Table 2.
Applications of deep learning (Hinton 2018)
| Types of data | Application | References |
|---|---|---|
| Electronic health records | ● It helps in indicating different population subtypes and to differentiate symptoms of gout and acute leukemia from uric acid | Lasko et al. (2013) |
| ● Assigns the diagnosis process for the patients by previous clinical status | Liang et al. (2014) | |
| ● To know about heart failure and chronic pulmonary illness in advance | Cheng et al. (2016) | |
| ● Advanced treatments over the onset of diseases by predicting from lab results | Razavian et al. (2016) | |
| ● End-to-end method for forecasting after discharge unplanned readmission | Nguyen et al. (2016) | |
| Clinical imaging | ● Advanced imaging using Magnetic Resonance Imaging (MRI) Scan to detect Alzheimer's disease | Brosch and Tam (2013) |
| ● Segmentation of knee cartilage using MRIs to know about damage of tissues | Prasoon et al. (2013) | |
| ● Alzheimer's diagnosis from the brain’s MRI can be diagnosed early | Liu et al. (2014) | |
| ● Skin cancer classification before the lab tests | Esteva et al. (2017) | |
| Genomics | ● Cancer recognition by profiles in gene expression | Fakoor et al. (2013) |
| ● Protein backbone analysis out of protein sequences | Lyons et al. (2014) | |
| ● Estimation of Energy Expenditure (EE) using wearable sensors | Zhu et al. (2015) | |
| ● Identify photo plethysmography signs for tracking wellbeing | Jindal et al. (2016) | |
| ● In single-cell sequencing, can perform tests of bisulfite ion (HSO3−) estimate methylation levels | Angermueller et al. (2017) |