Accesso libero

Application of machine learning algorithm for predicting gestational diabetes mellitus in early pregnancy

INFORMAZIONI SU QUESTO ARTICOLO

Cita

Figure 1

Technical route.
Technical route.

Figure 2

Accuracy curve of the training set and the test set of the F1 model.
Accuracy curve of the training set and the test set of the F1 model.

Figure 3

Accuracy curve of the training set and the test set of the F2 model.
Accuracy curve of the training set and the test set of the F2 model.

Figure 4

Accuracy curve of the training set and the test set of the F3 model.
Accuracy curve of the training set and the test set of the F3 model.

Figure 5

Weighted ranking in the F1 model (top 20).
Weighted ranking in the F1 model (top 20).

Figure 6

Weighted ranking in the F2 model (top 20).
Weighted ranking in the F2 model (top 20).

Figure 7

Weighted ranking in the F3 model (top 20).
Weighted ranking in the F3 model (top 20).

Definition of input data variables for model training.

Dimension Variables Input variables
1. Physical examination 1.1 Age Age
1.2 BMI BMI
1.3 Blood type-A A
1.4 Blood type-B B
1.5 Blood type-AB AB
1.6 Blood type-O O
1.7 Systolic blood pressure SBP
1.8 Diastolic blood pressure DBP
2. Past history 2.1 Hypertension Hypertension
2.2 Heart disease Heart disease
2.3 Thyroid disease Thyroid disease
2.4 Gynecological diseases Gynecological diseases
2.5 Kidney disease Kidney disease
2.6 Congenital spina bifida Congenital spina bifida
2.7 Benign tumor Benign tumor
2.8 Past surgical history Past surgical history
2.9 HPV HPV
2.10 Colpomycosis Colpomycosis
2.11 PCOS PCOS
2.12 Negative reproductive history Negative reproductive history
2.13 History of multiple pregnancies History of multiple pregnancies
2.14 Regular menstruation Regular menstruation
3. Personal history 3.1 Body weight at birth Body weight at birth
3.2 Mother's weight Mother's weight
3.3 Number of births by mother Number of births by mother
3.4 Smoking Smoking
4. Family history 4.1 Family history of diabetes Family history of diabetes
5. Specialist examination 5.1 Uterine height Uterine height
5.2 Abdominal circumference Abdominal circumference
5.3 Weight gain Weight gain
5.4 Gravidity history Gravidity history
5.5 Parity history Parity history
5.6 Multiple pregnancies Multiple pregnancies
5.7 Fetus number Fetus number
6. Laboratory indicators 6.1 Fasting glucose Fasting glucose
6.2 Hepatitis Hepatitis
6.3 HIV HIV
6.4 Syphilis Syphilis
7. Food frequency questionnaire (FFQ) 7.1 Porridge intake Porridge intake (kg/month)
7.2 Flour foods intake Flour foods intake (kg/month)
7.3 Sweet food Intake Sweet food Intake (kg/month)
7.4 Fried food Intake Fried food Intake (kg/month)
7.5 Filling food Intake Filling food Intake (kg/month)
7.6 Coarse grain intake Coarse grain intake (kg/month)
7.7 Potato intake Potato intake (kg/month)
7.8 Milk intake Milk intake (kg/month)
7.9 Egg intake Egg intake (kg/month)
7.10 Red meat intake Red meat intake (kg/month)
7.11 Poultry intake Poultry intake (kg/month)
7.12 Processed meat intake Processed meat intake (kg/month)
7.13 Freshwater fishes intake Freshwater fishes Intake (kg/month)
7.14 Seafood intake Seafood intake (kg/month)
7.15 Bean products intake Bean products intake (kg/month)
7.16 Nuts intake Nuts intake (kg/month)
7.17 Dark vegetables intake Dark vegetables intake (kg/month)
7.18 Light vegetables intake Light vegetables intake (kg/month)
7.19 Mushrooms intake Mushrooms intake (kg/month)
7.20 Fruit intake Fruit intake (kg/month)
7.21 Sweet drinks intake Sweet drinks intake (kg/month)
7.22 Alcohol intake Alcohol intake (l/month)
8. International Physical Activity Questionnaire (IPAQ) 8.1 Heavy physical activity Heavy physical activity (min/week)
8.2 Moderate physical activity Moderate physical activity (min/week)
8.3 Light physical activity Light physical activity (min/week)
8.4 Walking time Walking time (min/week)
8.5 Sedentary time Sedentary time (min/day)
8.6 Sleep duration on weekdays Sleep duration on weekdays (hour/day)
8.7 Sleep duration in rest days Sleep duration in rest days (hour/day)

Confusion matrix from prediction results of GDM incidence in the F1 model.

Actual value Total Predicted value Prediction accuracy (%)

0 1
0 735 735 0 100
1 82 56 26 31.70
In all 817 93.15

Confusion matrix from prediction results of GDM incidence in the F2 model.

Actual value Total Predicted value Prediction accuracy (%)

0 1
0 735 695 40 94.56
1 467 96 371 79.44
In all 1202 88.69

Results of prediction models using random forest.

Data sets Accuracy for training set Accuracy for test set AUC
F1 0.957 0.931 0.66
F2 0.911 0.887 0.87
F3 0.930 0.916 0.58

Confusion matrix from prediction results of GDM incidence in the F3 model.

Actual value Total Predicted value Prediction accuracy (%)

0 1
0 735 735 0 100
1 82 69 13 15.85
In all 817 91.55
eISSN:
2544-8994
Lingua:
Inglese
Frequenza di pubblicazione:
4 volte all'anno
Argomenti della rivista:
Medicine, Assistive Professions, Nursing