Skip to main content

Table 8 Input Variables and artificial intelligence that are applied the most in the identification of risk groups of osteoporosis or fractures

From: Artificial intelligence on the identification of risk groups for osteoporosis, a general review

Input variables Artificial intelligence
Abortions or stillbirths
Stroke
Height
Arthritis
Physical activities
Hearing
Cancer
Cataract
Alcohol consumption
Coffee consumption
Corticoids
Waist circumference
Diabetes
Difficulty of mobility
Heart condition
Hepatic disease
Chronic Respiratory Disease A
Pain when walking
Headache or migraine
Duration of breastfeeding
Education
Estrogen therapy
Hand hold medium Strength
Fracture
Smoking
Pregnancy
Hipertension
Hyperlipidemia
History of falling accidents
Age
BMI—body mass index
Urinary incontinence
Calcium intake
Glucosamine intake
Intake of milk
Vitamin intake
Parkinson’s disease
Menopause
DMO total value
Number of children born
Occupation
Weight
MMSE Score
Race
Gender
Hormone replacement therapy
Use of analgesic
Use of antidiabetics
ANFIS—adpative neuro-fuzzy inference system
ANNartificial neural network
CNN—condensed nearest neighbor
GA—genetic algorithm
LVQ—learning vector quantization
MFNN—multilayer feedforward neural networks
MLmachine learning
NN—nearest neighbor
PNN—probabilistic neural network
RBF—radial basis function
SVMsupport vector machine
LRlogistic regression
  1. Main input variables and artificial intelligence used to identify risk groups for osteoporosis