Abstract:From genome‐scale experimental studies to imaging data, behavioral footprints, and longitudinal healthcare records, the convergence of big data in cancer research and the advances in Artificial Intelligence (AI) is paving the way to develop a systems view of cancer. Nevertheless, this biomedical area is largely characterized by the co‐existence of big data and small data resources, highlighting the need for a deeper investigation about the crosstalk between different levels of data granularity, including varie… Show more
“…Artificial intelligence and machine learning approaches are increasingly applied in medicine (22,23). Our results in the validation set suggest that the overall effectiveness of traditional logistic regression method in assessing the risk of atypical metastasis is not good (AUC = 0.671), relatively, the comprehensive performance of Adaboost algorithm is better (AUC = 0.736).…”
BackgroundThe prognosis of colorectal cancer with atypical metastasis is poor. However, atypical metastasis was less common and under-appreciated.MethodsIn this study we attempted to present the first machine learning models to predict the risk of atypical metastasis in colorectal cancer patients. We evaluated the differences between metastasis and non-metastasis groups, assessed factors associated with atypical metastasis using univariate and multivariate logistic regression analyses, and preliminarily developed the multiple machine learning models to predict atypical metastasis.Results168 patients were included. Prognostic Nutritional Index (PNI) [OR = 0.998; P = 0.030], Cancer antigen 19–9 (CA19-9) [OR = 1.011; P = 0.043] and MR-Distance [-mid OR = 0.289; P = 0.009] [-high OR = 0.248; P = 0.021] were shown to be independent risk factors for the atypical metastasis via multivariate analysis. Furthermore, the machine learning model based on AdaBoost algorithm (AUC: 0736) has better predictive performance comparing to Logistic Regression (AUC: 0.671) and KNeighbors Classifier (AUC: 0.618) by area under the curve (AUC) in the validation cohorts. The accuracy, sensitivity, and specificity of the model trained using the Adaboost method in the validation set are 0.786, 0.776 and 0.700, while 0.601, 0.933, 0.508 using Logistic Regression and 0.743, 0.390, 0.831 using KNeighbors Classifier.ConclusionMachine-learning approaches containing PNI, CA19-9 and MR-Distance show great potentials in atypical metastasis prediction.
“…Artificial intelligence and machine learning approaches are increasingly applied in medicine (22,23). Our results in the validation set suggest that the overall effectiveness of traditional logistic regression method in assessing the risk of atypical metastasis is not good (AUC = 0.671), relatively, the comprehensive performance of Adaboost algorithm is better (AUC = 0.736).…”
BackgroundThe prognosis of colorectal cancer with atypical metastasis is poor. However, atypical metastasis was less common and under-appreciated.MethodsIn this study we attempted to present the first machine learning models to predict the risk of atypical metastasis in colorectal cancer patients. We evaluated the differences between metastasis and non-metastasis groups, assessed factors associated with atypical metastasis using univariate and multivariate logistic regression analyses, and preliminarily developed the multiple machine learning models to predict atypical metastasis.Results168 patients were included. Prognostic Nutritional Index (PNI) [OR = 0.998; P = 0.030], Cancer antigen 19–9 (CA19-9) [OR = 1.011; P = 0.043] and MR-Distance [-mid OR = 0.289; P = 0.009] [-high OR = 0.248; P = 0.021] were shown to be independent risk factors for the atypical metastasis via multivariate analysis. Furthermore, the machine learning model based on AdaBoost algorithm (AUC: 0736) has better predictive performance comparing to Logistic Regression (AUC: 0.671) and KNeighbors Classifier (AUC: 0.618) by area under the curve (AUC) in the validation cohorts. The accuracy, sensitivity, and specificity of the model trained using the Adaboost method in the validation set are 0.786, 0.776 and 0.700, while 0.601, 0.933, 0.508 using Logistic Regression and 0.743, 0.390, 0.831 using KNeighbors Classifier.ConclusionMachine-learning approaches containing PNI, CA19-9 and MR-Distance show great potentials in atypical metastasis prediction.
“…The difference in results in the Lin et al study can be explained by their use of time series data which provided the deep learning models in their study additional data. This study did not use time series data, which is challenging to construct and may suffer from the granularity issue for different variables (Cirillo et al, 2021).…”
ICU readmissions are associated with poor outcomes for patients and poor performance of hospitals. Patients who are re-admitted have an increased risk of in-hospital deaths; hospitals with a higher readmission rate have reduced profitability, due to an increase in cost and reduced payments from Medicare and Medicaid programs. Predicting a patient's likelihood of being readmitted to the ICU can help reduce early discharges, the risk of in-hospital deaths, and help increase profitability. In this study, we built and evaluated multiple machine learning models to predict 30-day readmission rates of ICU patients in the MIMIC-III database. We used both the structured data including demographics, laboratory tests, comorbidities, and unstructured discharge summaries as the predictors and evaluated different combinations of features. The best performing model in this study Logistic Regression achieved an AUROC of 75.7%. This study shows the potential of leveraging machine learning and deep learning for predicting ICU readmissions.
“…Cancer treatment significantly improved over the last decades, mainly due to an enhanced understanding of the mechanisms leading to tumor formation and disease progression which were often accelerated by technological advancements. Current trends such as machine learning and artificial intelligence (AI) are on the horizon and show the need to facilitate the system to improve drug response prediction in patients by transferring information from cancer models [142]. If we hope to truly advance precision oncology, we need a pan-optic view on all facets of cancer biology, and we need to go beyond genomics.…”
Cancer is a multifactorial disease with increasing incidence. There are more than 100 different cancer types, defined by location, cell of origin, and genomic alterations that influence oncogenesis and therapeutic response. This heterogeneity between tumors of different patients and also the heterogeneity within the same patient’s tumor pose an enormous challenge to cancer treatment. In this review, we explore tumor heterogeneity on the longitudinal and the latitudinal axis, reviewing current and future approaches to study this heterogeneity and their potential to support oncologists in tailoring a patient’s treatment regimen. We highlight how the ideal of precision oncology is reaching far beyond the knowledge of genetic variants to inform clinical practice and discuss the technologies and strategies already available to improve our understanding and management of heterogeneity in cancer treatment. We will focus on integrating multi-omics technologies with suitable in vitro models and their proficiency in mimicking endogenous tumor heterogeneity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.