Artificial intelligence enabled applications in kidney disease

Abstract

Artificial intelligence (AI) is considered as the next natural progression of traditional statistical techniques. Advances in analytical methods and infrastructure enable AI to be applied in health care. While AI applications are relatively common in fields like ophthalmology and cardiology, its use is scarcely reported in nephrology. We present the current status of AI in research toward kidney disease and discuss future pathways for AI. The clinical applications of AI in progression to end-stage kidney disease and dialysis can be broadly subdivided into three main topics: (a) predicting events in the future such as mortality and hospitalization; (b) providing treatment and decision aids such as automating drug prescription; and (c) identifying patterns such as phenotypical clusters and arteriovenous fistula aneurysm. At present, the use of prediction models in treating patients with kidney disease is still in its infancy and further evidence is needed to identify its relative value. Policies and regulations need to be addressed before implementing AI solutions at the point of care in clinics. AI is not anticipated to replace the nephrologists' medical decision-making, but instead assist them in providing optimal personalized care for their patients.

FIGURE 1

Figure shows the relationship between artificial intelligence (AI), machine learning (ML), and deep learning (DL). ML is a subset of AI and DL is a subset of ML. ML is a sub‐discipline of AI that uses training examples of how to perform a specific task without explicit instructions to identify associations for a given outcome measure. DL is a subfield of ML that mimics neural networks to learn

FIGURE 2

Supervised learning (SL) and unsupervised learning (UL) are the two main categories of machine learning (ML). Deep learning (DL) is a subset of ML. SL algorithms are used to learn the optimal parameters of the predictive model by investigating past examples with known inputs and known outputs. UL algorithms learn about patterns in the input data itself and does not have a known output

FIGURE 3

A very simple artificial neural network (ANN) with an input layer comprised of three inputs, hidden layer comprised of one neuron, and the output layer. ANN's neuron usually combines input from multiple sources through nonlinear activation functions

FIGURE 4

Deep Learning Network. Input layer with three inputs, multiple hidden layers of neurons, and two output layers. Higher the number of hidden layers deeper is the network

FIGURE 5

Convolution Neural Network (CNN) is a class of deep learning neural networks that is widely used for image classification. A CNN includes an input layer (image data), multiple hidden layers (convolution to extract features, pooling for subsampling features, and fully connected layer to classify images), and an output layer

FIGURE 6

Recurrent neural network (RNN). In RNN, the output from the function is fed back in the model in order to minimize error

FIGURE 7

Process for application of artificial intelligence with four phases: Problem definition, data preparation, model building, and production