Landslide precipitation thresholds in Rwanda

Abstract Regional empirical-statistical thresholds indicating the precipitation conditions initiating landslides are of crucial importance for landslide early warning system development. The objectives of this research were to use landslide and precipitation data in an empirical-statistical approach to (1) identify precipitation-related variables with the highest explanatory power for landslide occurrence and (2) define both trigger and trigger-cause based thresholds for landslides in Rwanda, Central-East Africa. Receiver operating characteristics (ROC) and area under the curve (AUC) metrics were used to test the suitability of a suite of precipitation-related explanatory variables. A Bayesian probabilistic approach, maximum true skill statistics and the minimum radial distance were used to determine the most informative threshold levels above which landslide are high likely to occur. The results indicated that the event precipitation volumes E, cumulative 1-day rainfall (RD1) that coincide with the day of landslide occurrence and 10-day antecedent precipitation are variables with the highest discriminatory power to distinguish landslide from no landslide conditions. The highest landslide prediction capability in terms of true positive alarms was obtained from single rainfall variables based on trigger-based thresholds. However, that predictive capability was constrained by the high rate of false positive alarms and thus the elevated probability to neglect the contribution of additional causal factors that lead to the occurrence of landslides and which can partly be accounted for by the antecedent precipitation indices. Further combination of different variables into trigger-cause pairs and the use of suitable thresholds in bilinear format improved the prediction capacity of the real trigger-based thresholds.

Download Full-text

Rainfall-Induced Landslide Prediction Using Machine Learning Models: The Case of Ngororero District, Rwanda

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph17114147 ◽

2020 ◽

Vol 17 (11) ◽

pp. 4147

Author(s):

Martin Kuradusenge ◽

Santhi Kumaran ◽

Marco Zennaro

Keyword(s):

Machine Learning ◽

Early Warning ◽

False Negative ◽

Early Warning Systems ◽

Rainfall Data ◽

Precipitation Data ◽

Operating Characteristics ◽

Landslide Prediction ◽

Landslide Occurrence ◽

Antecedent Precipitation

Landslides fall under natural, unpredictable and most distractive disasters. Hence, early warning systems of such disasters can alert people and save lives. Some of the recent early warning models make use of Internet of Things to monitor the environmental parameters to predict the disasters. Some other models use machine learning techniques (MLT) to analyse rainfall data along with some internal parameters to predict these hazards. The prediction capability of the existing models and systems are limited in terms of their accuracy. In this research paper, two prediction modelling approaches, namely random forest (RF) and logistic regression (LR), are proposed. These approaches use rainfall datasets as well as various other internal and external parameters for landslide prediction and hence improve the accuracy. Moreover, the prediction performance of these approaches is further improved using antecedent cumulative rainfall data. These models are evaluated using the receiver operating characteristics, area under the curve (ROC-AUC) and false negative rate (FNR) to measure the landslide cases that were not reported. When antecedent rainfall data is included in the prediction, both models (RF and LR) performed better with an AUC of 0.995 and 0.997, respectively. The results proved that there is a good correlation between antecedent precipitation and landslide occurrence rather than between one-day rainfall and landslide occurrence. In terms of incorrect predictions, RF and LR improved FNR to 10.58% and 5.77% respectively. It is also noted that among the various internal factors used for prediction, slope angle has the highest impact than other factors. Comparing both the models, LR model’s performance is better in terms of FNR and it could be preferred for landslide prediction and early warning. LR model’s incorrect prediction rate FNR = 9.61% without including antecedent precipitation data and 3.84% including antecedent precipitation data.

Download Full-text

End-to-end convolutional neural network enables COVID-19 detection from breath and cough audio: a pilot study

BMJ Innovations ◽

10.1136/bmjinnov-2021-000668 ◽

2021 ◽

Vol 7 (2) ◽

pp. 356-362

Author(s):

Harry Coppock ◽

Alex Gaskell ◽

Panagiotis Tzirakis ◽

Alice Baird ◽

Lyn Jones ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Low Cost ◽

Area Under The Curve ◽

Alternative Form ◽

Economic Damage ◽

Audio Signals ◽

Operating Characteristics ◽

Data Set ◽

Empirical Performance

BackgroundSince the emergence of COVID-19 in December 2019, multidisciplinary research teams have wrestled with how best to control the pandemic in light of its considerable physical, psychological and economic damage. Mass testing has been advocated as a potential remedy; however, mass testing using physical tests is a costly and hard-to-scale solution.MethodsThis study demonstrates the feasibility of an alternative form of COVID-19 detection, harnessing digital technology through the use of audio biomarkers and deep learning. Specifically, we show that a deep neural network based model can be trained to detect symptomatic and asymptomatic COVID-19 cases using breath and cough audio recordings.ResultsOur model, a custom convolutional neural network, demonstrates strong empirical performance on a data set consisting of 355 crowdsourced participants, achieving an area under the curve of the receiver operating characteristics of 0.846 on the task of COVID-19 classification.ConclusionThis study offers a proof of concept for diagnosing COVID-19 using cough and breath audio signals and motivates a comprehensive follow-up research study on a wider data sample, given the evident advantages of a low-cost, highly scalable digital COVID-19 diagnostic tool.

Download Full-text

Multi-scale characterizations of colon polyps via computed tomographic colonography

Visual Computing for Industry Biomedicine and Art ◽

10.1186/s42492-019-0032-7 ◽

2019 ◽

Vol 2 (1) ◽

Author(s):

Weiguo Cao ◽

Marc J. Pomeroy ◽

Yongfeng Gao ◽

Matthew A. Barish ◽

Almas F. Abbasi ◽

...

Keyword(s):

Area Under The Curve ◽

Texture Features ◽

Learning Model ◽

Colon Polyps ◽

Texture Descriptor ◽

Operating Characteristics ◽

Computed Tomographic ◽

Multi Scale ◽

Definition Of ◽

Occurrence Matrix

AbstractTexture features have played an essential role in the field of medical imaging for computer-aided diagnosis. The gray-level co-occurrence matrix (GLCM)-based texture descriptor has emerged to become one of the most successful feature sets for these applications. This study aims to increase the potential of these features by introducing multi-scale analysis into the construction of GLCM texture descriptor. In this study, we first introduce a new parameter - stride, to explore the definition of GLCM. Then we propose three multi-scaling GLCM models according to its three parameters, (1) learning model by multiple displacements, (2) learning model by multiple strides (LMS), and (3) learning model by multiple angles. These models increase the texture information by introducing more texture patterns and mitigate direction sparsity and dense sampling problems presented in the traditional Haralick model. To further analyze the three parameters, we test the three models by performing classification on a dataset of 63 large polyp masses obtained from computed tomography colonoscopy consisting of 32 adenocarcinomas and 31 benign adenomas. Finally, the proposed methods are compared to several typical GLCM-texture descriptors and one deep learning model. LMS obtains the highest performance and enhances the prediction power to 0.9450 with standard deviation 0.0285 by area under the curve of receiver operating characteristics score which is a significant improvement.

Download Full-text

Diagnostic work up of anemic patients: role of iron deficiency

LaboratoriumsMedizin ◽

10.1515/labmed-2020-0060 ◽

2020 ◽

Vol 0 (0) ◽

Author(s):

Daniela Meiser ◽

Lale Kayikci ◽

Matthias Orth

Keyword(s):

Iron Deficiency ◽

Complete Blood Count ◽

Iron Status ◽

Area Under The Curve ◽

Diagnostic Value ◽

Diagnostic Tools ◽

Operating Characteristics ◽

Inflammatory Conditions ◽

Reliable Parameter ◽

Work Up

AbstractObjectivesDiagnosing disturbances in iron metabolism can be challenging when accompanied by inflammation. New diagnostic tools such as the “Thomas-plot” (TP) (relation of soluble transferrin receptor [sTfR]/log ferritin to reticulocyte hemoglobin content [RET-He]) were established to improve classification of anemias. Aim of this retrospective study was to assess the added diagnostic value of the TP in anemia work up.MethodsPatients from December 2016 to September 2018 with a complete blood count, iron status, RET-He and sTfR were manually classified into the four quadrants of the TP on basis of conventional iron markers. Manual and algorithm-based classifications were compared using cross tabulations, Box–Whisker-Plots as well as Receiver-Operating-Characteristics (ROC) to calculate the diagnostic accuracy using Area under the Curve (AUC) analysis.ResultsA total of 3,745 patients with a conventional iron status, including 1,721 TPs, could be evaluated. In 70% of the cases the manual classification was identical to the TP, in 10% it was deviant. 20% could not clearly be classified, mostly due to inflammatory conditions. In the absence of an inflammatory condition, ferritin was a reliable parameter to define iron deficiency (ID) (AUC 0.958). In the presence of inflammation, the significance of the ferritin index (AUC 0.917) and of the RET-He (AUC 0.957) increased.ConclusionsThe TP can be useful for narrowing down the causes of anemia in complex cases. Further studies with focus on special patient groups, e.g., oncological or rheumatic patients, are desirable.

Download Full-text

New screening approach to detecting congenital syphilis in China: a retrospective cohort study

Archives of Disease in Childhood ◽

10.1136/archdischild-2020-320549 ◽

2020 ◽

pp. archdischild-2020-320549

Author(s):

Fang Hu ◽

Shuai-Jun Guo ◽

Jian-Jun Lu ◽

Ning-Xuan Hua ◽

Yan-Yan Song ◽

...

Keyword(s):

Predictive Value ◽

Congenital Syphilis ◽

Area Under The Curve ◽

Diagnostic Tools ◽

Operating Characteristics ◽

Loss To Follow Up ◽

Sensitivity Specificity ◽

Mother To Child ◽

Rule Out

BackgroundDiagnosis of congenital syphilis (CS) is not straightforward and can be challenging. This study aimed to evaluate the validity of an algorithm using timing of maternal antisyphilis treatment and titres of non-treponemal antibody as predictors of CS.MethodsConfirmed CS cases and those where CS was excluded were obtained from the Guangzhou Prevention of Mother-to-Child Transmission of syphilis programme between 2011 and 2019. We calculated sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) using receiver operating characteristics (ROC) in two situations: (1) receiving antisyphilis treatment or no-treatment during pregnancy and (2) initiating treatment before 28 gestational weeks (GWs), initiating after 28 GWs or receiving no treatment for syphilis seropositive women.ResultsAmong 1558 syphilis-exposed children, 39 had confirmed CS. Area under the curve, sensitivity and specificity of maternal non-treponemal titres before treatment and treatment during pregnancy were 0.80, 76.9%, 78.7% and 0.79, 69.2%, 88.7%, respectively, for children with CS. For the algorithm, ROC results showed that PPV and NPV for predicting CS were 37.3% and 96.4% (non-treponemal titres cut-off value 1:8 and no antisyphilis treatment), 9.4% and 100% (non-treponemal titres cut-off value 1:16 and treatment after 28 GWs), 4.2% and 99.5% (non-treponemal titres cut-off value 1:32 and treatment before 28 GWs), respectively.ConclusionsAn algorithm using maternal non-treponemal titres and timing of treatment during pregnancy could be an effective strategy to diagnose or rule out CS, especially when the rate of loss to follow-up is high or there are no straightforward diagnostic tools.

Download Full-text

First trimester prediction of maternal glycemic status

Journal of Perinatal Medicine ◽

10.1515/jpm-2014-0149 ◽

2015 ◽

Vol 43 (3) ◽

Cited By ~ 8

Author(s):

Rinat Gabbay-Benziv ◽

Lauren E. Doyle ◽

Miriam Blitzer ◽

Ahmet A. Baschat

Keyword(s):

Risk Score ◽

Predictive Value ◽

Challenge Test ◽

Area Under The Curve ◽

First Trimester ◽

Tolerance Test ◽

Oral Glucose ◽

Operating Characteristics ◽

Maternal Characteristics ◽

Predictive Algorithm

AbstractTo predict gestational diabetes mellitus (GDM) or normoglycemic status using first trimester maternal characteristics.We used data from a prospective cohort study. First trimester maternal characteristics were compared between women with and without GDM. Association of these variables with sugar values at glucose challenge test (GCT) and subsequent GDM was tested to identify key parameters. A predictive algorithm for GDM was developed and receiver operating characteristics (ROC) statistics was used to derive the optimal risk score. We defined normoglycemic state, when GCT and all four sugar values at oral glucose tolerance test, whenever obtained, were normal. Using same statistical approach, we developed an algorithm to predict the normoglycemic state.Maternal age, race, prior GDM, first trimester BMI, and systolic blood pressure (SBP) were all significantly associated with GDM. Age, BMI, and SBP were also associated with GCT values. The logistic regression analysis constructed equation and the calculated risk score yielded sensitivity, specificity, positive predictive value, and negative predictive value of 85%, 62%, 13.8%, and 98.3% for a cut-off value of 0.042, respectively (ROC-AUC – area under the curve 0.819, CI – confidence interval 0.769–0.868). The model constructed for normoglycemia prediction demonstrated lower performance (ROC-AUC 0.707, CI 0.668–0.746).GDM prediction can be achieved during the first trimester encounter by integration of maternal characteristics and basic measurements while normoglycemic status prediction is less effective.

Download Full-text

1233: PEDIATRIC EARLY WARNING SYSTEM DEVELOPMENT AND IMPLEMENTATION IN A PEDIATRIC INTENSIVE CARE UNIT

Critical Care Medicine ◽

10.1097/01.ccm.0000509907.96416.5f ◽

2016 ◽

Vol 44 (12) ◽

pp. 384-384

Author(s):

Kristen Nelson McMillan ◽

Kristen Brown ◽

Charlotte Woods-Hill ◽

Susan Floyd ◽

Bonnie Staso ◽

...

Keyword(s):

Intensive Care Unit ◽

Intensive Care ◽

Pediatric Intensive Care Unit ◽

Early Warning ◽

Early Warning System ◽

System Development ◽

Warning System ◽

Pediatric Intensive Care

Download Full-text

Abstract WP5: Outcomes Are Not Different Between Patients With Intermediate and High Dwi-aspects After Stent-retriever Thrombectomy

Stroke ◽

10.1161/str.47.suppl_1.wp5 ◽

2016 ◽

Vol 47 (suppl_1) ◽

Author(s):

Woong Yoon ◽

Seul Kee Kim ◽

Tae Wook Heo ◽

Byung Hyun Baek ◽

Jaechan Park

Keyword(s):

Functional Outcome ◽

Time Window ◽

Multivariate Logistic Regression Analysis ◽

Area Under The Curve ◽

Stent Retriever ◽

Operating Characteristics ◽

Anterior Circulation ◽

Good Outcome ◽

Characteristics Analysis ◽

The Impact

Introduction: Few studies have investigated the association between pretreatment DWI-ASPECTS and functional outcome after stent-retriever thrombectomy in patients with acute anterior circulation stroke. Hypothesis: Patients with acute stroke and DWI-ASPECTS <7 might have a similar chance of a good outcome compared to those with a higher DWI-ASPECTS, if they are treated with a stent-retriever thrombectomy in a short time window. However, this hypothesis has not been tested. Thus, this study aimed to investigate the impact of DWI-ASPECTS on functional outcome in patients with acute anterior circulation stroke who received a stent-retriever thrombectomy. Methods: We retrospectively analyzed the clinical and DWI data from 171 patients with acute anterior circulation stroke who were treated with stent-retriever thrombectomy within 6 hours of symptom onset. The DWI-ASPECTS was assessed by two readers. A good outcome was defined as a modified Rankin Scale score of 0-2 at 3 months. Results: The median DWI-ASPECTS was 7 (interquartile range, 6-8). Receiver operating characteristics analysis revealed an ASPECTS ≥ 7 was the optimal cut-off to predict a good outcome at 3 months (area under the curve=0.57; sensitivity, 75.3%; specificity, 34.4%). The rates of good outcome, symptomatic hemorrhage, and mortality were not different between high DWI-ASPECTS (scores of 7-10) and intermediate (scores of 4-6) groups. In patients with an intermediate DWI-ASPECTS, good outcome was achieved in 46.5% (20/43) of patients with successful revascularization (modified TICI 2b or 3), whereas no patients without successful revascularization had a good outcome ( P =0.016). In multivariate logistic regression analysis, independent predictors of good outcome were age and successful revascularization. Conclusions: Our study suggested that treatment outcomes were not different between patients with a high DWI-ASPECTS and those with an intermediate DWI-ASPECTS who underwent stent-retriever thrombectomy for acute anterior circulation stroke. Thus, patients with an intermediate DWI-ASPECTS otherwise eligible for endovascular therapy should not be excluded for stent-retriever thrombectomy or stroke trials.

Download Full-text

VIRTUAL SCREENING OF BETA-SECRETASE 1 (BACE1) INHIBITORS IN THE INDONESIAN HERBAL DATABASE AS USING AUTODOCK AND AUTODOCK VINA

Asian Journal of Pharmaceutical and Clinical Research ◽

10.22159/ajpcr.2017.v10s5.23119 ◽

2017 ◽

Vol 10 (17) ◽

pp. 148

Author(s):

Asti Anna Tanisa ◽

Rezi Riadhi

Keyword(s):

Binding Energy ◽

Virtual Screening ◽

Cellular Response ◽

Senile Plaque ◽

Area Under The Curve ◽

Neuronal System ◽

Operating Characteristics ◽

Autodock Vina ◽

Beta Secretase ◽

The Brain

Objective: Alzheimer’s is a neurodegenerative disease caused by the accumulation of senile plaque in the brain that affects neuronal system leading to a less sensitive cellular response from neurons. Previous research has found that beta-secretase 1 (BACE1) plays an important role in the senile plaque formation, become a target in Alzheimer’s medication.Methods: In this study, virtual screening of BACE1 inhibitors on the Indonesian Herbal Database was done using AutoDock and AutoDock Vina. The screening was validated using the directory of useful decoys: Enhanced database. Parameters for validation process of AutoDock and AutoDock Vina are enrichment factor (EF), receiver operating characteristics, and area under the curve (AUC).Results: The dimensions of grid boxes were 30×30×30 (AutoDock) and 11.25×11.25×11.25 (AutoDock Vina). The EF 1% and AUC values obtained from the AutoDock are 7.74 and 0.73, respectively, and in the AutoDock Vina are 4.6 and 0.77, respectively. Based on the virtual screening results, the top six compounds obtained using AutoDock (binding energy ranging from −7.84 kcal/mol to −8.79 kcal/mol) include: Azadiradione, cylindrin, lanosterol, sapogenin, simiarenol, and taraxerol. The top seven compounds (binding energy ranging from −8.8 kcal/mol to −9.4 kcal/mol) obtained using AutoDeck Vina include: Bryophyllin A, diosgenin, azadiradione, sojagol, beta-amyrin, epifriedelinol, and jasmolactone C.Conclusions: Only azadiradione was obtained from the virtual screening conducted using both types of software; it interacts with the active region in BACE1 at residue Trp 76 (AutoDock result) and Thr 232 (AutoDock Vina result).

Download Full-text

MicroRNAs Which Can Prognosticate Aggressiveness of Bladder Cancer

Cancers ◽

10.3390/cancers11101551 ◽

2019 ◽

Vol 11 (10) ◽

pp. 1551 ◽

Cited By ~ 3

Author(s):

Edyta Marta Borkowska ◽

Tomasz Konecki ◽

Michał Pietrusiński ◽

Maciej Borowiec ◽

Zbigniew Jabłonowski

Keyword(s):

Bladder Cancer ◽

Area Under The Curve ◽

Roc Curves ◽

Control Group ◽

Low Grade ◽

Operating Characteristics ◽

High Death Rate ◽

Biological Potential ◽

High Death ◽

Muscle Invasive

Bladder cancer (BC) is still characterized by a very high death rate in patients with this disease. One of the reasons for this is the lack of adequate markers which could help determine the biological potential of the tumor to develop into its invasive stage. It has been found that some microRNAs (miRNAs) correlate with disease progression. The purpose of this study was to identify which miRNAs can accurately predict the presence of BC and can differentiate low grade (LG) tumors from high grade (HG) tumors. The study included 55 patients with diagnosed bladder cancer and 30 persons belonging to the control group. The expression of seven selected miRNAs was estimated with the real-time PCR technique according to miR-103-5p (for the normalization of the results). Receiver operating characteristics (ROC) curves and the area under the curve (AUC) were used to evaluate the feasibility of using selected markers as biomarkers for detecting BC and discriminating non-muscle invasive BC (NMIBC) from muscle invasive BC (MIBC). For HG tumors, the relevant classifiers are miR-205-5p and miR-20a-5p, whereas miR-205-5p and miR-182-5p are for LG (AUC = 0.964 and AUC = 0.992, respectively). NMIBC patients with LG disease are characterized by significantly higher miR-130b-3p expression values compared to patients in HG tumors.

Download Full-text