538 research outputs found
Machine Learning Models Cannot Replace Screening Colonoscopy for the Prediction of Advanced Colorectal Adenoma
No full textScreening for colorectal cancer (CRC) continues to rely on colonoscopy and/or fecal occult blood testing since other (non-invasive) risk-stratification systems have not yet been implemented into European guidelines. In this study, we evaluate the potential of machine learning (ML) methods to predict advanced adenomas (AAs) in 5862 individuals participating in a screening program for colorectal cancer. Adenomas were diagnosed histologically with an AA being ≥ 1 cm in size or with high-grade dysplasia/villous features being present. Logistic regression (LR) and extreme gradient boosting (XGBoost) algorithms were evaluated for AA prediction. The mean age was 58.7 ± 9.7 years with 2811 males (48.0%), 1404 (24.0%) of whom suffered from obesity (BMI ≥ 30 kg/m2), 871 (14.9%) from diabetes, and 2095 (39.1%) from metabolic syndrome. An adenoma was detected in 1884 (32.1%), as well as AAs in 437 (7.5%). Modelling 36 laboratory parameters, eight clinical parameters, and data on eight food types/dietary patterns, moderate accuracy in predicting AAs with XGBoost and LR (AUC-ROC of 0.65–0.68) could be achieved. Limiting variables to established risk factors for AAs did not significantly improve performance. Moreover, subgroup analyses in subjects without genetic predispositions, in individuals aged 45–80 years, or in gender-specific analyses showed similar results. In conclusion, ML based on point-prevalence laboratory and clinical information does not accurately predict AAs
Gastroenterologist against the machine - opportunities and limitations of machine learning models for prediction of advanced adenoma
No full textBackground & Aims Screening for colorectal cancer (CRC) relies on colonoscopy and/or fecal occult blood test while other (non-invasive) risk-stratification systems have not been implemented into European guidelines. Here, we evaluated the potential of Machine Learning (ML) methods to optimize prediction of advanced adenoma (AA).
Patients & Methods 5862 individuals participating in a screening program for colorectal cancer were included after excluding patients with history of CRC, symptomatic patients and those with insufficient colonoscopy. Adenoma were diagnosed histologically with AA being ≥1cm in size, or high-grade dysplasia/ villous features being present. Clinical, laboratory and lifestyle parameters were assessed at the time of colonoscopy. Logistic regression (LR) and extreme gradient boosting algorithms (XGBoost) were evaluated for AA-prediction based on readily-available laboratory/clinical/lifestyle parameters. The dataset was divided into a derivation cohort (for model development and internal cross-validation) and an external validation cohort.
Results The mean age was 58.7±9.7 years with 2811 males (48.0 %). 1404 (24.0 %) suffered from obesity (BMI≥30kg/m2), 871 (14.9 %) from diabetes, and 2095 (39.1 %) from the metabolic syndrome. Any adenoma was detected in 1884 (32.1 %) and any AA in 437 (7.5 %). 659 individuals (11.2 %) had a first-degree relative with a history of CRC. Modelling 36 laboratory parameters, 8 clinical parameters and data on 8 food types/dietary patterns, a moderate accuracy to predict AA with XGBoost (AUC of 0.66-0.68) and LR (AUC of 0.65-0.66) could be achieved. Limiting variables to established risk factors for AA did not significantly improve performance. Also, subgroup analyses in subjects without genetic predisposition or gender-specific analyses showed similar results.
Conclusion ML, based on point prevalence laboratory and clinical information, does not accurately predict AA. Non-invasive risk-prediction seems insufficient to replace current CRC screening programs. However, the potential for sequential application before colonoscopy to increase pre-test probability warrants further investigation
A parameterized geometric magnetic field calibration method for vehicles with moving masses with applications to underwater gliders
No full textAuthor Posting. © The Author(s), 2016. This is the author's version of the work. It is posted here by permission of John Wiley & Sons for personal use, not for redistribution. The definitive version was published in Journal of Field Robotics 34 (2017): 209-223, doi:10.1002/rob.21660.The accuracy of magnetic measurements performed by autonomous vehicles is often limited
by the presence of moving ferrous masses. This work presents a parameterized ellipsoid
eld calibration method for magnetic measurements in the sensor frame. In this manner
the ellipsoidal calibration coe cients are dependent on the locations of the moving masses.
The parameterized calibration method is evaluated through eld trials with an autonomous
underwater glider equipped with a low power precision
uxgate sensor. A rst set of eld
trials were performed in the East Arm of Bonne Bay, Newfoundland in December of 2013.
During these trials a series of calibration pro les with the mass shifting and ballast mecha-
nisms at di erent locations were performed before and after the survey portion of the trials.
Further trials were performed in the Labrador Sea in July of 2014 with two reduced sets
of calibration runs. The nominal ellipsoidal coe cients were extracted using the full set
of measurements from a set of calibration pro les and used as the initial conditions for
the polynomials which de ne each parameterized coe cient. These polynomials as well as
the sensor misalignment matrix were then optimized using a gradient descent solver which
minimizes both the total magnetic eld di erence and the vertical magnetic eld variance
between the modeled and measured values. Including the vertical eld in this manner allows
for convergence in spite of severe limitations on the platform's motion and for computation
of the vehicle's magnetic heading.This work was supported by the Natural Sciences and Engineering Research Council (NSERC) through the
NSERC Canadian Field Robotics Network (NCFRN), the Research Development Corporation, the Marine
Institute and Memorial University of Newfoundland.2017-06-0
[The fossil record of the Eurasian Neogene insectivores (Erinaceomorpha, Soricomorpha, Mammalia) : Part I / L.W. van den Hoek Ostende, C.S. Doukas and J.W.F. Reumer (editors)]: Austria
No full textIntroduction Small mammals, and especially insectivores, long have been the stepchildren in Austrian palaeontology, although Hofmann described an insectivore species, Plesiosorex styriacus, from two Styrian sites as early as 1892. In 1893 the same author described and figured an erinaceid tooth, now known as Lantanotherium sp., from Göriach in Styria.
Thenius (1949) presented a revision of the insectivores of the Styrian Tertiary, that is the Miocene. No insectivores were known from other parts of Austria at that time, partly because research was centred in Vienna and Graz; many more fossil sites are known from the eastern parts of Austria, which, however, mainly yielded large mammals. Systematic searches for small mammals by means of screen washing techniques only began in the middle of the 20th century. Until then, finds of small mammals were more or less a side-product of the search for large mammals. The first large-scale excavations, which also yielded lots of small mammals, among them insectivores, started in 1955 in the Kohfidisch caves and fissures in Burgenland, and in the 1960s at the Eichkogel site near Mödling in the Vienna Basin. Bachmayer, Zapfe, Thenius and their students initiated and conducted the excavations at these sites. The Kohfidisch fauna, including the insectivores, was presented by Bachmayer & Wilson (1970, 1978, 1980), but not all of the material was taken into account in these contributions. Some insectivores from the Eichkogel were published by Rabeder (1973). The rodents of this site have been published in a number of papers by Daxner-Höck (e.g. 1972, 1977, 1981). Excavations of the Pliocen
A sex-specific propensity-adjusted analysis of colonic adenoma detection rates in a screening cohort
No full textThe prevalence of colorectal adenoma and advanced adenoma (AA) differs between sexes. Also, the optimal age for the first screening colonoscopy is under debate. We, therefore, performed a sex-specific and age-adjusted comparison of adenoma, AA and advanced neoplasia (AN) rates in a real-world screening cohort. In total, 2824 asymptomatic participants between 45- and 60-years undergoing screening colonoscopy at a single-centre in Austria were evaluated. 46% were females and mean age was 53 ± 4 years. A propensity score for being female was calculated, and adenoma, AA and AN detection rates evaluated using uni- and multivariable logistic regression. Sensitivity analyses for three age groups (group 1: 45 to 49 years, n = 521, 41% females, mean age 47 ± 1 years; group 2: 50 to 54 years, n = 1164, 47% females, mean age 52 ± 1 years; group 3: 55 to 60 years, n = 1139, 46% females, mean age 57 ± 2 years) were performed. The prevalence of any adenoma was lower in females (17% vs. 30%; OR 0.46, 95% CI 0.38-0.55; p < 0.001) and remained so after propensity score adjustment for baseline characteristics and lifestyle factors (aOR 0.52, 95% CI 0.41-0.66; p < 0.001). The same trend was seen for AA with a significantly lower prevalence in females (3% vs. 7%; OR 0.38, 95% CI 0.26-0.55; p < 0.001) that persisted after propensity score adjustment (aOR 0.54, 95% CI 0.34-0.86; p = 0.01). Also, all age-group sensitivity analyses showed lower adenoma, AA and AN rates in females. Similar numbers needed to screen to detect an adenoma, an AA or AN were found in female age group 3 and male age group 1. Colorectal adenoma, AA and AN were consistently lower in females even after propensity score adjustment and in all age-adjusted sensitivity analyses. Our study may add to the discussion of the optimal age for initial screening colonoscopy which may differ between the sexes
Nonalcoholic Fatty Liver Disease in Lean Subjects: Associations With Metabolic Dysregulation and Cardiovascular Risk—A Single-Center Cross-Sectional Study
No full textINTRODUCTION
Although a milder metabolic phenotype of nonalcoholic fatty liver disease (NAFLD) in lean patients (body mass index [BMI] <25 kg/m2) compared to overweight/obese patients with NAFLD is assumed, the relevance of NAFLD among lean subjects remains a matter of debate. We aimed to characterize the metabolic/cardiovascular phenotype of lean patients with NAFLD.
METHODS
In total, 3,043 subjects (cohort I) and 1,048 subjects (cohort II) undergoing screening colonoscopy between 2010 and 2020 without chronic liver disease other than NAFLD were assigned to one of the following groups: lean patients without NAFLD, lean NAFLD, overweight NAFLD (BMI 25-30 kg/m2), and obese NAFLD (BMI >30 kg/m2). Diagnosis of NAFLD was established using ultrasound (cohort I) and controlled attenuation parameter (cohort II).
RESULTS
The prevalence of lean patients with NAFLD was 6.7%/16.1% in the overall cohort I/II and 19.7%/40.0% in lean subjects of cohort I/II. Compared with lean subjects without NAFLD, lean patients with NAFLD had a higher prevalence of dyslipidemia, dysglycemia, and the metabolic syndrome, together with a higher median Framingham risk score in both cohorts (all P < 0.001). On multivariable analyses, NAFLD in lean subjects was associated with higher odds of metabolic syndrome (adjusted odds ratio cohort I: 4.27 [95% confidence interval (CI): 2.80-6.51], P < 0.001; cohort II: 2.97 [95% CI: 1.40-6.33], P < 0.001), and higher Framingham risk score (regression coefficient B cohort I: 1.93 [95% CI: 0.95-2.92], P < 0.003; cohort II: 1.09 [95% CI: 0.81-2.10], P = 0.034), among others. Only 69.8% of lean patients with NALFD in cohort I and 52.1% in cohort II fulfilled the novel criteria for metabolic associated fatty liver disease.
DISCUSSION
NAFLD in lean patients is associated with the metabolic syndrome and increased cardiovascular risk. Novel metabolic associated fatty liver disease criteria leave a considerable proportion of patients unclassified
Nut consumption and the prevalence and severity of non-alcoholic fatty liver disease
No full textBACKGROUND
Nut consumption has been associated with reduced inflammation, insulin resistance, and oxidative stress. However, the influence on the prevalence and severity of non-alcoholic fatty liver disease (NAFLD) has yet to be evaluated.
METHODS
4655 subjects were included as part of a colorectal carcinoma screening program (SAKKOPI) between 07/2010 and 07/2019 and analyzed 2020. Patients were characterized using biochemical and metabolic parameters, as well as a detailed questionnaire on dietary habits. The diagnosis of NAFLD was established using abdominal ultrasound. Consumption of nuts was graded as: no consumption or <1 time/week, 1-6 times/week, 1 time/day and ≥2 times/day.
RESULTS
Mean age was 58.5±9.8years with a mean BMI of 26.5±4.7kg/m2. 2058 (44.2%) patients suffered from the metabolic syndrome, 2407 (51.6%) had arterial hypertension, 2287 (49.1%) showed prediabetes/diabetes, 1854 (39.4%) had dyslipidemia and 1984 patients (43.5%) were diagnosed with NAFLD. Prevalence of metabolic syndrome (1219 [48.7%] vs. 605 [40.2%] vs. 189 [37.4%] vs. 45 [31.7%], p2.67: aOR: 0.551 [95%CI: 0.338-0.898], p = 0.017; Forns-Index >6.9: aOR: 0.585 [95%CI: 0.402-0.850], p = 0.005).
CONCLUSIONS
Nut consumption might exert beneficial effects on the prevalence of NAFLD in males. The negative association with advanced fibrosis warrants further investigation
Atrial Fibrillation: A New Indicator for Advanced Colorectal Neoplasia in Screening Colonoscopy
No full textBACKGROUND
Colorectal cancer (CRC) is a common and potentially preventable malignancy. Evidence has emerged that coronary artery disease patients are at increased risk for developing CRC by shared risk factors. Here we investigated an association between CRC and atrial fibrillation (AF), a surrogate marker of cardiovascular risk, in the setting of routine screening colonoscopy.
METHODS
We investigated 1949 asymptomatic participants (median age 61 [54-67] years, 49% females) undergoing screening colonoscopy within the SAKKOPI registry (Salzburg Colon Cancer Prevention Initiative). Forty-six participants with AF (2.4%) were identified, and colonoscopy findings were compared to non-AF participants. Propensity Score Matching (PSM) was used to create 1:1 and 3:1 age- and gender-matched couples.
RESULTS
Abnormal findings on screening colonoscopy (any form of adenoma or carcinoma) were more common in AF participants with an odds ratios (OR) of 2.4 [1.3-4.3] in the unmatched analysis, and 2.6 [1.1-6.3] and 2.0 [1.1-4.0] in the 1:1 and 3:1 matched groups, respectively. Correspondingly, the odds of finding advanced adenomas or carcinomas was elevated about three-fold across the different matched and unmatched analyses (OR 3.3 [1.1-10.8] for 3:1 matched participants). At the same time, the prevalence and number of colonic lesions were significantly higher in AF participants (63.0% vs. 33.4% for 3:1 matched participants, p < 0.001). Non-CRC related findings on colonoscopy, like diverticulosis, were non-different between groups.
CONCLUSION
Participants with AF had a higher burden of advanced premalignant adenomas and CRC in routine colonoscopy screening. Our data suggest that practitioners should monitor the CRC screening status, especially in AF patients
- …
