RESUMEN
Despite large investment cancer continues to be a major source of mortality and morbidity throughout the world. Traditional methods of detection and diagnosis such as biopsy and imaging, tend to be expensive and have risks of complications. As data becomes more abundant and machine learning continues advancing, it is natural to ask how they can help solve some of these problems. In this paper we show that using a person's personal health data it is possible to predict their risk for a wide variety of cancers. We dub this process a "statistical biopsy." Specifically, we train two neural networks, one predicting risk for 16 different cancer types in females and the other predicting risk for 15 different cancer types in males. The networks were trained as binary classifiers identifying individuals that were diagnosed with the different cancer types within 5 years of joining the PLOC trial. However, rather than use the binary output of the classifiers we show that the continuous output can instead be used as a cancer risk allowing a holistic look at an individual's cancer risks. We tested our multi-cancer model on the UK Biobank dataset showing that for most cancers the predictions generalized well and that looking at multiple cancer risks at once from personal health data is a possibility. While the statistical biopsy will not be able to replace traditional biopsies for diagnosing cancers, we hope there can be a shift of paradigm in how statistical models are used in cancer detection moving to something more powerful and more personalized than general population screening guidelines.
RESUMEN
INTRODUCTION: Working memory is a critical cognitive ability that affects our daily functioning and relates to many cognitive processes and clinical conditions. Episodic memory is vital because it enables individuals to form and maintain their self-identities. Our study analyzes the extent to which whole-brain functional connectivity observed during completion of an N-back memory task, a common measure of working memory, can predict both working memory and episodic memory. METHODS: We used connectome-based predictive models (CPMs) to predict 502 Human Connectome Project (HCP) participants' in-scanner 2-back memory test scores and out-of-scanner working memory test (List Sorting) and episodic memory test (Picture Sequence and Penn Word) scores based on functional magnetic resonance imaging (fMRI) data collected both during rest and N-back task performance. We also analyzed the functional brain connections that contributed to prediction for each of these models. RESULTS: Functional connectivity observed during N-back task performance predicted out-of-scanner List Sorting scores and to a lesser extent out-of-scanner Picture Sequence scores, but did not predict out-of-scanner Penn Word scores. Additionally, the functional connections predicting 2-back scores overlapped to a greater degree with those predicting List Sorting scores than with those predicting Picture Sequence or Penn Word scores. Functional connections with the insula, including connections between insular and parietal regions, predicted scores across the 2-back, List Sorting, and Picture Sequence tasks. CONCLUSIONS: Our findings validate functional connectivity observed during the N-back task as a measure of working memory, which generalizes to predict episodic memory to a lesser extent. By building on our understanding of the predictive power of N-back task functional connectivity, this work enhances our knowledge of relationships between working memory and episodic memory.
Asunto(s)
Conectoma , Memoria Episódica , Encéfalo/diagnóstico por imagen , Humanos , Imagen por Resonancia Magnética , Memoria a Corto PlazoRESUMEN
While colorectal cancer (CRC) is third in prevalence and mortality among cancers in the United States, there is no effective method to screen the general public for CRC risk. In this study, to identify an effective mass screening method for CRC risk, we evaluated seven supervised machine learning algorithms: linear discriminant analysis, support vector machine, naive Bayes, decision tree, random forest, logistic regression, and artificial neural network. Models were trained and cross-tested with the National Health Interview Survey (NHIS) and the Prostate, Lung, Colorectal, Ovarian Cancer Screening (PLCO) datasets. Six imputation methods were used to handle missing data: mean, Gaussian, Lorentzian, one-hot encoding, Gaussian expectation-maximization, and listwise deletion. Among all of the model configurations and imputation method combinations, the artificial neural network with expectation-maximization imputation emerged as the best, having a concordance of 0.70 ± 0.02, sensitivity of 0.63 ± 0.06, and specificity of 0.82 ± 0.04. In stratifying CRC risk in the NHIS and PLCO datasets, only 2% of negative cases were misclassified as high risk and 6% of positive cases were misclassified as low risk. In modeling the CRC-free probability with Kaplan-Meier estimators, low-, medium-, and high CRC-risk groups have statistically-significant separation. Our results indicated that the trained artificial neural network can be used as an effective screening tool for early intervention and prevention of CRC in large populations.
RESUMEN
Among women, breast cancer is a leading cause of death. Breast cancer risk predictions can inform screening and preventative actions. Previous works found that adding inputs to the widely-used Gail model improved its ability to predict breast cancer risk. However, these models used simple statistical architectures and the additional inputs were derived from costly and / or invasive procedures. By contrast, we developed machine learning models that used highly accessible personal health data to predict five-year breast cancer risk. We created machine learning models using only the Gail model inputs and models using both Gail model inputs and additional personal health data relevant to breast cancer risk. For both sets of inputs, six machine learning models were trained and evaluated on the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial data set. The area under the receiver operating characteristic curve metric quantified each model's performance. Since this data set has a small percentage of positive breast cancer cases, we also reported sensitivity, specificity, and precision. We used Delong tests (p < 0.05) to compare the testing data set performance of each machine learning model to that of the Breast Cancer Risk Prediction Tool (BCRAT), an implementation of the Gail model. None of the machine learning models with only BCRAT inputs were significantly stronger than the BCRAT. However, the logistic regression, linear discriminant analysis, and neural network models with the broader set of inputs were all significantly stronger than the BCRAT. These results suggest that relative to the BCRAT, additional easy-to-obtain personal health inputs can improve five-year breast cancer risk prediction. Our models could be used as non-invasive and cost-effective risk stratification tools to increase early breast cancer detection and prevention, motivating both immediate actions like screening and long-term preventative measures such as hormone replacement therapy and chemoprevention.