Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

CBCovid19EC: A dataset complete blood count and PCR test for COVID-19 detection in Ecuadorian population.

In Data in brief

In this work, we present the complete blood count data and PCR test results of a population of Ecuadorians from different provinces, primarily residing in the Andean region, especially in Quito. PCR was the standard test to detect Covid-19 during the pandemic since 2020. The data were obtained between March 1st and August 12th, 2021. Segurilab and Previne Salud laboratories performed the tests. The dataset contains about 400 clinical cases. Each patient agreed to participate in the study by sharing the results of their PCR (reverse transcription polymerase chain reaction) tests and CBC (complete blood count). CBC test measured several components and features of the blood, including red blood cells, white blood cells, hemoglobin, hematocrit, and platelets. The shared data are intended to provide researchers with input to analyze various events associated with the diagnosis of Covid-19 linked to potential diseases identified in the components measured in the CBC test. These data are helpful for pattern analysis of blood components in modeling prediction and clustering problems. The components measured in the complete blood count and CRP together can be helpful for the analysis of different medical conditions using machine learning algorithms.

Ordoñez-Avila R, Parraga-Alava J, Hormaza J Meza, Vaca-Cárdenas L, Portmann E, Terán L, Dorn M

2023-Apr

Ecuador, Hematological data, Machine learning, SARS-Cov-2

General General

Image dataset of urine test results on petri dishes for deep learning classification.

In Data in brief

Recent advancements in image analysis and interpretation technologies using computer vision techniques have shown potential for novel applications in clinical microbiology laboratories to support task automation aiming for faster and more reliable diagnostics. Deep learning models can be a valuable tool in the screening process, helping technicians spend less time classifying no-growth results and quickly separating the categories of tests that deserve further analysis. In this context, creating datasets with correctly classified images is fundamental for developing and improving such models. Therefore, a dataset of urine test Petri dishes images was collected following a standardized process, with controlled conditions of positioning and lighting. Image acquisition was conducted by applying a hardware chamber equipped with a led lightning source and a smartphone camera with 12 MP resolution. A software application was developed to support image classification and handling. Experienced microbiologists classified the images according to the positive, negative, and uncertain test results. The resulting dataset contains a total of 1500 images and can support the development of deep learning algorithms to classify urine exams according to their microbial growth.

da Silva Gabriel Rodrigues, Rosmaninho Igor Batista, Zancul Eduardo, de Oliveira Vanessa Rita, Francisco Gabriela Rodrigues, Dos Santos Nathamy Fernanda, de Mello Macêdo Karin, da Silva Amauri José, de Lima Érika Knabben, Lemo Mara Elisa Borsato, Maldonado Alessandra, Moura Maria Emilia G, da Silva Flávia Helena, Guimarães Gustavo Stuani

2023-Apr

Computational Vision, Image Classification, Petri Dish, Urine Test Classification

General General

Using machine learning prediction models for quality control: a case study from the automotive industry.

In Computational management science

This paper studies a prediction problem using time series data and machine learning algorithms. The case study is related to the quality control of bumper beams in the automotive industry. These parts are milled during the production process, and the locations of the milled holes are subject to strict tolerance limits. Machine learning models are used to predict the location of milled holes in the next beam. By doing so, tolerance violations are detected at an early stage, and the production flow can be improved. A standard neural network, a long short term memory network (LSTM), and random forest algorithms are implemented and trained with historical data, including a time series of previous product measurements. Experiments indicate that all models have similar predictive capabilities with a slight dominance for the LSTM and random forest. The results show that some holes can be predicted with good quality, and the predictions can be used to improve the quality control process. However, other holes show poor results and support the claim that real data problems are challenged by inappropriate information or a lack of relevant information.

Msakni Mohamed Kais, Risan Anders, Schütz Peter

2023

Manufacturing, Neural network, Quality control, Random forest

Ophthalmology Ophthalmology

Latest Trends in Retinopathy of Prematurity: Research on Risk Factors, Diagnostic Methods and Therapies.

In International journal of general medicine

Retinopathy of prematurity (ROP) is a vasoproliferative disorder with an imminent risk of blindness, in cases where early diagnosis and treatment are not performed. The doctors' constant motivation to give these fragile beings a chance at life with optimal visual acuity has never stopped, since Terry first described this condition. Thus, throughout time, several specific advancements have been made in the management of ROP. Apart from the most known risk factors, this narrative review brings to light the latest research about new potential risk factors, such as: proteinuria, insulin-like growth factor 1 (IGF-1) and blood transfusions. Digital imaging has revolutionized the management of retinal pathologies, and it is more and more used in identifying and staging ROP, particularly in the disadvantaged regions by the means of telescreening. Moreover, optical coherence tomography (OCT) and automated diagnostic tools based on deep learning offer new perspectives on the ROP diagnosis. The new therapeutical trend based on the use of anti-VEGF agents is increasingly used in the treatment of ROP patients, and recent research sustains the theory according to which these agents do not interfere with the neurodevelopment of premature babies.

Bujoreanu Bezman Laura, Tiutiuca Carmen, Totolici Geanina, Carneciu Nicoleta, Bujoreanu Florin Ciprian, Ciortea Diana Andreea, Niculet Elena, Fulga Ana, Alexandru Anamaria Madalina, Stan Daniela Jicman, Nechita Aurel

2023

anti-VEGF, artificial intelligence, optical coherence tomography, retinopathy of prematurity, risk factors, telescreening

Radiology Radiology

Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency setting.

In European journal of radiology open

RATIONALE AND OBJECTIVES : Triage and diagnostic deep learning-based support solutions have started to take hold in everyday emergency radiology practice with the hope of alleviating workflows. Although previous works had proven that artificial intelligence (AI) may increase radiologist and/or emergency physician reading performances, they were restricted to finding, bodypart and/or age subgroups, without evaluating a routine emergency workflow composed of chest and musculoskeletal adult and pediatric cases. We aimed at evaluating a multiple musculoskeletal and chest radiographic findings deep learning-based commercial solution on an adult and pediatric emergency workflow, focusing on discrepancies between emergency and radiology physicians.

MATERIAL AND METHODS : This retrospective, monocentric and observational study included 1772 patients who underwent an emergency radiograph between July and October 2020, excluding spine, skull and plain abdomen procedures. Emergency and radiology reports, obtained without AI as part of the clinical workflow, were collected and discordant cases were reviewed to obtain the radiology reference standard. Case-level AI outputs and emergency reports were compared to the reference standard. DeLong and Wald tests were used to compare ROC-AUC and Sensitivity/Specificity, respectively.

RESULTS : Results showed an overall AI ROC-AUC of 0.954 with no difference across age or body part subgroups. Real-life emergency physicians' sensitivity was 93.7 %, not significantly different to the AI model (P = 0.105), however in 172/1772 (9.7 %) cases misdiagnosed by emergency physicians. In this subset, AI accuracy was 90.1 %.

CONCLUSION : This study highlighted that multiple findings AI solution for emergency radiographs is efficient and complementary to emergency physicians, and could help reduce misdiagnosis in the absence of immediate radiological expertize.

Parpaleix Alexandre, Parsy Clémence, Cordari Marina, Mejdoubi Mehdi

2023

Add-on, Chest, Deep learning, Emergency, Musculoskeletal, Xray

General General

Chemical rules for optimization of chemical mutagenicity via matched molecular pairs analysis and machine learning methods.

In Journal of cheminformatics

Chemical mutagenicity is a serious issue that needs to be addressed in early drug discovery. Over a long period of time, medicinal chemists have manually summarized a series of empirical rules for the optimization of chemical mutagenicity. However, given the rising amount of data, it is getting more difficult for medicinal chemists to identify more comprehensive chemical rules behind the biochemical data. Herein, we integrated a large Ames mutagenicity data set with 8576 compounds to derive mutagenicity transformation rules for reversing Ames mutagenicity via matched molecular pairs analysis. A well-trained consensus model with a reasonable applicability domain was constructed, which showed favorable performance in the external validation set with an accuracy of 0.815. The model was used to assess the generalizability and validity of these mutagenicity transformation rules. The results demonstrated that these rules were of great value and could provide inspiration for the structural modifications of compounds with potential mutagenic effects. We also found that the local chemical environment of the attachment points of rules was critical for successful transformation. To facilitate the use of these mutagenicity transformation rules, we integrated them into ADMETopt2 ( http://lmmd.ecust.edu.cn/admetsar2/admetopt2/ ), a free web server for optimization of chemical ADMET properties. The above-mentioned approach would be extended to the optimization of other toxicity endpoints.

Lou Chaofeng, Yang Hongbin, Deng Hua, Huang Mengting, Li Weihua, Liu Guixia, Lee Philip W, Tang Yun

2023-Mar-20

Consensus model, Lead optimization, Machine learning, Matched molecular pairs analysis, Mutagenicity optimization