Dataset Information

NetDx: interpretable patient classification using integrated patient similarity networks.

ABSTRACT: Patient classification has widespread biomedical and clinical applications, including diagnosis, prognosis, and treatment response prediction. A clinically useful prediction algorithm should be accurate, generalizable, be able to integrate diverse data types, and handle sparse data. A clinical predictor based on genomic data needs to be interpretable to drive hypothesis-driven research into new treatments. We describe netDx, a novel supervised patient classification framework based on patient similarity networks, which meets these criteria. In a cancer survival benchmark dataset integrating up to six data types in four cancer types, netDx significantly outperforms most other machine-learning approaches across most cancer types. Compared to traditional machine-learning-based patient classifiers, netDx results are more interpretable, visualizing the decision boundary in the context of patient similarity space. When patient similarity is defined by pathway-level gene expression, netDx identifies biological pathways important for outcome prediction, as demonstrated in breast cancer and asthma. netDx can serve as a patient classifier and as a tool for discovery of biological features characteristic of disease. We provide a free software implementation of netDx with automation workflows.

SUBMITTER: Pai S

PROVIDER: S-EPMC6423721 | biostudies-literature | 2019 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

netDx: interpretable patient classification using integrated patient similarity networks.

Pai Shraddha S Hui Shirley S Isserlin Ruth R Shah Muhammad A MA Kaka Hussam H Bader Gary D GD

Molecular systems biology 20190314 3

Patient classification has widespread biomedical and clinical applications, including diagnosis, prognosis, and treatment response prediction. A clinically useful prediction algorithm should be accurate, generalizable, be able to integrate diverse data types, and handle sparse data. A clinical predictor based on genomic data needs to be interpretable to drive hypothesis-driven research into new treatments. We describe netDx, a novel supervised patient classification framework based on patient si ...[more]

PMID: 30872331

Similar Datasets

Project description:Very preterm birth (VPT; ≤32 weeks' gestation) is associated with altered brain development and cognitive and behavioral difficulties across the lifespan. However, heterogeneity in outcomes among individuals born VPT makes it challenging to identify those most vulnerable to neurodevelopmental sequelae. Here, we aimed to stratify VPT children into distinct behavioral subgroups and explore between-subgroup differences in neonatal brain structure and function. 198 VPT children (98 females) previously enrolled in the Evaluation of Preterm Imaging Study (EudraCT 2009-011602-42) underwent Magnetic Resonance Imaging at term-equivalent age and neuropsychological assessments at 4-7 years. Using an integrative clustering approach, we combined neonatal socio-demographic, clinical factors and childhood socio-emotional and executive function outcomes, to identify distinct subgroups of children based on their similarity profiles in a multidimensional space. We characterized resultant subgroups using domain-specific outcomes (temperament, psychopathology, IQ and cognitively stimulating home environment) and explored between-subgroup differences in neonatal brain volumes (voxel-wise Tensor-Based-Morphometry), functional connectivity (voxel-wise degree centrality) and structural connectivity (Tract-Based-Spatial-Statistics). Results showed two- and three-cluster data-driven solutions. The two-cluster solution comprised a 'resilient' subgroup (lower psychopathology and higher IQ, executive function and socio-emotional scores) and an 'at-risk' subgroup (poorer behavioral and cognitive outcomes). No neuroimaging differences between the resilient and at-risk subgroups were found. The three-cluster solution showed an additional third 'intermediate' subgroup, displaying behavioral and cognitive outcomes intermediate between the resilient and at-risk subgroups. The resilient subgroup had the most cognitively stimulating home environment and the at-risk subgroup showed the highest neonatal clinical risk, while the intermediate subgroup showed the lowest clinical, but the highest socio-demographic risk. Compared to the intermediate subgroup, the resilient subgroup displayed larger neonatal insular and orbitofrontal volumes and stronger orbitofrontal functional connectivity, while the at-risk group showed widespread white matter microstructural alterations. These findings suggest that risk stratification following VPT birth is feasible and could be used translationally to guide personalized interventions aimed at promoting children's resilience.

Project description:BackgroundRecent years have been witnessing a substantial improvement in the accuracy of skin cancer classification using convolutional neural networks (CNNs). CNNs perform on par with or better than dermatologists with respect to the classification tasks of single images. However, in clinical practice, dermatologists also use other patient data beyond the visual aspects present in a digitized image, further increasing their diagnostic accuracy. Several pilot studies have recently investigated the effects of integrating different subtypes of patient data into CNN-based skin cancer classifiers.ObjectiveThis systematic review focuses on the current research investigating the impact of merging information from image features and patient data on the performance of CNN-based skin cancer image classification. This study aims to explore the potential in this field of research by evaluating the types of patient data used, the ways in which the nonimage data are encoded and merged with the image features, and the impact of the integration on the classifier performance.MethodsGoogle Scholar, PubMed, MEDLINE, and ScienceDirect were screened for peer-reviewed studies published in English that dealt with the integration of patient data within a CNN-based skin cancer classification. The search terms skin cancer classification, convolutional neural network(s), deep learning, lesions, melanoma, metadata, clinical information, and patient data were combined.ResultsA total of 11 publications fulfilled the inclusion criteria. All of them reported an overall improvement in different skin lesion classification tasks with patient data integration. The most commonly used patient data were age, sex, and lesion location. The patient data were mostly one-hot encoded. There were differences in the complexity that the encoded patient data were processed with regarding deep learning methods before and after fusing them with the image features for a combined classifier.ConclusionsThis study indicates the potential benefits of integrating patient data into CNN-based diagnostic algorithms. However, how exactly the individual patient data enhance classification performance, especially in the case of multiclass classification problems, is still unclear. Moreover, a substantial fraction of patient data used by dermatologists remains to be analyzed in the context of CNN-based skin cancer classification. Further exploratory analyses in this promising field may optimize patient data integration into CNN-based skin cancer diagnostics for patients' benefits.

Dataset Information

NetDx: interpretable patient classification using integrated patient similarity networks.

Publications

netDx: interpretable patient classification using integrated patient similarity networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets