Table 2 Summary of machine learning algorithms for hypertension management in reviewed literature

[82]/2019

Hyp. Pred. (PH)

RFr, RFc, LLR, Boosted C5.0, SVM

Echo

RFc (85)

SVM (95)

RFr/RFc (67)

RFc (90)

RFr (87)

SVM (76)

-

HMIS

No

[89]/2020

Hyp. Pred. (PH)

LB, LDA, SVM, KNN, DT, AB, GD, LR

13 Echo+RHC

LB (87)

LB (90)

-

LB (87)

LB (87)

LB (83)

LB (88)

-

No

[86]/2021

Hyp. Pred. (PAH)

XGB, Rpart, RF, Ensemble

-

XGB (83)

Rpart/XGB/Ensemble (91)

RF/XGB (71)

RF/XGB (83)

RF (84)

-

XGB (83)

-

No

[83]/2021

Hyp. Pred. (based on

RF, CatBoost, MLP, LR

29,700 samples

RF (82)

RF (83)

RF (81)

-

RF (92)

-

-

UCI

No

easy-to-collect factors)

[51]/2022

NT/PHT

SVM, LR, LDA, KNN, DT

PPG+WST

SVM (71.42)

SVM (52.38/90.47)

-

SVM (84.61/65.51)

-

SVM (64.70/76.60)

-

PPG-BP

No

NT/PHT

SVM, LR, LDA, KNN, DT

C+S

SVM (64.29)

SVM (52.38/76.19)

-

SVM (68.75/61.54)

-

SVM (59.46/68.09)

-

PPG-BP

No

[76]/2018

Hyp. Pred.

SVM, MLP, LR, NB, C4.5, RF, HPM

175 samples

HPM (76.42)

HPM (70.27)

SVM/C4.5 (96.04)

HPM (78.79)

-

HPM (82.2)

-

Golino et al. [90]

No

[88]/2018

Hyp. Pred

LB, BN, LWNB, SVM, RF, ANN

23,095 samples

-

RF (69.96)

RF (91.71)

RF (81.69)

RF (93)

RF (86.70)

-

No

[84]/2021

Risk factors

ANN, DT, RF, GB, SVM, LASSO, SVMRFE

6956 samples

SVMRFE-GB (66.98)

SVMRFE-GB (97.92)

-

-

-

SVMRFE-GB (78.99)

-

Survey

No

[85]/2020

Risk factors

DT, LR, RF

987 records

DT/RF (82.1)

DT/RF (82.1)

-

RF (81.4)

-

RF (81.6)

-

QBB

No

[87]/2022

Risk factors

RF, DT, XGB, GB, LR, LDA

818603 samples

XGB/GB/LR/LDA (90)

=ACC

-

DT (91)

-

=ACC

-

Survey

No