In this paper, a new approach for leak detection in water networks is proposed which considersan extended time horizon analysis of pressure sensitivities. Previous works based on pressure sensitivitiesanalysis were developed by considering time instant evaluation. This fact makes them very sensitive todemand changes and noise in measurements. The proposed approach has been combined with fivedetection methods: the first is the binarization method, the second, third and fourth are based on thecomparison of measured pressure vectors with leak sensitivity matrix using methods of correlation, vectorangle and Euclidean distance respectively. And, finally, the fifth is based on the least square optimizationmethod. Another contribution of this paper is the performance comparison between the five detectionmethods in presence of single leaks in scenarios with noise in measurements and nodal demands. Resultsshowed that in most of the methods effectiveness is high, being the best the vector angle method, witheffectiveness higher than 96%. The correlation and optimization method had similar behaviors witheffectiveness superior to 90%. Finally, the binarization method is effective only in some scenarios but inpresence of noise has a poor performance.