Linear model-based estimation of blood pressure and cardiac output for Normal and Paranoid cases

• Published in: Neural computing & applications Vol. 25; no. 6; pp. 1223 - 1240
• Main Authors: Aboamer, Mohamed Abdelkader, Azar, Ahmad Taher, Wahba, Khaled, Mohamed, Abdallah S. A.
• Format: Journal Article
• Language: English
• Published: London Springer London 01-11-2014; Springer
• Subjects: Adult and adolescent clinical studies; Applied sciences; Artificial Intelligence; Biological and medical sciences; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer science; control theory; systems; Control theory. Systems; Data Mining and Knowledge Discovery; Exact sciences and technology; Fundamental and applied biological sciences. Psychology; Heart; Image Processing and Computer Vision; Medical sciences; Modelling and identification; Original Article; Probability and Statistics in Computer Science; Psychology. Psychoanalysis. Psychiatry; Psychopathology. Psychiatry; Psychoses; Vertebrates: cardiovascular system; Heart rate; MISO transfer function; Blood pressure; System identification; Cardiac output; Stroke volume; Drug; Root; Neuroleptic; Paranoiac psychosis; Consistency; Modeling; Quadrupoles; Linear model; Mean square error; Linear system; Z transformation; Parallel processing; Linear estimation; Cardiology; Transfer function; MISO system; Poles and zeros
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-014-1566-4

Provisioning a generic simple linear mathematical model for Paranoid and Healthy cases leading to auxiliary investigation of the neuroleptic drugs effect imposed on cardiac output (CO) and blood pressure (BP). Multi-input single output system identification in consistency with the Z-Transform is considered an essential role in the exploration of linear discrete system identification. Twenty Paranoid and 20 Healthy peer cases have been chosen to lie under study. The generated CO model forming two poles and two zeros produced a root–mean-squared error (RMSE) of 0.109 and an average RMSE of 1.39 due to Paranoid cases. On the other hand, Healthy cases obtained model held three poles and two zeros with RMSE equal to 0.17 and an average of 0.63. The BP model with four poles and two zeros showed a 2.15 and 21.69 for RMSE and an average RMSE, respectively, for Paranoid cases, whereas seven poles and two zeros provided an RMSE of 5.7 and an average RMSE of 17.19 for Healthy cases. The obtained results were provided a generic models of CO with promising outcomes for Paranoid and Healthy cases. Moreover, the BP model has less and yet acceptable results in both Paranoid and Healthy cases.