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

oncology Oncology

Machine learning analysis of breast ultrasound to classify triple negative and HER2+ breast cancer subtypes.

In Breast disease

OBJECTIVES : Early diagnosis of triple-negative (TN) and human epidermal growth factor receptor 2 positive (HER2+) breast cancer is important due to its increased risk of micrometastatic spread necessitating early treatment and for guiding targeted therapies. This study aimed to evaluate the diagnostic performance of machine learning (ML) classification of newly diagnosed breast masses into TN versus non-TN (NTN) and HER2+ versus HER2 negative (HER2-) breast cancer, using radiomic features extracted from grayscale ultrasound (US) b-mode images.

MATERIALS AND METHODS : A retrospective chart review identified 88 female patients who underwent diagnostic breast US imaging, had confirmation of invasive malignancy on pathology and receptor status determined on immunohistochemistry available. The patients were classified as TN, NTN, HER2+ or HER2- for ground-truth labelling. For image analysis, breast masses were manually segmented by a breast radiologist. Radiomic features were extracted per image and used for predictive modelling. Supervised ML classifiers included: logistic regression, k-nearest neighbour, and Naïve Bayes. Classification performance measures were calculated on an independent (unseen) test set. The area under the receiver operating characteristic curve (AUC), sensitivity (%), and specificity (%) were reported for each classifier.

RESULTS : The logistic regression classifier demonstrated the highest AUC: 0.824 (sensitivity: 81.8%, specificity: 74.2%) for the TN sub-group and 0.778 (sensitivity: 71.4%, specificity: 71.6%) for the HER2 sub-group.

CONCLUSION : ML classifiers demonstrate high diagnostic accuracy in classifying TN versus NTN and HER2+ versus HER2- breast cancers using US images. Identification of more aggressive breast cancer subtypes early in the diagnostic process could help achieve better prognoses by prioritizing clinical referral and prompting adequate early treatment.

Ferre Romuald, Elst Janne, Senthilnathan Seanthan, Lagree Andrew, Tabbarah Sami, Lu Fang-I, Sadeghi-Naini Ali, Tran William T, Curpen Belinda

2023

HER2+ breast cancer, Machine learning, triple negative breast cancer, ultrasound

General General

The role of the mass vaccination programme in combating the COVID-19 pandemic: An LSTM-based analysis of COVID-19 confirmed cases.

In Heliyon

The COVID-19 virus has impacted all facets of our lives. As a global response to this threat, vaccination programmes have been initiated and administered in numerous nations. The question remains, however, as to whether mass vaccination programmes result in a decrease in the number of confirmed COVID-19 cases. In this study, we aim to predict the future number of COVID-19 confirmed cases for the top ten countries with the highest number of vaccinations in the world. A well-known Deep Learning method for time series analysis, namely, the Long Short-Term Memory (LSTM) networks, is applied as the prediction method. Using three evaluation metrics, i.e., Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE), we found that the model built by using LSTM networks could give a good prediction of the future number and trend of COVID-19 confirmed cases in the considered countries. Two different scenarios are employed, namely: 'All Time', which includes all historical data; and 'Before Vaccination', which excludes data collected after the mass vaccination programme began. The average MAPE scores for the 'All Time' and 'Before Vaccination' scenarios are 5.977% and 10.388%, respectively. Overall, the results show that the mass vaccination programme has a positive impact on decreasing and controlling the spread of the COVID-19 disease in those countries, as evidenced by decreasing future trends after the programme was implemented.

Hansun Seng, Charles Vincent, Gherman Tatiana

2023-Mar

COVID-19, Confirmed cases, Deep learning, LSTM, Mass vaccination

General General

Predicting Chemical End-of-Life Scenarios Using Structure-Based Classification Models.

In ACS sustainable chemistry & engineering

Analyzing chemicals and their effects on the environment from a life cycle viewpoint can produce a thorough analysis that takes end-of-life (EoL) activities into account. Chemical risk assessment, predicting environmental discharges, and finding EoL paths and exposure scenarios all depend on chemical flow data availability. However, it is challenging to gain access to such data and systematically determine EoL activities and potential chemical exposure scenarios. As a result, this work creates quantitative structure-transfer relationship (QSTR) models for aiding environmental managment decision-making based on chemical structure-based machine learning (ML) models to predict potential industrial EoL activities, chemical flow allocation, environmental releases, and exposure routes. Further multi-label classification methods may improve the predictability of QSTR models according to the ML experiment tracking. The developed QSTR models will assist stakeholders in predicting and comprehending potential EoL management activities and recycling loops, enabling environmental decision-making and EoL exposure assessment for new or existing chemicals in the global marketplace.

Hernandez-Betancur Jose D, Ruiz-Mercado Gerardo J, Martin Mariano

2023-Mar-06

General General

Utility of a machine-guided tool for assessing risk behaviour associated with contracting HIV in three sites in South Africa.

In Informatics in medicine unlocked

INTRODUCTION : Digital data collection and the associated mobile health technologies have allowed for the recent exploration of artificial intelligence as a tool for combatting the HIV epidemic. Machine learning has been found to be useful both in HIV risk prediction and as a decision support tool for guiding pre-exposure prophylaxis (PrEP) treatment. This paper reports data from two sequential studies evaluating the viability of using machine learning to predict the susceptibility of adults to HIV infection using responses from a digital survey deployed in a high burden, low-resource setting.

METHODS : 1036 and 593 participants were recruited across two trials. The first trial was a cross-sectional study in one location and the second trial was a cohort study across three trial sites. The data from the studies were merged, partitioned using standard techniques, and then used to train and evaluate multiple different machine learning models and select and evaluate a final model. Variable importance estimates were calculated using the PIMP and SHAP methodologies.

RESULTS : Characteristics associated with HIV were consistent across both studies. Overall, HIV positive patients had a higher median age (34 [IQR: 29-39] vs 26 [IQR 22-33], p < 0.001), and were more likely to be female (155/703 [22%] vs 107/927 [12%], p < 0.001). HIV positive participants also had more commonly gone a year or more since their last HIV test (183/262 [70%] vs 540/1368 [39%], p < 0.001) and were less likely to report consistent condom usage (113/262 [43%] vs 758/1368 [55%], p < 0.001). Patients who reported TB symptoms were more likely to be HIV positive. The trained models had accuracy values (AUROCs) ranging from 78.5% to 82.8%. A boosted tree model performed best with a sensitivity of 84% (95% CI 72-92), specificity of 71% (95% CI 67-76), and a negative predictive value of 95% (95% CI 93-96) in a hold-out dataset. Age, duration since last HIV test, and number of male sexual partners were consistently three of the four most important variables across both variable importance estimates.

CONCLUSIONS : This study has highlighted the synergies present between mobile health and machine learning in HIV. It has been demonstrated that a viable ML model can be built using digital survey data from an low-middle income setting with potential utility in directing health resources.

Majam M, Segal B, Fieggen J, Smith Eli, Hermans L, Singh L, Phatsoane M, Arora L, Lalla-Edward S T

2023

HIV, HIV risk Assessment, ML, Machine guided tool, Machine learning, PrEP, Predictive analysis, Supervised learning

oncology Oncology

A predictive model for personalization of nanotechnology-based phototherapy in cancer treatment.

In Frontiers in oncology

A major challenge in radiation oncology is the prediction and optimization of clinical responses in a personalized manner. Recently, nanotechnology-based cancer treatments are being combined with photodynamic therapy (PDT) and photothermal therapy (PTT). Predictive models based on machine learning techniques can be used to optimize the clinical setup configuration, including such parameters as laser radiation intensity, treatment duration, and nanoparticle features. In this article we demonstrate a methodology that can be used to identify the optimal treatment parameters for PDT and PTT by collecting data from in vitro cytotoxicity assay of PDT/PTT-induced cell death using a single nanocomplex. We construct three machine learning prediction models, employing regression, interpolation, and low- degree analytical function fitting, to predict the laser radiation intensity and duration settings that maximize the treatment efficiency. To examine the accuracy of these prediction models, we construct a dedicated dataset for PDT, PTT, and a combined treatment; this dataset is based on cell death measurements after light radiation treatment and is divided into training and test sets. The preliminary results show that the performance of all three models is sufficient, with death rate errors of 0.09, 0.15, and 0.12 for the regression, interpolation, and analytical function fitting approaches, respectively. Nevertheless, due to its simple form, the analytical function method has an advantage in clinical application and can be used for further analysis of the sensitivity of performance to the treatment parameters. Overall, the results of this study form a baseline for a future personalized prediction model based on machine learning in the domain of combined nanotechnology- and phototherapy-based cancer treatment.

Varon Eli, Blumrosen Gaddi, Shefi Orit

2022

PDT (photodynamic therapy), PTT (photothermal therapy), biomedical model development, cancer, personalized medicine, prediction medicine, radiation

Cardiology Cardiology

Association between serum folate levels and blood eosinophil counts in American adults with asthma: Results from NHANES 2011-2018.

In Frontiers in immunology ; h5-index 100.0

BACKGROUND : To date, many researches have investigated the correlation of folate and asthma occurrence. Nevertheless, few studies have discussed whether folate status is correlated with dis-ease severity, control or progression of asthma. So, we explored the correlation of serum folate and blood eosinophil counts in asthmatic adults to gain the role of folate in the control, progression, and treatment of asthma.

METHODS : Data were obtained from the 2011-2018 NHANES, in which serum folate, blood eosinophils, and other covariates were measured among 2332 asthmatic adults. The regression model, XGBoost algorithm model, and generalized linear model were used to explore the potential correlation. Moreover, we conducted stratified analyses to determine certain populations.

RESULTS : Among three models, the multivariate regression analysis demonstrated serum folate levels were negatively correlated with blood eosinophil counts among asthmatic adults with statistical significance. And we observed that blood eosinophil counts decreased by 0.20 (-0.34, -0.06)/uL for each additional unit of serum folate (nmol/L) after adjusting for confounders. Moreover, we used the XGBoost Algorithm model to identify the relative significance of chosen variables correlated with blood eosinophil counts and observed the linear relationship between serum folate levels and blood eosinophil counts by constructing the generalized linear model.

CONCLUSIONS : Our study indicated that serum folate levels were inversely associated with blood eosinophil counts in asthmatic adult populations of America, which indicated serum folate might be correlated with the immune status of asthmatic adults in some way. We suggested that serum folate might affect the control, development, and treatment of asthma. Finally, we hope more people will recognize the role of folate in asthma.

Wen Jun, Wang Changfen, Giri Mohan, Guo Shuliang

2023

asthma, eosinophil, folate, machine learning, national health and nutrition examination survey