Scientific Papers

The machine learning methods to analyze the using strategy of antiplatelet drugs in ischaemic stroke patients with gastrointestinal haemorrhage | BMC Neurology


Baseline character

Initially, the study recruited 300 patients. Among them, eight patients were no longer suited for inclusion criteria, 15 were lost to follow-up, and nine withdrew from the study. Finally, we acquired the data from 268 patients (176 in stopped group and 92 in reduced group). Among the 268 patients (mean age: 67.00 ± 13.49 years), 113 (40.3%) were female. Stopped group had a lower rate of patients with a history of antihypertensive drugs than reduced group. The other baseline data between the two groups had not shown a significant difference (Table 1).

Primary outcome events

As shown in Fig. 1a, to compare with reduced group (recurrence patients = 6, ischemic stroke = 5, hemorrhagic stroke = 1), the patients of stopped group (recurrence patients = 5, ischemic stroke = 5) had lower rate of recurrence of stroke (p = 0.161), but the difference had not a statistic significant.

Fig. 1
figure 1

Difference rates of outcome between stopped group and reduced group

In the univariate logistic regression analysis, we could not acquire the relationship between risk factors and the recurrence of stroke events or bleeding events.

Second outcome events

As shown in Fig. 1a, to compare with reduced group, the patients of stopped group had lower mortality (p = 0.008) and a lower rate of bleeding events (p = 0.125), but the last results had not a statistic significant. As shown in Fig. 1b, to compare with reduced group, the patients of stopped group had a lower rate distribution of severe patients (mRS 3–6) at 90 days (p = 0.056) but the results had not a statistic significant.

In the univariate logistic regression analysis, when we analysed risk factors of mortality, we found that older age (OR = 1.070, p = 0.001), female (OR = 2.609, p = 0.024), and higher NIHSS scores at admission (OR = 2.812, p < 0.001), patients in reduced group (OR = 2.922, p = 0.011) were related to the higher mortality within 90 days after admission. Smoking (OR = 0.287, p = 0.017) and using statin (OR = 0.390, p = 0.023) negatively correlated with higher mortality within 90 days after admission. When we analysed the risk factor of UFO, we found that older age (OR = 1.041, p < 0.001), female (OR = 1.735, p = 0.028), patients in reduced group(OR = 1.220, p < 0.001) and higher NIHSS scores at admission (OR = 1.892, p < 0.001) were related to the UFO at 90 days after admission. Smoking (OR = 0.666, p = 0.044), using statin (OR = 0.465, p = 0.002), higher value of triglyceride (TG) (OR = 0.287, p = 0.017) and higher value of glutamic-pyruvic transaminase (ALT) (OR = 0.977, p = 0.015) at admission were negative correlation with the UFO at 90 days after admission.

By the multivariable logistic regression analysis, we found that the older age (OR = 1.060, p = 0.009), higher NIHSS scores at admission (OR = 2.179, p = 0.008) and patients in reduced group (OR = 2.826, p = 0.030) were still related to the higher mortality within 90 days after admission. The older age (OR = 1.028, p = 0.021), patients in reduced group (OR = 0.621, p = 0.044) and higher NIHSS scores at admission (OR = 1.090, p < 0.001) were still related to the unfavourable functional outcome at 90 days after admission.

Supervised machine learning

We explored the relationship between risk factors and mortality and FFO with a machine learning model. The support vector machine model, including six factors, had the best performance for mortality (the accuracy score = 0.952), and the support vector machine model, including three factors, had the best performance for FFO (the accuracy score = 0.652).

The final support vector machine model for mortality showed that its AUC was 0.92, and prediction accuracy was 0.95 (Fig. 2a). The final support vector machine model for FFO showed that its AUC was 0.820, and prediction accuracy was 0.78 (Fig. 2b). The coefficient of the model is displayed in Table 2.

Fig. 2
figure 2

a The AUC plot of the support vector machine model for mortality; b The AUC plot of the support vector machine model for FFO. AUC area under the curve; FFO favourable functional outcome

Table 2 The coefficient of support vector machine model

Unsupervised machine learning

As shown in Fig. 3a, the line chart of Silhouette score showed that the 2 group was the best choice. The hot map showed that the 2 group was better for the Hierarchical Clustering model (Fig. 3b). The two-dimension scatter plot showed that the two groups by k-means had more precise discrimination (Fig. 3c).

Fig. 3
figure 3

a The line chart of Silhouette score for k-means methods; b The hot map for hierarchical clustering methods;  The two-dimension scatter plot of 2 groups by k-means

We grouped data into km2-1group and km2-2 group by K-means methods. We grouped data into hc2-1 group and hc2-2 group by the hierarchical clustering methods. The outcome event rate had not shown a significant difference between hc2-1 group and hc2-2 group. The km2-1 group had a lower rate of bleeding events (p < 0.001), lower mortality (p < 0.001), a lower rate of recurrence of stroke (p = 0.107) and a higher rate of FFO (P = 0.007) than km2-2 group (Fig. 4). Therefore, the 2 group by K-means method was the best grouping method.

Fig. 4
figure 4

Difference rates of outcome between km2-1 group and km2-2 group

To compare with km2-2 group, the patients of the km2-1 group had lesser female patients, lesser older patients, higher diastolic blood pressure at admission, lower NIHSS score at admission, higher rate of statin used, lower rate of disease history, higher value of platelet at admission and higher value of blood lipid at admission (Table 3).

Table 3 Difference character between Km2-1 group And Km2-2 group



Source link