- Characteristics of the study group
The study cohort consisted of 420 subjects with a history of overt hyperthyroidism, 79.3% women and 20.7% men, whose mean age at the onset of hyperthyroidism was 44.3±12.1 years. 94% of patients had GD, others had nonimmune thyroid pathology: TA or MNG. Detailed characteristic of the study population is shown in table 2.
TSH level was lower than the detection limit of 0.01 μIU/l in the majority of cases. When calculating the median for the group, it was considered that these individuals had TSH level of 0.01 µIU/l. The median, thereby, was presented as <0.014 µIU/l (table 2).
The lipid panel assessment showed that TC, LDL and TG mean levels were target (for low or moderate cardiovascular risk). HDL mean level for the men and women was at the lower limit of the target range.
The proportion of diabetes cases was high due to the big amount of diabetes patients at Almazov centre and Pavlov University. They were enrolled in the study because they had hyperthyroidism as a secondary diagnosis.
Table 3 shows cardiovascular status of the participants before and during hyperthyroidism. Before hyperthyroidism development, 30.1% of patients had arterial hypertension, 42.7% of which had above target ABP most of the time. During hyperthyroidism, the proportion of hypertensive patients significantly increased to 54.8%, but the participants were less likely to have above target ABP (28.1%). Similarly, the frequency of congestive heart failure dramatically increased after hyperthyroidism development from around one in twenty (4.8%) to more than one in four (31.4%). Coronary heart disease was detected in 12.9% of subjects, 31.5% of which had a prior history of myocardial infarction.
Heart rhythm disorders before hyperthyroidism were established in only 1.2% of participants. During hyperthyroidism 81.5% of participants were found to have dysrhythmias, the most common of which was premature atrial contraction (PAC) (44.9%). The median heart rate during hyperthyroidism of the study cohort was 94 bpm (IQR 85; 103.5 bpm). Sinus tachycardia (heart rate ≥90 bpm) was found in 64.3% of participants. Regarding TAF, we intentionally enrolled TAF subjects in the study cohort, which explains the abnormally high percentage (30.2%) of these patients in our sample.
Table 2
Characteristics of the study group
Male, % (n)
|
20.7 (87)
|
Mean age, years
|
44.3±12.1*
|
Thyrotoxicosis duration, months**
|
10; (6;20)***
|
Subclinical hyperthyroidism duration, % (n):
|
|
<1 year
|
34.3 (128)
|
≥1 year
|
65.7 (245)
|
Number of relapses, % (n):
|
|
0 (no relapses)
|
36.6 (140)
|
1
|
33.8 (129)
|
≥2
|
29.6 (113)
|
Hyperthyroidism origin, % (n):
|
|
Graves’ disease
|
94 (395)
|
Toxic adenoma or multinodular toxic goiter
|
6 (25)
|
TSH, μIU/l
|
<0.014 (0.01; 0.05)
|
fТ3, times above ULN range
|
1.8 (1.4; 2.6)***
|
fТ4, times above ULN range
|
2.0 (1.5; 3.0)***
|
Weight loss in the onset of hyperthyroidism, kg
|
6 (0.0; 12.0) ***
|
Extrathyroidal Graves 'disease manifestations, % (n):****
|
|
ophthalmopathy
|
48.3 (191)
|
pretibial myxedema
|
1.0 (4)
|
TSH receptors antibodies, times above ULN range ****
|
8.4 (3.6; 26.7)***
|
Body mass index, kg/m2
|
25.4 (22.4; 30.0)***
|
Overweight, % (n)
|
27.7 (108)
|
Obesity, % (n):
|
24.9 (97)
|
level 1
|
16.9 (66)
|
level 2
|
6.4 (25)
|
level 3
|
1.5 (6)
|
Carbohydrate metabolism disorders, % (n):
|
16.6 (57)
|
impaired fasting glucose
|
4.4 (15)
|
impaired glucose tolerance
|
2.6 (9)
|
diabetes mellitus (type 1 or 2)
|
9.6 (33)
|
Lipid profile:
|
|
total cholesterol, mmol/l
|
4.2 (3.5; 5.2)***
|
triglycerides, mmol/l
|
1.0 (0.8; 1.4)***
|
low density lipoproteins, mmol/l
|
2.2 (1.4; 3.1)***
|
high density lipoproteins, mmol/l
|
1.1 (0.9; 1.4)***
|
Smokers, % (n)
|
28.4 (113)
|
Plasma creatinine level, µmol/l
|
61.2±17.8*
|
GFR, ml/min/1.73 m2
|
104.6 (85.0; 125.1)***
|
GFR 60-90 ml/min/1.73 m2, % (n)
|
25.9 (56)
|
GFR <60 ml/min/1.73 m2, % (n)
|
5.2 (11)
|
Plasma potassium level, mmol/l
|
4.4 ±0.5*
|
Hypokalaemia (plasma potassium <3.5 mmol/l), % (n)
|
2.8 (6)
|
Haemoglobin, g/l
|
132±17.8*
|
Anemia (haemoglobin <120 g/l for women, <130 g/l for men), % (n)
|
22.1 (53)
|
TSH= thyroid-stimulating hormone. fT3=free triiodothyronine. fT4=free tetraiodothyronine. ULN=upper limit of normal. GFR=glomerular filtration rate.
* mean±S.D.
** for patients with AF thyrotoxicosis duration is referred before AF development
*** median (interquartile range or percentiles 25; 75)
**** only in subjects with Graves’ disease
Table 3
Cardiovascular status
Arterial hypertension, %:
|
|
Before hyperthyroidism
|
30.1
|
During hyperthyroidism
|
54.8
|
Congestive heart failure, %:
|
Before hyperthyroidism
|
4.8
|
During hyperthyroidism
|
31.4
|
Coronary heart disease, %
|
12.9
|
Rhythm disorders before hyperthyroidism, %:
|
1.2
|
Premature atrial contraction
|
0.5
|
Premature ventricular contraction
|
0.7
|
Rhythm disorders during hyperthyroidism, %:
|
81.5
|
Premature atrial contraction
|
44.9
|
Premature ventricular contraction
|
16.2
|
Supraventricular tachycardia
|
13.3
|
Non-sustained ventricular tachycardia
|
5.1
|
Wandering of atrial pacemaker
|
2.0
|
Heart rate during hyperthyroidism, beat per minute
|
94 (85; 103.5)*
|
Sinus tachycardia during hyperthyroidism, %:
|
64.3
|
* median (interquartile range or percentiles 25; 75)
2. Differences in study variables between TAF and non-TAF patients
2.1 Demographic, metabolic parameters, smoking status, blood tests, characteristics of hyperthyroidism course
In TAF group we observed greater proportion of men, smokers, patients with nonimmune thyrotoxicosis, with prolonged duration (one year and more) of subclinical hyperthyroidism and with multiple relapses (≥2) of hyperthyroidism than in non-TAF group. TAF individuals had elder age, higher body mass index, more prolonged hyperthyroidism duration and higher serum creatinine level compared to non-TAF patients.
Table 4
Risk factors associated with TAF: demographic parameters, characteristics of hyperthyroidism course and others
|
TAF patients
|
Non-TAF patients
|
P-value
|
Male, %
|
32.3
|
15.7
|
<0.001
|
Smokers, %
|
35.2
|
25.3
|
0.042
|
Nonimmune origin of hyperthyroidism, %
|
10.2
|
4.1
|
0.015
|
Subclinical hyperthyroidism
duration ≥1 year, %
|
75.0
|
61.5
|
0.011
|
≥2 relapses of hyperthyroidism, %
|
45.4
|
23.4
|
<0.001
|
Age, years
|
48.9±12.2*
|
42.3±11.5*
|
<0.001
|
Body mass index, kg/m2
|
26.9 (23.6; 30.5)**
|
24.7 (21.9; 29.1)**
|
0.002
|
Thyrotoxicosis duration, months
|
18 (8;32)**
|
8 (5.5;14.0)**
|
<0.001
|
Serum creatinine level, mcmol/l
|
65.5±22.6*
|
58.7±13.9*
|
0.017
|
* mean±S.D.
**median (interquartile range or percentiles 25; 75)
2.2 Cardiovascular status
Among individuals diagnosed with TAF, there were more cases of arterial hypertension and congestive heart failure, both before and during hyperthyroidism development, compared to non-TAF patients. In addition, there were more participants who had above target ABP most of the time in TAF group compared to non-TAF subjects. The data are shown in table 5.
There was no statistically significant difference in the coronary heart disease frequency depending on the TAF presence.
Before hyperthyroidism there were too few cases of arrhythmias (1.2%, n=5) to analyze its association with TAF. The analysis of the heart rhythm disorders during hyperthyroidism showed that TAF patients were more likely to have both atrial and ventricular premature contraction (PVC) than non-TAF subjects. The frequency of other arrhythmias, detected during hyperthyroidism, was also higher in TAF group (table 5).
There was no association of TAF frequency with heart rate. The median heart rate for patients diagnosed with TAF was 96 bpm (IQR 88.3; 106 bpm), compared with 92 bpm (IQR 84; 102 bpm) for non-TAF individuals, but this difference was not statistically significant: p=0.181. Similarly, the frequency of sinus tachycardia (heart rate 90 bpm or more) was higher among TAF patients, compared to/with non-TAF participants (73.6% vs 61.9%), but the difference still was not significant: p=0.065.
Table 5
Risk factors associated with TAF: cardiovascular diseases
|
TAF patients
|
Non-TAF patients
|
Arterial hypertension before hyperthyroidism, % (p<0.001):
|
45.6
|
23.3
|
Above target ABP, % from hypertensive patients
|
45.6
|
40.3
|
Arterial hypertension during hyperthyroidism, % (p<0.001):
|
75.6
|
46.1
|
Above target ABP, % from hypertensive patients
|
32.2
|
25.2
|
Heart failure before hyperthyroidism, % (p=0.002):
|
10.5
|
2.4
|
Heart failure during hyperthyroidism, % (p<0.001):
|
51.1
|
23.3
|
Rhythm disorders during hyperthyroidism, %:
|
Premature atrial contraction (p<0.001)
|
87.5
|
35.5
|
Premature ventricular contraction (p<0.001)
|
50
|
8.8
|
Other arrhythmias (p<0.001):
|
Supra-ventricular tachycardia
|
28.2
|
10.6
|
Non-sustained ventricular tachycardia
|
20.5
|
2.3
|
Wandering of atrial pacemaker
|
2.6
|
1.8
|
ABP=arterial blood pressure.
2.3 Heart rate-reducing therapy
It should be noted that all patients before hyperthyroidism and 97% of those during hyperthyroidism (97%) received beta-blockers as heart rate-reducing therapy. /The former patients were more inclined to develop TAF, compared with non-TAF patients: 13% vs 5.9%, p=0.015. There was no significant difference between TAF and non-TAF participants on heart rate-reducing therapy during hyperthyroidism.
- Thyrotoxic atrial fibrillation prediction models
3.1 Derivation and validation of the prediction models
The final TAF prediction model included ten variables: age (1), sex (2), hyperthyroidism duration (3) and number of relapses (4), heart rate (5), the presence of arterial hypertension (6) and rhythm disturbances (PAC (7), PVC (8); supraventricular tachycardia, non-sustained ventricular tachycardia, wandering of atrial pacemaker (9)) and heart rate-reducing therapy (10). The last six features were evaluated during hyperthyroidism before TAF development.
According to the cross-validation method, among the eight machine learning methods, XGB classifier achieved the highest accuracy. The best performing XGB model was validated on the test set. The performance metrics for this model on the test set were as follows: 84% accuracy, 82% precision and 77% recall.
The model discrimination ability was estimated by the AUROC. The final XGB model achieved the high predictive capacity with AUROC of 0.93, when it was calculated with the full sample. The AUROC on the test set was slightly worse: 0.89.
3.2 Interpretation of the prediction models
In this section we present the results of applying three interpretability techniques for our TAF prediction model. They are as follows: Feature Importance, Shapley Values and Partial Dependence Plot.
- Feature importance method
Figure 1 shows the ranking of the input features importance. As shown in the figure, the feature other heart rhythm disorders during hyperthyroidism is the most important one, followed by PAC and PVC during hyperthyroidism. The variable relapses of hyperthyroidism is the least significant feature.
2. Shapley values (SHAP method)
Figure 2 shows the Shapley values for the model’s input features. The figure is organized in descending order of the feature importance, so that the PAC during hyperthyroidism contributes most to the TAF prediction. The figure also shows the feature values increasing and reducing TAF risk. The advanced age and long duration of hyperthyroidism have the highest positive impact on TAF risk (raised the risk), whereas short duration of hyperthyroidism, absence of PAC and low heart rate during hyperthyroidism have a highest negative impact on TAF risk (reduced the risk).
Figure 3 provides the interpretation of the model prediction for one random patient. We highlighted the variables that had a strong impact on the model prediction for the patient. The influence values of the features were calculated by the SHAP method. Features increasing TAF probability were marked in red, the ones reducing TAF - in blue. Heart rate during hyperthyroidism of 98 bpm and PAC during hyperthyroidism increased the probability of TAF most strongly. Features, reducing the probability of TAF for this particular patient, were as follows: short duration of hyperthyroidism (Duration of HT = 9), absence of PVC (PVC during HT = 1), absence of arterialhypertension during hyperthyroidism (AH during HT = 1) and heart rate-reducing therapy during hyperthyroidism (HRRT during HT = 2). The duration of hyperthyroidism had the strongest absolute influence on the resulting value. As a result, TAF development probability of 7% was calculated for this patient.
3. Partial Dependence Plot method
Figure 4 shows the cumulative effect of two predictors. This effect was calculated by the Partial dependence plot method. The scale shows how age and hyperthyroidism duration values alterations change TAF probability, provided the other features values are fixed. If a patient was older than 33, and hyperthyroidism duration was more than 20 months, the patient had TAF development risk more than 0.5. These two features increased the probability of TAF, when their values were increasing. Minimal risk value was 0.16 for patients who were younger than 20 with the short period of hyperthyroidism. Maximal risk value was 0.7 for patients who were older than 60 with the period of hyperthyroidism for over 40 months.
4. Top thyrotoxic atrial fibrillation risk factors elicited from the prediction model
The next aim of the study was to rank TAF predictors by the importance value and identify the most important features. For this purpose, we used feature importance (figure 1) and Shapley values (figure 2) techniques, assessing the features impact on the model output in two different ways. If consider the top five features, the four of them are the same in both methods. They are as follows: hyperthyroidism duration, PAC, PVC and heart rate during hyperthyroidism. According to the feature importance method, the five most important factors also include different rhythm disorders during hyperthyroidism, estimated collectively (figure 1). By contrast, according to the SHAP method the top five features include age.
When creating a list of five most important TAF risk factors, we took into account all the results of both methods. Apart from the four consistent predictors, we included age for three reasons listed below. Firstly, it is more difficult to obtain information about rhythm disorders than about age. Data collection challenges may provoke some errors. Secondly, there were many missing values for the variable other rhythm disorders during hyperthyroidism by contrast to age, for which there was none. Finally, age is an acknowledged TAF risk factor [4, 5, 7-14]. Thus, the top five TAF predictors, elicited from our model, include age, hyperthyroidism duration, PAC, PVC and heart rate during hyperthyroidism.