Categories
Nevin Manimala Statistics

Evaluation of machine learning algorithms for groundwater quality modeling

Environ Sci Pollut Res Int. 2023 Jan 30. doi: 10.1007/s11356-023-25596-3. Online ahead of print.

ABSTRACT

Groundwater quality is typically measured through water sampling and lab analysis. The field-based measurements are costly and time-consuming when applied over a large domain. In this study, we developed a machine learning-based framework to map groundwater quality in an unconfined aquifer in the north of Iran. Groundwater samples were provided from 248 monitoring wells across the region. The groundwater quality index (GWQI) in each well was measured and classified into four classes: very poor, poor, good, and excellent, according to their cut-off values. Factors affecting groundwater quality, including distance to industrial centers, distance to residential areas, population density, aquifer transmissivity, precipitation, evaporation, geology, and elevation, were identified and prepared in the GIS environment. Six machine learning classifiers, including extreme gradient boosting (XGB), random forest (RF), support vector machine (SVM), artificial neural networks (ANN), k-nearest neighbor (KNN), and Gaussian classifier model (GCM), were used to establish relationships between GWQI and its controlling factors. The algorithms were evaluated using the receiver operating characteristic curve (ROC) and statistical efficiencies (overall accuracy, precision, recall, and F-1 score). Accuracy assessment showed that ML algorithms provided high accuracy in predicting groundwater quality. However, RF was selected as the optimum model given its higher accuracy (overall accuracy, precision, and recall = 0.92; ROC = 0.95). The trained RF model was used to map GWQI classes across the entire region. Results showed that the poor GWQI class is dominant in the study area (covering 66% of the study area), followed by good (19% of the area), very poor (14% of the area), and excellent (< 1% of the area) classes. An area of very poor GWQI was observed in the north. Feature analysis indicated that the distance to industrial locations is the main factor affecting groundwater quality in the region. The study provides a cost-effective methodology in groundwater quality modeling that can be duplicated in other regions with similar hydrological and geological settings.

PMID:36715809 | DOI:10.1007/s11356-023-25596-3

Categories
Nevin Manimala Statistics

Coupling machine learning with signal process techniques and particle swarm optimization for forecasting flood routing calculations in the Eastern Black Sea Basin, Türkiye

Environ Sci Pollut Res Int. 2023 Jan 30. doi: 10.1007/s11356-023-25496-6. Online ahead of print.

ABSTRACT

With the effect of global warming, the frequency of floods, one of the most important natural disasters, increases, and this increases the damage it causes to people and the environment. Flood routing models play an important role in predicting floods so that all necessary precautions are taken before floods reach the region, loss of life and property in the region is prevented, and agricultural lands are protected. This research aims to compare the performance of hybrid machine learning models such as least-squares support vector machine technique hybridized with particle swarm optimization, empirical mode decomposition, variational mode decomposition, and discrete wavelet transform processes for flood routing estimation models in Ordu, Eastern Black Sea Basin, Türkiye. In addition, it is aimed to examine the effect of data division in flood forecasting. Accordingly, 70%, 80%, and 90% of the data were used for training, respectively. For this purpose, the flood data of 2009 and 2013 in Ordu were used. The performance of the established models was evaluated with the help of statistical indicators such as mean bias error, mean absolute percentage error, determination coefficient, Nash-Sutcliffe efficiency, Taylor Diagrams, and boxplot. As a result of the study, the particle swarm optimization least-squares support vector machine technique was chosen as the most successful model in predicting flood routing results. In addition, the optimum data partition ratio was found to be Train:70:Test:30 in the flood routing calculation. The findings are essential regarding flood management and taking necessary precautions before the flood occurs.

PMID:36715798 | DOI:10.1007/s11356-023-25496-6

Categories
Nevin Manimala Statistics

Does previous fragility fracture impact upon mortality in a hip fracture cohort? a retrospective study

Ir J Med Sci. 2023 Jan 30. doi: 10.1007/s11845-022-03267-5. Online ahead of print.

ABSTRACT

BACKGROUND: Fragility fractures are described as fractures resulting from low-energy trauma and are considered diagnostic of reduced bone mineral density or osteoporosis. They often present as hip fractures with hip fractures remaining a common but devastating injury among older patients. Many factors influence a patient’s risk of hip fracture and their subsequent risk of death.

AIM: In this study, we examined if previous fragility fracture impacts upon mortality after hip fracture.

METHODS: This was a retrospective single-center cohort study of patients included in the Irish Hip Fracture registry over a 5-year time period. Epidemiological data including gender, age, type of fracture, type of surgery, bone protection medication, American Society of Anesthetics (ASA) grade, and post-fracture outcomes including death at 30 days and death at 1 year were recorded. The presence or absence of a previous fragility fracture was examined to explore if a previous fragility fracture was an independent predictor of mortality.

RESULTS: There were 964 patients included, and 290 of whom had sustained a previous fragility fracture; 289 patients were males and 675 females, 33 patients had died in the 30 days following their surgery, and 180 patients had died within 1 year. We found statistically significant results for gender and age but not for previous fragility fracture influencing mortality (p value 0.230).

CONCLUSION: We found that previous fragility fracture does not impact upon mortality in a hip fracture cohort. However, gender and age did impact upon mortality in this study.

PMID:36715792 | DOI:10.1007/s11845-022-03267-5

Categories
Nevin Manimala Statistics

The influence of a probiotic/prebiotic supplement on microbial and metabolic parameters of equine cecal fluid or fecal slurry in vitro

J Anim Sci. 2023 Jan 28:skad034. doi: 10.1093/jas/skad034. Online ahead of print.

ABSTRACT

The microbes that reside within the equine hindgut create a complex and dynamic ecosystem. The equine hindgut microbiota is intimately associated with health and, as such, represents an area which can be beneficially modified. Synbiotics, supplements that combine probiotic microorganisms with prebiotic ingredients, are a potential means of influencing the hindgut microbiota to promote health and prevent disease. The objective of the current study was to evaluate the influence of an equine probiotic/prebiotic supplement on characteristics of the microbiota and metabolite production in vitro. Equine cecal fluid and fecal material were collected from an abattoir in QC, CAN. Five hundred ml of cecal fluid was used to inoculate chemostat vessels maintained as batch fermenters (chemostat cecal, n=11) with either 0g (control) or 0.44g of supplement added at 12h intervals. One hundred ml of cecal fluid (anaerobic cecal, n=15) or 5% fecal slurry (anaerobic fecal, n=6) were maintained in an anaerobic chamber with either 0g (control) or 0.356g of supplement added at the time of vessel establishment. Samples were taken from vessels at vessel establishment (0h), 24h, or 48h of incubation. Illumina sequencing of the V4 region of the 16S rRNA gene and bioinformatics were performed for microbiome analysis. Metabolite data was obtained via NMR spectroscopy. All statistical analyses were run in SAS 9.4. There was no effect of treatment at 24h or 48h on alpha or beta diversity indices and limited taxonomic differences were noted. Acetate, propionate, and butyrate were higher in treated compared to untreated vessels in all methods. A consistent effect of supplementation on the metabolic profile with no discernable impact on the microbiota of these in vitro systems indicates inoculum microbe viability and a utilization of the provided fermentable substrate within the systems. Although no changes within the microbiome were apparent, the consistent changes in metabolites indicates a potential prebiotic effect of the added supplement and merits further exploration.

PMID:36715114 | DOI:10.1093/jas/skad034

Categories
Nevin Manimala Statistics

Automated Creak Differentiates Adductor Laryngeal Dystonia and Muscle Tension Dysphonia

Laryngoscope. 2023 Jan 30. doi: 10.1002/lary.30588. Online ahead of print.

ABSTRACT

OBJECTIVE: The purpose of this study was to determine whether automated estimates of vocal creak would differentiate speakers with adductor laryngeal dystonia (AdLD) from speakers with muscle tension dysphonia (MTD) and speakers without voice disorders.

METHODS: Sixteen speakers with AdLD, sixteen speakers with MTD, and sixteen speakers without voice disorders were recorded in a quiet environment reading aloud a standard paragraph. An open-source creak detector was used to calculate the percentage of creak (% creak) in each of the speaker’s six recorded sentences.

RESULTS: A Kruskal-Wallis one-way analysis of variance revealed a statistically significant effect of group on the % creak with a large effect size. Pairwise Wilcoxon tests revealed a statistically significant difference in % creak between speakers with AdLD and controls as well as between speakers with AdLD and MTD. Receiver operating characteristic curve analyses indicated that % creak differentiated AdLD from both controls and speakers with MTD with high sensitivity and specificity (area under the curve statistics of 0.94 and 0.86, respectively).

CONCLUSION: Percentage of creak as calculated by an automated creak detector may be useful as a quantitative indicator of AdLD, demonstrating the potential for use as a screening tool or to aid in a differential diagnosis.

LEVEL OF EVIDENCE: 3 Laryngoscope, 2023.

PMID:36715109 | DOI:10.1002/lary.30588

Categories
Nevin Manimala Statistics

Mother-Child Neural Synchronization Is Time Linked to Mother-Child Positive Affective State Matching

Soc Cogn Affect Neurosci. 2023 Jan 27:nsad001. doi: 10.1093/scan/nsad001. Online ahead of print.

ABSTRACT

BACKGROUND: In the first years of life, in which self-regulation occurs via external means, mother-child synchronization of positive affect (PA) facilitates regulation of child homeostatic systems. Mother-child affective synchrony may contribute to mother-child synchronization of neural systems, but limited research has explored this possibility.

METHODS: Participants were 41 healthy mother-child dyads (56% girls; Mage=24.76 months; SD=8.77 months, Range=10 to 42 months). Mothers’ and children’s brain activity were assessed simultaneously using near-infrared spectroscopy while engaging in dyadic play. Mother and child PA during play were coded separately to characterize periods in which mothers and children (1) matched on high PA (2) matched on low/no PA or (3) showed a mismatch in PA. Models evaluated moment-to-moment correlations between affective matching and neural synchrony in mother-child dyads.

RESULTS: Greater positive affective synchrony, in which mother and child showed similarly high levels of PA but not similarly low levels of PA, was related to greater synchrony in medial and lateral frontal and temporoparietal regions. Age moderated associations between mother and child neural activity, but only during moments of high PA state matching.

CONCLUSIONS: Positive, synchronous mother-child interactions may foster greater neural responding in affective and social regions important for self-regulation and interpersonal bonds.

PMID:36715078 | DOI:10.1093/scan/nsad001

Categories
Nevin Manimala Statistics

A sensitive LC-MS/MS Method for the Simultaneous Determination of Skimmin, a Potential Agent for Treating Postpartum Stroke, and Its Metabolite Umbelliferone in Rat Plasma

J AOAC Int. 2023 Jan 28:qsad012. doi: 10.1093/jaoacint/qsad012. Online ahead of print.

ABSTRACT

BACKGROUND: Skimmin, a potential agent for treating postpartum stroke, is one of the most important coumarins extracted from the leave of skimmia.

OBJECTIVE: In this study, a specific, sensitive and simple high performance liquid chromatography with tandem mass spectrometry method for the simultaneous determination of skimmin and its metabolite umbelliferone in rat plasma was established and validated.

METHODS: Chromatographic separation was performed by an Inertsil ODS-3 column (50 mm × 4.6 mm, 5 μm) with a mobile phase consisting of 0.1% formic acid in distilled water-acetonitrile at a flow rate of 0.5 mL/min with gradient elution mode. All analytes were detected and quantified in negative multiple reaction monitoring.

RESULTS: All calibration curves shown good linearity (r > 0.995) over the concentration range of 10-10000 ng/mL and 2.0-2000 ng/mL for skimmin and umbelliferone, respectively. The selectivity, sensitivity, extraction recovery, matrix effect, and stability met all requirements.

CONCLUSIONS: The analysis method was successfully applied to pharmacokinetic study of skimmin and umbelliferone in rats following oral administration of skimmin at the doses of 10, 30 and 90 mg/kg. With the exception of AUC(0-∞) and Cmax, MRT and Cl/F of skimmin had significant statistical difference with the increasing doses. Skimmin might exhibit nonlinear pharmacokinetic characteristics in rats.

HIGHLIGHTS: This was the first study to investigate the pharmacokinetic characteristics of skimmin as a candidate agent for treating postpartum stroke.

PMID:36715062 | DOI:10.1093/jaoacint/qsad012

Categories
Nevin Manimala Statistics

Musculoskeletal Ultrasound in Monitoring the Efficacy of Gout: A Prospective Study Based on Tophus and Double Contour Sign Corresponding author

Balkan Med J. 2023 Jan 30. doi: 10.4274/balkanmedj.galenos.2022.2022-7-39. Online ahead of print.

ABSTRACT

BACKGROUND: In patients with gout receiving uric acid-lowering therapy, musculoskeletal ultrasound has the potential to observe changes in gout lesions.

AIMS: To analyze the effectiveness of uric acid-lowering therapy in patients with gout over one year using musculoskeletal ultrasound as a monitoring technique.

STUDY DESIGN: Prospective cross-sectional study.

METHODS: A total of 215 patients meeting the 1977 American College of Rheumatology gout classification criteria and treated with uric acid-lowering therapy were separated into two groups, treat-to-target and treat-to-non-target depending on the target serum urate levels. Lower extremity joints were evaluated by ultrasound before therapy (M0), as well as three (M3), six (M6), and twelve (M12) months after therapy. At various moments during uric acid-lowering therapy, the tophus size and the semiquantitative ultrasound scoring system of double contour sign were measured in the treat-to-target and treat-to-non-target groups.

RESULTS: Ninety-five tophi (45 in treat-to-target and 50 in treat-to-non-target) and sixty-seven double contour sign (34 in treat-to-target and 33 in treat-to-non-target) were evaluated longitudinally. In both groups, the long diameter, short diameter, and area of tophus in treat-to-target decreased as the duration of uric acid-lowering treatment increased. Differences in the long diameter of tophus between M12 and M0, M3 and M6 were statistically significant (P < 0.05), while differences between the other time points were not significant (P > 0.05). No statistically significant differences were observed in the short diameter and the area of tophus between M0 and M3 (P > 0.05), while there were statistically significant differences between other periods (P < 0.05). In treat-to-non-target, the long diameter, short diameter, and area of tophus showed a slight increase at different uric acid-lowering therapy time points. The differences in the long diameter, short diameter, and area of tophus at different uric acid-lowering therapy time points were not significant (P > 0.05). The semiquantitative ultrasound scoring system of double contour sign of treat-to-target sand treat-to-non-target showed a decreasing trend with increasing uric acid-lowering therapy time, with a more pronounced drop in treat-to-target than treat-to-non-target. In treat-to-target, the difference in the semiquantitative ultrasound scoring system of double contour sign at each uric acidlowering therapy time point was significant (P < 0.05). In treat-to-non-target, the difference in semiquantitative ultrasound scoring system of double contour sign scores between M0 and M3 was not statistically significant (P >0.05), but it was statistically significant for the remaining time points (P < 0.05).

CONCLUSION: After one year of uric acid-lowering therapy in patients with gout, an ultrasound indicated that the size of tophus and the semiquantitative ultrasound scoring system of double contour sign score decreased dramatically in the treat-to-target group. semiquantitative ultrasound scoring system of double contour sign score was dramatically reduced in the treat-to-non-target group, but the size of the tophus remained the same. Therefore, musculoskeletal ultrasound is an effective tool to monitor the efficacy of uric acid-lowering therapy.

PMID:36715053 | DOI:10.4274/balkanmedj.galenos.2022.2022-7-39

Categories
Nevin Manimala Statistics

Improved Glycemic Control Using a Bluetooth®-Connected Blood Glucose Meter and a Mobile Diabetes App: Real-World Evidence From Over 144 000 People With Diabetes

J Diabetes Sci Technol. 2023 Jan 30:19322968221148764. doi: 10.1177/19322968221148764. Online ahead of print.

ABSTRACT

BACKGROUND: The OneTouch Verio Flex® (OTVF) blood glucose (BG) meter features a ColorSure® Range Indicator. Diabetes management is enhanced by connecting the meter to the OneTouch Reveal® (OTR) mobile app. We sought to provide real-world evidence (RWE) that combining both devices improves glycemic control.

METHODS: Anonymized glucose and app analytics were extracted from a server from over 144 000 people with diabetes (PWDs). Data from their first 14 days using OTVF and OTR were compared with 14 days prior to 90- and 180-day timepoints using paired within-subject differences.

RESULTS: In people with type 1 diabetes (PwT1D) or people with type 2 diabetes (PwT2D), readings in-range (RIR) improved by +6.1 (54.5% to 60.6%) and +11.9 percentage points (68.2% to 80.1%), respectively, over 180 days, and hyperglycemia was reduced by -6.6 (40.5% to 33.9%) and -12.0 (30.3% to 18.3%). In total, 35% of PwT1D and 40% of PwT2D improved RIR by >10 percentage points. People with type 1 diabetes spending two to four sessions or 10 to 20 minutes per week on the app improved RIR by +5.1 and 7.0, respectively. People with type 2 diabetes spending two to four sessions or 10 to 20 minutes per week on the app improved RIR by +11.6 and 12.0, respectively. In PwT1D or PwT2D, mean BG reduced by -11.4 and -19.5 mg/dL, respectively, from baseline to 180 days, with no clinically meaningful changes in percentage of hypoglycemic readings. All glycemic changes were statistically significant (P < .0005 level).

CONCLUSION: Real-world data from over 144 000 PWDs demonstrated improved percentage readings in-range and reduced hyperglycemia in PWDs using the OneTouch Verio Flex blood glucose meter and OneTouch Reveal app.

PMID:36714954 | DOI:10.1177/19322968221148764

Categories
Nevin Manimala Statistics

Familial Risk of Gout and Interaction with Obesity and Alcohol Consumption: A Population-Based Cohort Study in Korea

Arthritis Care Res (Hoboken). 2023 Jan 30. doi: 10.1002/acr.25095. Online ahead of print.

ABSTRACT

OBJECTIVE: Population-based studies on the familial aggregation of gout are scarce and gene-environment interactions are not well-studied. We aimed to evaluate the familial aggregation of gout, as well as assess interactions between family history and obesity or alcohol consumption on the development of gout.

METHODS: Using the National Health Insurance database, which includes information on familial relationships and risk factor data, we identified 5,524,403 individuals from 2002-2018. Familial risk was calculated using hazard ratios (HRs) with 95% confidence intervals (CIs) which compare the risk of individuals with and without affected first-degree relatives (FDRs). Interactions between family history and obesity/alcohol consumption were assessed on an additive scale using the relative excess risk due to interaction (RERI).

RESULTS: Individuals with a gout-affected FDR had a 2.42-fold (95% CI 2.39-2.46) increased risk of disease compared to those with unaffected FDR. Having both a positive family history of gout and either overweight or moderate alcohol consumption was associated with a markedly increased risk of disease, with HRs of 4.39 (95% CI 4.29-4.49) and 2.28 (95% CI 2.22-2.35), respectively, which exceeded the sum of their individual risks, but was statistically significant only for overweight (RERI 0.96 95% CI 0.85-1.06). Obese individuals (RERI 1.88 95% CI 1.61-2.16) and heavy drinkers (RERI 0.36 95% CI 0.20-0.52) showed a more prominent interaction than overweight individuals and moderate drinkers, suggesting a dose-response interaction pattern.

CONCLUSION: Our findings indicate the possibility of an interaction between gout-associated genetic factors and obesity/alcohol consumption. This article is protected by copyright. All rights reserved.

PMID:36714912 | DOI:10.1002/acr.25095