Discussion
Main findings
In this study, a RF model was made to predict surgical re-intervention
within two years after EA. Comparison of the predictive value of a RF
model with the existing logistic regression model of Stevens et al. was
made (1).
The existing logistic regression model has a C-index of 0.71 (95% CI
0.64-0.78) (1). The RF model, developed in this study, shows a C-index
of 0.65 (95% CI 0.56-0.74) after hyperparameter optimization. This
shows that the LR prediction model developed by Stevens et al. probably
performs better in predicting surgical re-intervention within two years
after EA than the newly developed RF model. However, this difference in
performance is not statistically significant when we look at the
confidence intervals. Significant predictors of the model are age,
duration of menstruation >7 days, dysmenorrhea, parity ≥5
and previous caesarean section(1).
In our database, high parity (≥5) is a predictive variable for surgical
re-intervention. This can be related to the larger uterine cavity of
grand multiparous women. However, when considering our RF model, parity
has no large impact on the AUC. This is in line with previously reported
studies that show no significant increased risk of treatment failure
with increasing parity (2,17).
Previous caesarean section is also related to higher rates of surgical
re-intervention which can be explained by irregularity of the uterine
wall caused by the uterine scar (44). This can inhibit complete contact
of the ablation device with the uterine wall, leading to residual active
endometrium.
In our cohort, pre-operative dysmenorrhea is associated with a higher
risk of surgical re-intervention. There is evidence that gynaecologic
pathology causing this dysmenorrhea (adenomyosis and endometriosis)
reduces the success of endometrial ablation (9,18,32,45,46). This can be
explained by the fact that EA is not an appropriate treatment for these
diseases due to the superficial effect of energy to the uterine wall of
ablation. It could help to diagnose these diseases before performance of
EA. However, sensitivity and specificity of the diagnostic tools for
determining these diseases in the pre-operative setting are still low
(47).
In line with previous studies, we found that younger age was associated
with a higher risk of surgical re-intervention (8,10–14,31).
The duration of menstruation > 7 days is also a negative
predictive factor for surgical re-intervention after EA. This may be
caused by a thicker endometrium which is more difficult to completely
remove by the device (8,11).