High-accuracy detection of malaria mosquito habitats using drone-based multispectral imagery and Artificial Intelligence (AI) algorithms in an agro-village peri-urban pastureland intervention site (Akonyibedo) in Unyama SubCounty, Gulu District, Northern Uganda

Drilling a high-pressure, high-temperature (HPHT) well involves many difficulties and challenges. One of the greatest difficulties is the loss of circulation. Almost 40% of the drilling cost is attributed to the drilling fluid, so the loss of the fluid considerably increases the total drilling cost. There are several approaches to avoid loss of return; one of these approaches is preventing the occurrence of the losses by identifying the lost circulation zones. Most of these approaches are difficult to apply due to some constraints in the field. The purpose of this work is to apply three artificial intelligence (AI) techniques, namely, functional networks (FN), artificial neural networks (ANN), and fuzzy logic (FL), to identify the lost circulation zones. Real-time surface drilling parameters of three wells were obtained using real-time drilling sensors. Well A was utilized for training and testing the three developed AI models, whereas Well B and Well C were utilized to validate them. High accuracy was achieved by the three AI models based on the root mean square error (RMSE), confusion matrix, and correlation coefficient (R). All the AI models identified the lost circulation zones in Well A with high accuracy where the R is more than 0.98 and RMSE is less than 0.09. ANN is the most accurate model with R=0.99 and RMSE=0.05. An ANN was able to predict the lost circulation zones in the unseen Well B and Well C with R=0.946 and RMSE=0.165 and R=0.952 and RMSE=0.155, respectively.

Download Full-text

Artificial Intelligence Analysis of Gene Expression Predicted the Overall Survival of Mantle Cell Lymphoma and a Large Pan-Cancer Series

Healthcare ◽

10.3390/healthcare10010155 ◽

2022 ◽

Vol 10 (1) ◽

pp. 155

Author(s):

Joaquim Carreras ◽

Naoya Nakamura ◽

Rifat Hamoudi

Keyword(s):

Artificial Intelligence ◽

Overall Survival ◽

B Cell ◽

Mantle Cell Lymphoma ◽

Cell Lymphoma ◽

High Accuracy ◽

Gene Set Enrichment Analysis ◽

Intelligence Analysis ◽

Mantle Cell ◽

Pan Cancer

Mantle cell lymphoma (MCL) is a subtype of mature B-cell non-Hodgkin lymphoma characterized by a poor prognosis. First, we analyzed a series of 123 cases (GSE93291). An algorithm using multilayer perceptron artificial neural network, radial basis function, gene set enrichment analysis (GSEA), and conventional statistics, correlated 20,862 genes with 28 MCL prognostic genes for dimensionality reduction, to predict the patients’ overall survival and highlight new markers. As a result, 58 genes predicted survival with high accuracy (area under the curve = 0.9). Further reduction identified 10 genes: KIF18A, YBX3, PEMT, GCNA, and POGLUT3 that associated with a poor survival; and SELENOP, AMOTL2, IGFBP7, KCTD12, and ADGRG2 with a favorable survival. Correlation with the proliferation index (Ki67) was also made. Interestingly, these genes, which were related to cell cycle, apoptosis, and metabolism, also predicted the survival of diffuse large B-cell lymphoma (GSE10846, n = 414), and a pan-cancer series of The Cancer Genome Atlas (TCGA, n = 7289), which included the most relevant cancers (lung, breast, colorectal, prostate, stomach, liver, etcetera). Secondly, survival was predicted using 10 oncology panels (transcriptome, cancer progression and pathways, metabolic pathways, immuno-oncology, and host response), and TYMS was highlighted. Finally, using machine learning, C5 tree and Bayesian network had the highest accuracy for prediction and correlation with the LLMPP MCL35 proliferation assay and RGS1 was made. In conclusion, artificial intelligence analysis predicted the overall survival of MCL with high accuracy, and highlighted genes that predicted the survival of a large pan-cancer series.

Download Full-text

384 High Accuracy and Effectiveness With Deep Neural Networks and Artificial Intelligence in Detection of Early Esophageal Neoplasia in Barrett's Esophagus

The American Journal of Gastroenterology ◽

10.14309/01.ajg.0000591068.35597.2b ◽

2019 ◽

Vol 114 (1) ◽

pp. S224-S225

Author(s):

Rintaro Hashimoto ◽

Nabil El Hage Chehade ◽

Kenneth J. Chang ◽

Tyler Dao ◽

Andrew Ninh ◽

...

Keyword(s):

Artificial Intelligence ◽

Neural Networks ◽

Barrett’S Esophagus ◽

Barrett's Esophagus ◽

Deep Neural Networks ◽

High Accuracy ◽

Esophageal Neoplasia

Download Full-text

Influence of Climatic Factors on Malaria Epidemic in Gulu District, Northern Uganda: A 10-Year Retrospective Study

Malaria Research and Treatment ◽

10.1155/2018/5482136 ◽

2018 ◽

Vol 2018 ◽

pp. 1-8 ◽

Cited By ~ 2

Author(s):

Ouma Simple ◽

Arnold Mindra ◽

Gerald Obai ◽

Emilio Ovuga ◽

Emmanuel Igwaro Odongo-Aginya

Keyword(s):

Retrospective Study ◽

Relative Humidity ◽

Malaria Control ◽

Malaria Infection ◽

Climatic Factors ◽

Indoor Residual Spraying ◽

Sub Saharan Africa ◽

Maximum Temperature ◽

Northern Uganda ◽

Gulu District

Background. Globally, 15 countries, mainly in Sub-Saharan Africa, account for 80% of malaria cases and 78% of malaria related deaths. In Uganda, malaria is endemic and the mortality and morbidity due to malaria cause significant negative impact on the economy. In Gulu district, malaria is the leading killer disease among children <5 years. In 2015, the high intensity of malaria infection in Northern Uganda revealed a possible link between malaria and rainfall. However, available information on the influence of climatic factors on malaria are scarce, conflicting, and highly contextualized and therefore one cannot reference such information to malaria control policy in Northern Uganda, thus the need for this study. Methods and Results. During the 10 year’s retrospective study period a total of 2,304,537 people suffered from malaria in Gulu district. Malaria infection was generally stable with biannual peaks during the months of June-July and September-October but showed a declining trend after introduction of indoor residual spraying. Analysis of the departure of mean monthly malaria cases from the long-term mean monthly malaria cases revealed biannual seasonal outbreaks before and during the first year of introduction of indoor residual spraying. However, there were two major malaria epidemics in 2015 following discontinuation of indoor residual spraying in the late 2014. Children <5 years of age were disproportionally affected by malaria and accounted for 47.6% of the total malaria cases. Both rainfall (P=0.04) and relative humidity (P=0.003) had significant positive correlations with malaria. Meanwhile, maximum temperature had significant negative correlation with malaria (P=0.02) but minimum temperature had no correlation with malaria (P=0.29). Conclusion. Malaria in Gulu disproportionately affects children under 5 years and shows seasonality with a generally stable trend influenced by rainfall and relative humidity. However, indoor residual spraying is a very promising method to achieve a sustained malaria control in this population.

Download Full-text

Prevention of spina bifida: folic acid intake during pregnancy in Gulu district, northern Uganda

Pan African Medical Journal ◽

10.11604/pamj.2015.20.90.5338 ◽

2015 ◽

Vol 20 ◽

Cited By ~ 3

Author(s):

Femke Bannink ◽

Rita Larok ◽

Peter Kirabira ◽

Lieven Bauwens ◽

Geert van Hove

Keyword(s):

Folic Acid ◽

Spina Bifida ◽

Northern Uganda ◽

Folic Acid Intake ◽

Acid Intake ◽

Gulu District

Download Full-text

Pattern Recognition using a Neural Network on a Microcontroller with I2C Ultrasonic Sensors

Annals of Emerging Technologies in Computing ◽

10.33166/aetic.2019.01.002 ◽

2019 ◽

Vol 3 (1) ◽

pp. 9-19 ◽

Cited By ~ 1

Author(s):

Fazal Noor

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Pattern Recognition ◽

Integrated Circuit ◽

High Accuracy ◽

Ultrasonic Sensors ◽

Motion Patterns ◽

The Neural Network ◽

Proposed Model ◽

Neural Network Algorithm

Ultrasonic sensors have been used in a variety of applications to measure ranges to objects. Hand gestures via ultrasonic sensors form unique motion patterns for controls. In this research, patterns formed by placing a set of objects in a grid of cells are used for control purposes. A neural network algorithm is implemented on a microcontroller which takes in range signals as inputs read from ultrasonic sensors and classifies them in one of four classes. The neural network is then trained to classify patterns based on objects’ locations in real-time. The testing of the neural network for pattern recognition is performed on a testbed consisting of Inter-Integrated Circuit (I2C) ultrasonic sensors and a microcontroller. The performance of the proposed model is presented and it is observed the model is highly scalable, accurate, robust and reliable for applications requiring high accuracy such as in robotics and artificial intelligence.

Download Full-text

MIXTURE of human expertise and deep learning - Developing an explainable model for predicting pathological diagnosis and survival in patients with interstitial lung disease

10.1101/2021.07.21.21260920 ◽

2021 ◽

Author(s):

Wataru Uegami ◽

Andrey Bychkov ◽

Mutsumi Ozasa ◽

Kazuki Uehara ◽

Kensuke Kataoka ◽

...

Keyword(s):

Artificial Intelligence ◽

Deep Learning ◽

Interstitial Pneumonia ◽

Proportional Hazards Model ◽

Histopathological Examination ◽

Usual Interstitial Pneumonia ◽

High Accuracy ◽

Cox Proportional Hazards ◽

Cox Proportional Hazards Model ◽

Learning Models

Interstitial pneumonia is a heterogeneous disease with a progressive course and poor prognosis, at times even worse than those in the main cancer types. Histopathological examination is crucial for its diagnosis and estimation of prognosis. However, the evaluation strongly depends on the experience of pathologists, and the reproducibility of diagnosis is low. Herein, we propose MIXTURE (huMan-In-the-loop eXplainable artificial intelligence Through the Use of REcurrent training), a method to develop deep learning models for extracting pathologically significant findings based on an expert pathologist's perspective with a small annotation effort. The procedure of MIXTURE consists of three steps as follows. First, we created feature extractors for tiles from whole slide images using self-supervised learning. The similar looking tiles were clustered based on the output features and then pathologists integrated the pathologically synonymous clusters. Using the integrated clusters as labeled data, deep learning models to classify the tiles into pathological findings were created by transfer-learning the feature extractors. We developed three models for different magnifications. Using these extracted findings, our model was able to predict the diagnosis of usual interstitial pneumonia, a finding suggestive of progressive disease, with high accuracy (AUC 0.90). This high accuracy could not be achieved without the integration of findings by pathologists. The patients predicted as UIP had significantly poorer prognosis (five-year overall survival [OS]: 55.4% than those predicted as non-UIP (OS: 95.2%). The Cox proportional hazards model for each microscopic finding and prognosis pointed out dense fibrosis, fibroblastic foci, elastosis, and lymphocyte aggregation as independent risk factors. We suggest that MIXTURE may serve as a model approach to different diseases evaluated by medical imaging, including pathology and radiology, and be the prototype for artificial intelligence that can collaborate with humans.

Download Full-text

Factors associated with use of long-acting reversible contraception among female sex workers operating in Gulu district, Northern Uganda – a cross-sectional study

10.21203/rs.3.rs-275872/v1 ◽

2021 ◽

Author(s):

Simple Ouma ◽

Nazarius Mbona Tumwesigye ◽

Catherine Abbo ◽

Rawlance Ndejjo

Keyword(s):

Sex Work ◽

Unintended Pregnancy ◽

Sex Workers ◽

Female Sex Workers ◽

Northern Uganda ◽

Sectional Study ◽

Factors Associated ◽

History Of ◽

Gulu District ◽

Long Acting

Abstract Background: Long-acting reversible contraception (LARC) are the most effective and reliable contraceptives for female sex workers (FSWs) and require periodic users’ involvement only at the time of application or re-application. However, information on LARC use among FSWs in Uganda is scarce. To fill this gap, we determined the prevalence of LARC use among FSWs and examined factors associated with LARC use among FSWs operating in Gulu district, Northern Uganda.Methods: Across-sectional study was conducted among 300 FSWs aged 18 years and above and operating in Gulu district. Semi-structured questionnaires were used to measure factors associated with the use of LARC: intrauterine device (IUD), Implants, and injectables. Data analyses were conducted using STATA 14.0 and restricted to 280 non-gravid adult FSWs aged 18-49 years who were not on permanent contraception method. To examine factors associated with LARC use, prevalence ratios (PR) with robust standard errors were computed using Poisson regression.Results: Among the participants, the mean age (SD, range) was 26.5 (5.9, 18 - 45) years, 53.2% never married, 66.1% reported consistent condom use independent of LARC, 58.9% had unintended pregnancy during a lifetime, 48.6% had at least one unintended pregnancy during sex work, and 37.4% had at least one induced abortion. The prevalence of LARC use was 58.6%; the majority were using Implants (48.2%), followed by injectables (42.7%), and IUDs (9.1%). Independent factors associated with LARC use included: longer duration of sex work [≥ two years] (adjusted PR=1.44, 95% CI: 1.03-2.02), higher parity [≥ two] (adjusted PR=1.13, 95% CI: 1.02-1.26), history of unintended pregnancy during sex work (adjusted PR=1.24 CI: 1.01-1.51), and being a brothel/lodge-based FSWs (adjusted PR=1.28, 95% CI: 1.01-1.63).Conclusions: There is a big gap in LARC use with only 58.6% of FSWs using LARC. LARC use was associated with longer duration of sex work, higher parity, history of sex work-related unintended pregnancy, and being a brothel/lodge-based FSW. Therefore, interventions to improve LARC use should intensively target the newly recruited FSWs, FSWs with low parity, and FSWs not based in brothels or lodges.

Download Full-text

Computational analysis of transition temperatures (Tts) of proteins fused to elastin-like polypeptide (ELP): deep fake evaluation of proteins, linkers, and trailers features

10.1101/2021.12.29.474407 ◽

2021 ◽

Author(s):

Mohammad Davoud Ghafari ◽

Iraj Rasooli ◽

Khosro Khajeh ◽

Bahareh Dabirmanesh ◽

Mohammadreza Ghafari ◽

...

Keyword(s):

Artificial Intelligence ◽

Phase Transition ◽

Transition Temperature ◽

Computational Analysis ◽

Large Data ◽

High Accuracy ◽

Sequence Length ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Protein Feature

The phase transition temperature (Tt) prediction of the Elastin-like polypeptides (ELPs) is not trivial because it is related to complex sets of variables such as composition, sequence length, hydrophobic characterization, hydrophilic characterization, the sequence order in the fused proteins, linkers and trailer constructs. In this paper, two unique quantitative models are presented for the prediction of the Tt of a family of ELPs that could be fused to different proteins, linkers, and trailers. The lack of need to use multiple software, peptide information, such as PDB file, as well as knowing the second and third structures of proteins are the advantages of this model besides its high accuracy and speed. One of our models could predict the Tt values of the fused ELPs by entering the protein, linker, and trailer features with R2=99%. Also, another model is able to predict the Tt value by entering the fused protein feature with R2=96%. For more reliability, our method is enriched by Artificial Intelligence (AI) to generate similar proteins. In this regard, Generative Adversarial Network (GAN) is our AI method to create fake proteins and similar values. The experimental results show that our strategy for prediction of Tt is reliable in large data.

Download Full-text