Penetration of Deep Learning in Human Health Care and Pharmaceutical Industries; the Opportunities and Challenges

Computational medicine has emerged as a result of the advancement of medical technology, which has led to the emergence of the big data era in the biomedical area, which is supported by artificial intelligence technology. To advance the development of precision medicine, people must be able to extract the valuable information from this vast biomedical data. In the past, professionals in the field of feature engineering and domain knowledge were typically utilised to extract the features from the biological data using machine learning techniques, which took a lot of time and resources. Modern machine learning techniques like deep learning (DL) have an advantage over them in that they can automatically find strong, complex features from fresh data without the necessity for succeeding engineering. The study of DL's applications in the fields of genomics, drug development, electronic health records, and medical imaging suggests that deep learning has clear advantages in maximising the use of biomedical data. Deep learning is becoming increasingly important in the field of medicine and health due to its large range of potential applications. The lack of data, interpretability, data privacy, and heterogeneity are some of the limitations of deep learning in computational medical health. A resource for improving the use of deep learning in medical health is provided by the analysis and discussion of these difficulties.

[1]  Rui Li,et al.  Imputation of single-cell gene expression with an autoencoder neural network , 2018, bioRxiv.

[2]  Jay Shendure,et al.  Predicting mRNA abundance directly from genomic sequence using deep convolutional neural networks , 2018, bioRxiv.

[3]  Jason H. Moore,et al.  Mapping Patient Trajectories using Longitudinal Extraction and Deep Learning in the MIMIC-III Critical Care Database , 2017, bioRxiv.

[4]  Eugenio Culurciello,et al.  LinkNet: Exploiting encoder representations for efficient semantic segmentation , 2017, 2017 IEEE Visual Communications and Image Processing (VCIP).

[5]  Raúl San José Estépar,et al.  Development and Progression of Interstitial Lung Abnormalities in the Framingham Heart Study. , 2016, American journal of respiratory and critical care medicine.

[6]  P. Cattin,et al.  Multi-dimensional Gated Recurrent Units for the Segmentation of Biomedical 3D-Data , 2016, LABELS/DLMIA@MICCAI.

[7]  Jimeng Sun,et al.  RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism , 2016, NIPS.

[8]  Ian Goodfellow,et al.  Deep Learning with Differential Privacy , 2016, CCS.

[9]  Ping Zhang,et al.  Risk Prediction with Electronic Health Records: A Deep Learning Approach , 2016, SDM.

[10]  Ning Zhang,et al.  Improving Tuberculosis Diagnostics Using Deep Learning and Mobile Health Technologies among Resource-Poor and Marginalized Communities , 2016, 2016 IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE).

[11]  Sergey Plis,et al.  Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data. , 2016, Molecular pharmaceutics.

[12]  Yan Liu,et al.  Recurrent Neural Networks for Multivariate Time Series with Missing Values , 2016, Scientific Reports.

[13]  O. Stegle,et al.  DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning , 2016, Genome Biology.

[14]  D. Shen,et al.  Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans , 2016, Scientific Reports.

[15]  Marios Anthimopoulos,et al.  Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network , 2016, IEEE Transactions on Medical Imaging.

[16]  Xinghua Lu,et al.  Learning a hierarchical representation of the yeast transcriptomic machinery using an autoencoder model , 2016, BMC Bioinformatics.

[17]  Hamid Jafarkhani,et al.  A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI , 2015, Medical Image Anal..

[18]  A. Subramanian,et al.  Gene expression inference with deep learning , 2015, bioRxiv.

[19]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[20]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.