fixes and improvements

thesis/sections/conclusion.tex

@@ -9,7 +9,7 @@ for fertility prediction based on high-resolution body core temperature data.
 By comparing LSTM- and Transformer-based models, as well as their convolutional variants,
 the results show that machine learning can achieve high predictive performance.
 LSTM models performed best according to standard evaluation metrics, whereas Transformer-based models
-proved more robust in simulated use-case evaluations for contraception and Natural Family Planning (NFP).
+proved more robust in simulated use case evaluations for contraception and Natural Family Planning (NFP).
 Predictions were consistently more reliable in regular cycles than in irregular ones,
 highlighting both the potential and the inherent limits of temperature-based approaches.
 
@@ -17,13 +17,12 @@ A characteristic pre-ovulatory temperature drop was identified as correlating wi
 Both its timing and its magnitude appear to influence fertility probability,
 pointing to a concrete physiological marker that could be exploited in practice.
 
-Use-case evaluations indicate that the model outputs could be highly relevant for contraception and NFP\@.
-In simulations, pregnancy rates approached those reported for commonly used contraceptives such as condoms
-or oral contraceptives, and with simple additional measures could even approximate the effectiveness of
-long-term hormonal methods or sterilization.
-While pregnancy rates for the NFP use-case were not significantly improved,
-the predictions enabled a four-fold increase in the efficiency of timed intercourse,
-facilitating more targeted pregnancy efforts for couples.
+Use case evaluations indicate that the model outputs could be relevant for contraception and NFP\@.
+In simulations, model-guided decisions reduced unintended pregnancies relative to naive and
+calendar baselines and improved the efficiency (pregnancies per 1000 intercourse events) of timed intercourse.
+These results are simulation-based and depend on assumptions about intercourse
+patterns and fecundability; they should not be interpreted as clinical effectiveness estimates or as
+direct comparisons to established contraceptive methods.
 
 Despite the limitations of real-world tracking data, including missing entries, noise,
 and user heterogeneity, this work underscores the potential of personalized, data-driven predictions