Machine learning for precision medicine

MacEachern, Sarah J.; Forkert, Nils D.

doi:10.1139/gen-2020-0131

Cited by 266 publications

(225 citation statements)

References 47 publications

Supporting

Mentioning

182

Contrasting

Unclassified

Order By: Relevance

“…Supervised machine learning techniques are capable of identifying complex patterns in highdimensional data, whereas the identified patterns can then be used to make patient-specific predictions on new unseen cases (12). Machine learning has been used successfully for various precision medicine problems (13) and multiple studies have attempted to utilize features obtained from the aforementioned group-wise studies to classify individual PD and PSP-RS patients [e.g., (14)(15)(16)].…”

Section: Introductionmentioning

confidence: 99%

Utility of Multi-Modal MRI for Differentiating of Parkinson's Disease and Progressive Supranuclear Palsy Using Machine Learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background: Patients with Parkinson's disease (PD) and progressive supranuclear palsy Richardson's syndrome (PSP-RS) often show overlapping clinical features, leading to misdiagnoses. The objective of this study was to investigate the feasibility and utility of using multi-modal MRI datasets for an automatic differentiation of PD patients, PSP-RS patients, and healthy control (HC) subjects.Material and Methods: T1-weighted, T2-weighted, and diffusion-tensor (DTI) MRI datasets from 45 PD patients, 20 PSP-RS patients, and 38 HC subjects were available for this study. Using an atlas-based approach, regional values of brain morphology (T1-weighted), brain iron metabolism (T2-weighted), and microstructural integrity (DTI) were measured and employed for feature selection and subsequent classification using combinations of various established machine learning methods.Results: The optimal machine learning model using regional morphology features only achieved a classification accuracy of 65% (67/103 correct classifications) differentiating PD patients, PSP-RS patients, and HC subjects. The optimal machine learning model using only quantitative T2 values performed slightly better and achieved an accuracy of 75.7% (78/103). The optimal classifier using DTI features alone performed considerably better with 95.1% accuracy (98/103). The optimal multi-modal classifier using all features also achieved an accuracy of 95.1% but required more features and achieved a slightly lower F1-score compared to the optimal model using DTI features alone.Conclusion: Machine learning models using multi-modal MRI perform significantly better than uni-modal machine learning models using morphological parameters based on T1-weighted MRI datasets alone or brain iron metabolism markers based on T2-weighted MRI datasets alone. However, machine learnig models using regional brain microstructural integrity metrics computed from DTI datasets perform similar to the optimal multi-modal machine learning model. Thus, given the results from this study cohort, it appears that morphology and brain iron metabolism markers may not provide additional value for classification compared to using DTI metrics alone.

show abstract

Section: Introductionmentioning

confidence: 99%

Utility of Multi-Modal MRI for Differentiating of Parkinson's Disease and Progressive Supranuclear Palsy Using Machine Learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…This has led to the increased use and development of diagnostic methods to streamline the process and improve patient outcomes by decreasing the time needed to identify the cause of an infection, determine whether it is a resistant strain, and adjust patient treatment [ 27 , 28 , 29 ]. This vast range of techniques and their utility in identifying not only infectious diseases but also non-transmissible conditions can be attributed to the progress in technologies that support precision medicine over the last decade, including advances in microfluidic devices [ 30 , 31 , 32 , 33 , 34 ], next-generation sequencing (NGS) and nucleic acid amplification (NAA) methods [ 35 , 36 , 37 , 38 ], mass spectrometry (MS) techniques [ 29 , 38 , 39 , 40 ], laboratory automation [ 41 ], power sources for medical devices [ 42 ], smart materials and nanomaterials for imaging and sensing [ 8 , 43 , 44 , 45 ], biosensing technologies [ 34 , 43 , 46 , 47 , 48 , 49 , 50 ], smart devices for providing mobile power sources and computing power [ 50 , 51 , 52 , 53 ], data analysis techniques such as machine learning (ML) [ 54 , 55 , 56 , 57 ], and improved modeling of disease spread [ 58 ].…”

Section: Medical Diagnosismentioning

confidence: 99%

Sample Preparation and Diagnostic Methods for a Variety of Settings: A Comprehensive Review

Nichols

Geddes

2021

Molecules

View full text Add to dashboard Cite

Sample preparation is an essential step for nearly every type of biochemical analysis in use today. Among the most important of these analyses is the diagnosis of diseases, since their treatment may rely greatly on time and, in the case of infectious diseases, containing their spread within a population to prevent outbreaks. To address this, many different methods have been developed for use in the wide variety of settings for which they are needed. In this work, we have reviewed the literature and report on a broad range of methods that have been developed in recent years and their applications to point-of-care (POC), high-throughput screening, and low-resource and traditional clinical settings for diagnosis, including some of those that were developed in response to the coronavirus disease 2019 (COVID-19) pandemic. In addition to covering alternative approaches and improvements to traditional sample preparation techniques such as extractions and separations, techniques that have been developed with focuses on integration with smart devices, laboratory automation, and biosensors are also discussed.

show abstract

“…Consequently, many commercial systems using deep learning models are being deployed in practice for tasks, such as segmentation and classification [ 3 ], while many other non-commercial models are made publicly available. Overall, deep learning is expected to play a leading role in the future of precision medicine [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

An Analysis of the Vulnerability of Two Common Deep Learning-Based Medical Image Segmentation Techniques to Model Inversion Attacks

Subbanna

Wilms

Tuladhar

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Recent research in computer vision has shown that original images used for training of deep learning models can be reconstructed using so-called inversion attacks. However, the feasibility of this attack type has not been investigated for complex 3D medical images. Thus, the aim of this study was to examine the vulnerability of deep learning techniques used in medical imaging to model inversion attacks and investigate multiple quantitative metrics to evaluate the quality of the reconstructed images. For the development and evaluation of model inversion attacks, the public LPBA40 database consisting of 40 brain MRI scans with corresponding segmentations of the gyri and deep grey matter brain structures were used to train two popular deep convolutional neural networks, namely a U-Net and SegNet, and corresponding inversion decoders. Matthews correlation coefficient, the structural similarity index measure (SSIM), and the magnitude of the deformation field resulting from non-linear registration of the original and reconstructed images were used to evaluate the reconstruction accuracy. A comparison of the similarity metrics revealed that the SSIM is best suited to evaluate the reconstruction accuray, followed closely by the magnitude of the deformation field. The quantitative evaluation of the reconstructed images revealed SSIM scores of 0.73±0.12 and 0.61±0.12 for the U-Net and the SegNet, respectively. The qualitative evaluation showed that training images can be reconstructed with some degradation due to blurring but can be correctly matched to the original images in the majority of the cases. In conclusion, the results of this study indicate that it is possible to reconstruct patient data used for training of convolutional neural networks and that the SSIM is a good metric to assess the reconstruction accuracy.

show abstract

Machine learning for precision medicine

Cited by 266 publications

References 47 publications

Utility of Multi-Modal MRI for Differentiating of Parkinson's Disease and Progressive Supranuclear Palsy Using Machine Learning

Utility of Multi-Modal MRI for Differentiating of Parkinson's Disease and Progressive Supranuclear Palsy Using Machine Learning

Sample Preparation and Diagnostic Methods for a Variety of Settings: A Comprehensive Review

An Analysis of the Vulnerability of Two Common Deep Learning-Based Medical Image Segmentation Techniques to Model Inversion Attacks

Contact Info

Product

Resources

About