Cross-Validation Indicates Predictive Models May Provide an Alternative to Indicator Organism Monitoring for Evaluating Pathogen Presence in Southwestern US Agricultural Water

Pathogen contamination of agricultural water has been identified as a probable cause of recalls and outbreaks. However, variability in pathogen presence and concentration complicates the reliable identification of agricultural water at elevated risk of pathogen presence. In this study, we collected data on the presence of Salmonella and genetic markers for enterohemorrhagic E. coli (EHEC; PCR-based detection of stx and eaeA) in southwestern US canal water, which is used as agricultural water for produce. We developed and assessed the accuracy of models to predict the likelihood of pathogen contamination of southwestern US canal water. Based on 169 samples from 60 surface water canals (each sampled 1–3 times), 36% (60/169) and 21% (36/169) of samples were positive for Salmonella presence and EHEC markers, respectively. Water quality parameters (e.g., generic E. coli level, turbidity), surrounding land-use (e.g., natural cover, cropland cover), weather conditions (e.g., temperature), and sampling site characteristics (e.g., canal type) data were collected as predictor variables. Separate conditional forest models were trained for Salmonella isolation and EHEC marker detection, and cross-validated to assess predictive performance. For Salmonella, turbidity, day of year, generic E. coli level, and % natural cover in a 500–1,000 ft (~150–300 m) buffer around the sampling site were the top 4 predictors identified by the conditional forest model. For EHEC markers, generic E. coli level, day of year, % natural cover in a 250–500 ft (~75–150 m) buffer, and % natural cover in a 500–1,000 ft (~150–300 m) buffer were the top 4 predictors. Predictive performance measures (e.g., area under the curve [AUC]) indicated predictive modeling shows potential as an alternative method for assessing the likelihood of pathogen presence in agricultural water. Secondary conditional forest models with generic E. coli level excluded as a predictor showed < 0.01 difference in AUC as compared to the AUC values for the original models (i.e., with generic E. coli level included as a predictor) for both Salmonella (AUC = 0.84) and EHEC markers (AUC = 0.92). Our data suggests models that do not require the inclusion of microbiological data (e.g., indicator organism) show promise for real-time prediction of pathogen contamination of agricultural water (e.g., in surface water canals).

Download Full-text

Extending the Holding Time for Agricultural Water Testing EPA Method 1603 for Produce Growers

Water ◽

10.3390/w11102020 ◽

2019 ◽

Vol 11 (10) ◽

pp. 2020

Author(s):

Manreet Singh Bhullar ◽

Angela Shaw ◽

Joseph Hannan ◽

Smaranda Andrews

Keyword(s):

Surface Water ◽

Test Time ◽

Time Interval ◽

Agricultural Water ◽

E Coli ◽

Produce Safety ◽

Water Testing ◽

Sample Test ◽

Safety Rule ◽

Us Epa

Agricultural water is a known vector for the transfer of foodborne pathogens onto fresh produce. Development of pre-harvest and post-harvest microbial profiles of agricultural water used by fresh produce growers, processors, and holdings is a requirement under the Food Safety Modernization Act Produce Safety Rule. One of the United States Environmental Protection Agency (US EPA) approved agricultural water testing methods is US EPA Method 1603, which requires no greater than a 6-h time frame between the collection of the water sample and initiation of analysis. This 6-h timeframe is unrealistic for many produce growers due to there being few laboratories certified to conduct testing and the geographic location of the farms. Agricultural water samples (n = 101) from well water and surface water were collected from 60 different farms to determine if holding samples for 24 h yielded significantly more generic Escherichia coli (E.coli) than 6 h using EPA 1603 method. A total of 32 samples were found contaminated with generic E. coli. Of these positive samples, surface water accounted for 87.5% of the samples (n = 28). There was no significant disparity between populations of generic E. coli at 6- and 24-h sample-test time interval (p > 0.05). These results provide evidence that the sample-test time interval can be extended to 24-h time, which makes quantitative generic E. coli testing for agricultural water as mandated by the FSMA Produce Safety Rule more accessible to growers.

Download Full-text

Evaluation of Microbiological Quality of Agricultural Water and Effect of Water Source and Holding Temperature on the Stability of Indicator Organisms' Levels by Seven U.S. Environmental Protection Agency–Approved Methods

Journal of Food Protection ◽

10.4315/0362-028x.jfp-19-381 ◽

2020 ◽

Vol 83 (2) ◽

pp. 249-255

Author(s):

ACHYUT ADHIKARI ◽

VIJAY SINGH CHHETRI ◽

ANDREA CAMAS

Keyword(s):

Surface Water ◽

Environmental Protection ◽

Environmental Protection Agency ◽

Water Source ◽

Indicator Organisms ◽

Agricultural Water ◽

Protection Agency ◽

E Coli ◽

Holding Temperature

ABSTRACT The Food Safety Modernization Act Produce Safety Rule requires covered produce growers to monitor the quality of their agricultural water on a regular basis by some U.S. Environmental Protection Agency (EPA)–approved methods recognized by the U.S. Food and Drug Administration. In this study, we evaluated the changes in the population of indicator organisms in surface water up to 6 months, and the effects of water source and holding temperature on the survival of indicator organisms by seven EPA-approved methods (five methods for Escherichia coli and two methods for Enterococcus). The levels of E. coli and Enterococcus in the surface water were variable with sampling month, ranging from 1.61 ± 0.04 to 2.68 ± 0.15 log most probable number (MPN)/100 mL and from undetectable level to 1.19 ± 0.29 log MPN/100 mL, respectively. At 25°C (holding temperature), there were significant reductions (P < 0.05) in E. coli and Enterococcus populations in surface water after 48 and 24 h, respectively, whereas at 4°C, no significant changes in the bacterial populations were observed up to 48 h. Methods 1603, 1604, 1103.1, 10029, and Colilert showed a comparable sensitivity in quantifying E. coli, whereas method 1600 and Enterolert showed a variable sensitivity with the type of water. The results indicated that regular monitoring of agricultural water is essential to examine whether the microbial quality of water is appropriate for its intended use. Water samples should be maintained at 4°C to minimize the changes in microbial populations between sampling and testing. The comparison of the sensitivity of EPA methods for quantifying indicator organisms could provide growers with useful information for choosing the method for their water quality analysis. HIGHLIGHTS

Download Full-text

Magnetic resonance cisternography imaging findings related to the leakage of Gadolinium into the subarachnoid space

Japanese Journal of Radiology ◽

10.1007/s11604-021-01137-1 ◽

2021 ◽

Author(s):

Rei Nakamichi ◽

Toshiaki Taoka ◽

Hisashi Kawai ◽

Tadao Yoshida ◽

Michihiko Sone ◽

...

Keyword(s):

Magnetic Resonance ◽

Subarachnoid Space ◽

Area Under The Curve ◽

Rank Correlation ◽

Predictive Performance ◽

Roc Curves ◽

Imaging Findings ◽

Spearman’S Rank Correlation ◽

Sagittal Sinus ◽

Magnetic Resonance Cisternography

Abstract Purpose To identify magnetic resonance cisternography (MRC) imaging findings related to Gadolinium-based contrast agent (GBCA) leakage into the subarachnoid space. Materials and methods The number of voxels of GBCA leakage (V-leak) on 3D-real inversion recovery images was measured in 56 patients scanned 4 h post-intravenous GBCA injection. Bridging veins (BVs) were identified on MRC. The numbers of BVs with surrounding cystic structures (BV-cyst), with arachnoid granulations protruding into the superior sagittal sinus (BV-AG-SSS) and the skull (BV-AG-skull), and including any of these factors (BV-incl) were recorded. Correlations between these variables and V-leak were examined based on the Spearman’s rank correlation coefficient. Receiver-operating characteristic (ROC) curves were generated to investigate the predictive performance of GBCA leakage. Results V-leak and the number of BV-incl were strongly correlated (r = 0.609, p < 0.0001). The numbers of BV-cyst and BV-AG-skull had weaker correlations with V-leak (r = 0.364, p = 0.006; r = 0.311, p = 0.020, respectively). The number of BV-AG-SSS was not correlated with V-leak. The ROC curve for contrast leakage exceeding 1000 voxels and the number of BV-incl had moderate accuracy, with an area under the curve of 0.871. Conclusion The number of BV-incl may be a predictor of GBCA leakage and a biomarker for waste drainage function without using GBCA.

Download Full-text

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients

Scientific Reports ◽

10.1038/s41598-021-81844-x ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Espen Jimenez-Solem ◽

Tonny S. Petersen ◽

Casper Hansen ◽

Christian Hansen ◽

Christina Lioma ◽

...

Keyword(s):

Prediction Models ◽

Severe Disease ◽

External Validation ◽

Area Under The Curve ◽

Predictive Performance ◽

Mortality Prediction ◽

Icu Admission ◽

Risk Of Death ◽

Online Risk ◽

The United Kingdom

AbstractPatients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics—Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.

Download Full-text

Limited Sampling Strategy for Determination of Ibrutinib Plasma Exposure: Joint Analyses with Metabolite Data

Pharmaceuticals ◽

10.3390/ph14020162 ◽

2021 ◽

Vol 14 (2) ◽

pp. 162

Author(s):

Félicien Le Louedec ◽

Fanny Gallais ◽

Fabienne Thomas ◽

Mélanie White-Koning ◽

Ben Allal ◽

...

Keyword(s):

Area Under The Curve ◽

Sampling Strategy ◽

Predictive Performance ◽

Pharmacokinetic Profile ◽

Limited Sampling Strategy ◽

Joint Analysis ◽

Therapeutic Drug ◽

Post Dose ◽

Limited Sampling ◽

Three Samples

Therapeutic drug monitoring of ibrutinib is based on the area under the curve of concentration vs. time (AUCIBRU) instead of trough concentration (Cmin,ss) because of a limited accumulation in plasma. Our objective was to identify a limited sampling strategy (LSS) to estimate AUCIBRU associated with Bayesian estimation. The actual AUCIBRU of 85 patients was determined by the Bayesian analysis of the full pharmacokinetic profile of ibrutinib concentrations (pre-dose T0 and 0.5, 1, 2, 4 and 6 h post-dose) and experimental AUCIBRU were derived considering combinations of one to four sampling times. The T0–1–2–4 design was the most accurate LSS (root-mean-square error RMSE = 11.0%), and three-point strategies removing the 1 h or 2 h points (RMSE = 22.7% and 14.5%, respectively) also showed good accuracy. The correlation between the actual AUCIBRU and Cmin,ss was poor (r2 = 0.25). The joint analysis of dihydrodiol-ibrutinib metabolite concentrations did not improve the predictive performance of AUCIBRU. These results were confirmed in a prospective validation cohort (n = 27 patients). At least three samples, within the pre-dose and 4 h post-dose period, are necessary to estimate ibrutinib exposure accurately.

Download Full-text

Prediction of the number of metastatic axillary lymph nodes in breast cancer by radiomic signature based on dynamic contrast-enhanced MRI

Acta Radiologica ◽

10.1177/02841851211025857 ◽

2021 ◽

pp. 028418512110258

Author(s):

Lan Li ◽

Tao Yu ◽

Jianqing Sun ◽

Shixi Jiang ◽

Daihong Liu ◽

...

Keyword(s):

Breast Cancer ◽

Lymph Nodes ◽

Area Under The Curve ◽

Test Group ◽

Predictive Performance ◽

Axillary Lymph Nodes ◽

Axillary Lymph ◽

Dynamic Contrast Enhanced ◽

Contrast Enhanced ◽

Delayed Phase

Background The number of metastatic axillary lymph nodes (ALNs) play a crucial role in the staging, prognosis and therapy of patients with breast cancer. Purpose To predict the number of metastatic ALNs in breast cancer via radiomics. Material and Methods We enrolled 197 patients with breast cancer who underwent dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). A total of 3386 radiomic features were extracted from the early- and delayed-phase subtraction images. To classify the number of metastatic ALNs, logistic regression was used to develop a radiomic signature and nomogram. Results The radiomic signature were constructed to distinguish the N0 group from the N+ (metastatic ALNs ≥ 1) group, which yielded area under the curve (AUC) values of 0.82 and 0.81 in the training and test group, respectively. Based on the radiomic signature and BI-RADS category, a nomogram was further developed and showed excellent predictive performance with AUC values of 0.85 and 0.89 in the training and test groups, respectively. Another radiomic signature was constructed to distinguish the N1 (1–3 ALNs) group from the N2–3 (≥4 metastatic ALNs) group and showed encouraging performance with AUC values of 0.94 and 0.84 in training and test group, respectively. Conclusions We developed a nomogram and a radiomic signature that can be used to predict ALN metastasis and distinguish the N1 from the N2-3 group. Both nomogram and radiomic signature may be potential tools to assist clinicians in assessing ALN metastasis in patients with breast cancer.

Download Full-text

A proof-of-concept study applying machine learning methods to putative risk factors for eating disorders: results from the multi-centre European project on healthy eating

Psychological Medicine ◽

10.1017/s003329172100489x ◽

2021 ◽

pp. 1-10

Author(s):

I. Krug ◽

J. Linardon ◽

C. Greenwood ◽

G. Youssef ◽

J. Treasure ◽

...

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Logistic Regression ◽

Predictive Accuracy ◽

Area Under The Curve ◽

Prediction Rule ◽

Predictive Performance ◽

Individual Risk ◽

European Project ◽

Wide Range

Abstract Background Despite a wide range of proposed risk factors and theoretical models, prediction of eating disorder (ED) onset remains poor. This study undertook the first comparison of two machine learning (ML) approaches [penalised logistic regression (LASSO), and prediction rule ensembles (PREs)] to conventional logistic regression (LR) models to enhance prediction of ED onset and differential ED diagnoses from a range of putative risk factors. Method Data were part of a European Project and comprised 1402 participants, 642 ED patients [52% with anorexia nervosa (AN) and 40% with bulimia nervosa (BN)] and 760 controls. The Cross-Cultural Risk Factor Questionnaire, which assesses retrospectively a range of sociocultural and psychological ED risk factors occurring before the age of 12 years (46 predictors in total), was used. Results All three statistical approaches had satisfactory model accuracy, with an average area under the curve (AUC) of 86% for predicting ED onset and 70% for predicting AN v. BN. Predictive performance was greatest for the two regression methods (LR and LASSO), although the PRE technique relied on fewer predictors with comparable accuracy. The individual risk factors differed depending on the outcome classification (EDs v. non-EDs and AN v. BN). Conclusions Even though the conventional LR performed comparably to the ML approaches in terms of predictive accuracy, the ML methods produced more parsimonious predictive models. ML approaches offer a viable way to modify screening practices for ED risk that balance accuracy against participant burden.

Download Full-text

A robust framework for shoulder implant X-ray image classification

Data Technologies and Applications ◽

10.1108/dta-08-2021-0210 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Minh Thanh Vo ◽

Anh H. Vo ◽

Tuong Le

Keyword(s):

Image Classification ◽

Performance Metrics ◽

State Of The Art ◽

Area Under The Curve ◽

Predictive Performance ◽

Extraction Process ◽

Content Type ◽

X Ray ◽

Robust Model ◽

Input Dataset

PurposeMedical images are increasingly popular; therefore, the analysis of these images based on deep learning helps diagnose diseases become more and more essential and necessary. Recently, the shoulder implant X-ray image classification (SIXIC) dataset that includes X-ray images of implanted shoulder prostheses produced by four manufacturers was released. The implant's model detection helps to select the correct equipment and procedures in the upcoming surgery.Design/methodology/approachThis study proposes a robust model named X-Net to improve the predictability for shoulder implants X-ray image classification in the SIXIC dataset. The X-Net model utilizes the Squeeze and Excitation (SE) block integrated into Residual Network (ResNet) module. The SE module aims to weigh each feature map extracted from ResNet, which aids in improving the performance. The feature extraction process of X-Net model is performed by both modules: ResNet and SE modules. The final feature is obtained by incorporating the extracted features from the above steps, which brings more important characteristics of X-ray images in the input dataset. Next, X-Net uses this fine-grained feature to classify the input images into four classes (Cofield, Depuy, Zimmer and Tornier) in the SIXIC dataset.FindingsExperiments are conducted to show the proposed approach's effectiveness compared with other state-of-the-art methods for SIXIC. The experimental results indicate that the approach outperforms the various experimental methods in terms of several performance metrics. In addition, the proposed approach provides the new state of the art results in all performance metrics, such as accuracy, precision, recall, F1-score and area under the curve (AUC), for the experimental dataset.Originality/valueThe proposed method with high predictive performance can be used to assist in the treatment of injured shoulder joints.

Download Full-text

Survival of cryptosporidium parvum, escherichia coli, faecal enterococci and clostridium perfringens in river water: influence of temperature and autochthonous microorganisms

Water Science & Technology ◽

10.2166/wst.1997.0742 ◽

1997 ◽

Vol 35 (11-12) ◽

pp. 249-252 ◽

Cited By ~ 61

Author(s):

G. J. Medema ◽

M. Bahar ◽

F. M. Schets

Keyword(s):

Surface Water ◽

River Water ◽

Cryptosporidium Parvum ◽

Health Hazard ◽

Influence Of Temperature ◽

E Coli ◽

Untreated Water ◽

Time Required ◽

Micro Organisms

Oocysts of Cryptosporidium parvum can survive for several months in surface water, one of the main factors determining their success in environmental transmission and thus their health hazard via water. Several factors in the environment, e.g. temperature, presence of predators and exo-enzymes will probably influence oocyst survival. The high persistence of oocysts may also limit the value of traditional faecal indicator bacteria. The aim of this study was to determine the rate at which C parvum oocysts, E coli, faecal enterococci and C perfringens spores die in surface water and the influence of temperature and the presence of autochthonous (micro)organisms on the die-off rate. Microcosms with autoclaved river water were inoculated with the organisms. Microcosms with untreated river water were inoculated with concentrated primary effluent containing the bacteria and with C parvum oocysts. Microcosms were incubated at 5°C or 15°C at 100rpm. Viability of oocysts was monitored by in vitro excystation and dye-exclusion; viability of the bacteria was determined on appropriate selective media. When pseudo first-order die-off kinetics were assumed, the die-off rate of oocysts at 5°C was 0.010 log10/d and at 15°C, 0.006–0.024 log10/d. These rates underestimate die-off since oocyst disintegration was not accounted for. Incubation in autoclaved or untreated water did influence the die-off rate of oocysts at 15°C but not at 5°C. The die-off rate of E coli and enterococci was faster in the non-sterile river water than in autoclaved water at both temperatures. At 15°C, E coli (and possibly E faecium) even multiplied in autoclaved water. In untreated river water, the die-off of E coli and enterococci was approximately 10x faster than die-off of oocysts but die-off rates of C perfringens were lower than those of oocysts. As for oocysts, die-off of the bacteria and spores was faster at 15°C than at 5°C. Oocysts are very persistent in river water: the time required for a 10x reduction in viability being 40–160d at 15°C and 100d at 5°C. Biological/biochemical activity influenced oocyst survival at 15°C and survival of both vegetative bacteria at 5 and 15°C. The rapid die-off of E coli and enterococci makes them less suitable as indicators of oocyst presence in water. As C perfringens survived longer in untreated river water than oocysts, it may prove useful as an indicator of the presence of C parvum.

Download Full-text

Factors Associated with Acute Community-Acquired Pyelonephritis Caused by Extended-Spectrum β-Lactamase-Producing Escherichia coli

Journal of Clinical Medicine ◽

10.3390/jcm10215192 ◽

2021 ◽

Vol 10 (21) ◽

pp. 5192

Author(s):

Mónica Romero Nieto ◽

Sara Maestre Verdú ◽

Vicente Gil ◽

Carlos Pérez Barba ◽

Jose Antonio Quesada Rico ◽

...

Keyword(s):

Roc Curve ◽

Goodness Of Fit ◽

Logistic Models ◽

Predictive Performance ◽

Demographic Characteristics ◽

E Coli ◽

Factors Associated ◽

Extended Spectrum ◽

Male Sex ◽

Tract Infections

This study aimed to identify the factors associated with the presence of extended-spectrum ß-lactamase-(ESBL) in patients with acute community-acquired pyelonephritis (APN) caused by Escherechia coli (E. coli), with a view of optimising empirical antibiotic therapy in this context. We performed a retrospective analysis of patients with community-acquired APN and confirmed E. coli infection, collecting data related to demographic characteristics, comorbidities, and treatment. The associations of these factors with the presence of ESBL were quantified by fitting multivariate logistic models. Goodness-of-fit and predictive performance were measured using the ROC curve. We included 367 patients of which 51 presented with ESBL, of whom 90.1% had uncomplicated APN, 56.1% were women aged ≤55 years, 33.5% had at least one mild comorbidity, and 12% had recently taken antibiotics. The prevalence of ESBL-producing E. coli was 13%. In the multivariate analysis, the factors independently associated with ESBL were male sex (OR 2.296; 95% CI 1.043–5.055), smoking (OR 4.846, 95% CI 2.376–9.882), hypertension (OR 3.342, 95% CI 1.423–7.852), urinary incontinence (OR 2.291, 95% CI 0.689–7.618) and recurrent urinary tract infections (OR 4.673, 95% CI 2.271–9.614). The area under the ROC curve was 0.802 (IC 95% 0.7307–0.8736), meaning our model can correctly classify an individual with ESBL-producing E. coli infection in 80.2% of cases.

Download Full-text