diff --git a/paper/40_experiments.tex b/paper/40_experiments.tex
index 18483e77ad44e31aa438b6596542f88bdf904da3..df188b9c6cc292c084a802c0b21a4eb9fac7bcf2 100644
--- a/paper/40_experiments.tex
+++ b/paper/40_experiments.tex
@@ -75,15 +75,24 @@ The two modeles where combined to create the final pipeline.
 We tested both NER models in the final pipeline, as their performance differs significantly.
 As both NEN models performe similary, we used the word and extended ICD-10 classification model in the final pipeline.
 The results obtained during training are presented in Table \ref{tab:final_train}.
+Results obtained on the evaluation dataset are shown in Table \ref{tab:final_test}
 
 \begin{table}[]
 \centering
-\begin{tabular}{l|l|l|l|l|l}
+\begin{tabular}{|l|l|l|l|}
 Model &  Precision & Recall & F-1\\
 S2S balanced + ICD-10 extended & 0.73 & 0.61 & 0.61 \\
 S2S extended + ICD-10 extended & 0.74 & 0.62 & 0.63 \\
 \end{tabular}
 \caption{Final Pipeline Evaluation}
 \label{tab:final_train}
+\begin{tabular}{|l|l|l|l|}
+Model &  Precision & Recall & F-1\\
+S2S balanced + ICD-10 extended &  &  & \\
+S2S extended + ICD-10 extended &  &  & \\
+\end{tabular}
+\caption{Final Pipeline Evaluation}
+\label{tab:final_test}
+
 \end{table}