.821, 95% CI 0.787-0.854) and accurate calibration (slope = 1, intercept = -0.12). A cut-off of 0.4 provides a sensitivity and specificity of 0.71 and 0.78, respectively. In conclusion, we built a risk prediction model from a large amount of data from several pandemic waves, which had good calibration and discrimination ability. We also created a user-friendly web application that can aid rapid decision-making in clinical practice.

Prediction of Late-Onset Small for Gestational Age and Fetal Growth Restriction by Fetal Biometry at 35 Weeks and Impact of Ultrasound-Delivery Interval: Comparison of Six Fetal Growth Standards.

Small-for-gestational-age (SGA) infants have been associated with increased risk of adverse perinatal outcomes (APOs). In this work, we assess the predictive ability of the ultrasound-estimated percentile weight (EPW) at 35 weeks of gestational age to predict late-onset SGA and APOs, according to six growth standards, and whether the ultrasound-delivery interval influences the detection rate. To this purpose, we analyze a retrospective cohort study of 9585 singleton pregnancies. EPWs at 35 weeks were calculated to the customized Miguel Servet University Hospital (MSUH) and Figueras standards and the non-customized MSUH, Fetal Medicine Foundation (FMF), INTERGROWTH-21st, and WHO standards. As results of our analysis, for a 10% false positive rate, the detection rates for SGA ranged between 48.9% with the customized Figueras standard (AUC 0.82) and 60.8% with the non-customized FMF standard (AUC 0.87). Detection rates to predict SGA by ultrasound-delivery interval (1-6 weeks) show higher detection rates as intervals decrease. APOs detection rates ranged from 27.0% with FMF to 7.9% with the Figueras standard. In conclusion, the ability of EPW to predict SGA at 35 weeks is good for all standards, and slightly better for non-customized standards. The APO detection rate is significantly greater for non-customized standards.

Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear.

The increase in the proportion of elderly in Europe brings with it certain challenges that society needs to address, such as custodial care. We propose a scalable, easily modulated and live assistive technology system, based on a comfortable smart footwear capable of detecting walking behaviour, in order to prevent possible health problems in the elderly, facilitating their urban life as independently and safety as possible. This brings with it the challenge of handling the large amounts of data generated, transmitting and pre-processing that information and analysing it with the aim of obtaining useful information in real/near-real time. This is the basis of information theory. This work presents a complete system aiming at elderly people that can detect different user behaviours/events (sitting, standing without imbalance, standing with imbalance, walking, running, tripping) through information acquired from 20 types of sensor measurements (16 piezoelectric pressure sensors, one accelerometer returning reading for the 3 axis and one temperature sensor) and warn the relatives about possible risks in near-real time. For the detection of these events, a hierarchical structure of cascading binary models is designed and applied using artificial neural network (ANN) algorithms and deep learning techniques. The best models are achieved with convolutional layered ANN and multilayer perceptrons. The overall event detection performance achieves an average accuracy and area under the ROC curve of 0.84 and 0.96, respectively.

Prediction of Large for Gestational Age by Ultrasound at 35 Weeks and Impact of Ultrasound-Delivery Interval: Comparison of 6 Standards.

OBJECTIVE: The aim of the study was to assess the predictive ability of the ultrasound estimated percentile weight (EPW) at 35 weeks to predict large for gestational age (LGA) at term delivery according to 6 growth standards, including population, population-customized, and international references. The secondary objectives were to determine its predictive ability to detect adverse perinatal outcomes (APOs) and whether the ultrasound-delivery interval influences the detection rate of LGA newborns. METHODS: This was a retrospective cohort study of 9,585 singleton pregnancies. Maternal clinical characteristics, fetal ultrasound data obtained at 35 weeks, and pregnancy and perinatal outcomes were used to calculate EPWs to predict LGAs at delivery according to the customized and the non-customized (NC) Miguel Servet University Hospital (MSUH), the customized Figueras, the NC Fetal Medicine Foundation (FMF), the NC INTERGROWTH-21st, and the NC World Health Organization (WHO) standards. RESULTS: For a 10% false-positive rate, detection rates for total LGAs at delivery ranged from 31.2% with the WHO (area under the curve [AUC] 0.77; 95% confidence interval [CI], 0.76-0.79) to 56.5% with the FMF standard (AUC 0.85; 95% CI, 0.84-0.86). Detection rates and values of AUCs to predict LGAs by ultrasound-delivery interval (range 1-6 weeks) show higher detection rates as the interval decreases. APO detection rates ranged from 2.5% with the WHO to 12.6% with the Figueras standard. CONCLUSION: The predictive ability of ultrasound estimated fetal weight at 35 weeks to detect LGA infants is significantly greater for FMF and MSUH NC standards. In contrast, the APO detection rate is significantly greater for customized standards. The shorter ultrasound-delivery interval relates to better prediction rates.

A cohort study of fetal growth in twin pregnancies by chorionicity: comparison with European and American standards.

OBJECTIVE: To develop fetal growth standards for twin gestations by placental chorionicity in a Spanish population and compare them with European and American standards to estimate the suitability of their use in clinical practice. STUDY DESIGN: This was a retrospective cohort study of 518 twin pregnancies, 435 dichorionic-diamniotic and 83 monochorionic-diamniotic, performed between January 2012 and December 2017. A total of 4,783 and 1,455 estimated fetal weights were considered from the 17th to the 37th week of gestation, using multilevel models, to build dichorionic-diamniotic and monochorionic-diamniotic standards, respectively. The percentages of small and large for gestational age were calculated as a model adjustment measure and adjustment to the studied data and the values provided by our model were compared against those of six European and American twin standards and three singleton standards. Correlation analyses between percentile predictions were performed using Cohen kappa coefficient. The predictive ability to detect small for gestational age was also provided by the sensitivity and positive predictive value. RESULTS: We found slight differences between standards by chorionicity, being dichorionic-diamniotic percentiles slightly higher than monochorionic-diamniotic ones from the 17th to 37th weeks' gestation. For dichorionic-diamniotic cases, both our standard (9.8-8.2) and that of Grantz (8.2-10.5) showed good adjustments for the 10th and 90th percentiles while the other compared standards underestimated or overestimated them. For monochorionic-diamniotic cases, both our standard (10.2-8.5) and that of Shivkumar (11.4-6.8) had the most suitable adjustment. The correlation analysis between small and large for gestational age cases provided by standards, showed clear differences among them. Kappa's coefficient showed a substantial agreement between both Ananth (0.7) and Stirrup (0.69) dichorionic-diamniotic cases and our standard. There was also a substantial agreement between the Shivkumar (0.77) standard and our results for monochorionic-diamniotic cases. The correlation was moderate for all other comparisons. CONCLUSIONS: Our model showed a good adjustment to the studied population. There are clear differences among small and large for gestational age cases provided by twin standards in our studied population. The twin growth standards depend on the population characteristics and model structure. We found the use of singleton standards for twin pregnancies inadequate.