Skip to main content

Table 2 Machine learning and deep learning models used on data collected in one and multiple timepoints, ordered by number of publications

From: Using artificial intelligence to predict patient outcomes from patient-reported outcome measures: a scoping review

Machine Learning (ML)

One Timepoint

Multiple Timepoints

Regression (n = 61)

[29,30,31,32,33,34,35,36,37,38,39]

[40,41,42,43,44,45,46,47,48,49,50]

[40, 51,52,53,54,55,56,57,58,59,60]

[61,62,63,64,65,66,67,68,69,70,71]

[72,73,74,75]

[76]

[77,78,79,80,81,82,83,84,85,86]

[28, 87, 88]

Boosting (n = 53)

[31, 32, 36,37,38,39,40, 42, 44, 89, 90]

[45, 48, 49, 51,52,53, 91,92,93,94]

[40, 56, 58, 60, 62,63,64, 95,96,97]

[2, 33, 66, 69, 72, 73, 75, 98,99,100]

[70, 74, 101]

[76]

[102]

[28, 77,78,79, 81,82,83,84, 103, 104]

Random Forest (n = 50)

[29,30,31,32,33, 36, 41, 42, 44, 89, 105]

[45,46,47,48, 50,51,52,53, 56, 92, 106]

[58, 60, 61, 64, 65, 69, 75, 95, 100, 107, 108]

[62, 63, 71, 73, 74, 97, 101]

[26, 28, 77, 78, 80, 87, 88, 104, 109, 110]

Support Vector Machine (n = 39)

[29, 31, 32, 34, 37, 41,42,43, 45, 46, 48]

[26, 50,51,52, 56, 57, 92, 96, 111, 112]

[61, 62, 64, 66, 71, 74, 89, 107, 108]

[102]

[78, 81, 83, 84, 87, 88, 103, 104]

Decision Tree (n = 24)

[37, 39, 41, 57, 92,93,94,95, 111, 112]

[2, 58, 63, 74, 96, 98, 100, 101, 108]

[77, 79, 84, 103, 109]

K-Nearest-Neighbours (n = 13)

[34, 36, 37, 39, 48, 56, 61, 74, 113]

[26, 83, 87, 104]

Na¨ıve Bayes (n = 12)

[36, 44, 50, 57, 70, 73, 74, 94, 108]

[26, 104, 109]

Voting Classifier (n = 4)

[37, 44]

[28, 82]

Discriminant Analysis (n = 4)

[34, 38, 94, 108]

None reported

Classification and Regression Tree (n = 2)

[34, 46]

None reported

Super Learner (n = 2)

[62, 69]

None reported

Other ML Methods (n = 8)

Wide and Deep [49]

Stochastic Gradient Descent [61] Bagging [63]

Bayesian Updating Algorithm [66]

Graphical Gaussian Model [67]

Multivariate Adaptive Regression Spline [41]

Hierarchical Gaussian Process [85]

Autoregressive Integrated Moving Average [26]

Deep Learning (DL)

One Timepoint

Multiple Timepoints

Multilayer Perceptron (n = 43)

[29, 30, 35,36,37, 39,40,41,42, 45, 90]

[48, 52,53,54, 56, 92, 94, 111, 112, 114]

[40, 57, 59, 61, 64, 66, 68, 96, 107, 115]

[72,73,74,75]

[76]

[26, 28, 79, 83, 84, 86, 104, 109, 116]

Recurrent Neural Network (RNN) (n = 3)

None reported

Long-Short Term Memory [26, 27]

RNN with Gated Recurrent Units [28]

Other DL Methods (n = 4)

Adaptive Neural Network [36]

Stacking Algorithm [57]

Bayesian Network Model [117]

Adaptive Neural Network [27]

  1. In the square brackets we list the number of the cited paper, according to the reference lis