Comparison of Machine Learning Algorithms for Sepsis Detection

Asad Ullah; Huma Qayyum; Farman Hassan; Muhammad Khateeb Khan; Auliya Ur Rahman

Authors

Asad Ullah University of Engineering and Technology Taxila, Punjab Pakistan
Huma Qayyum University of Engineering and Technology Taxila, Punjab Pakistan
Farman Hassan University of Engineering and Technology Taxila, Punjab Pakistan
Muhammad Khateeb Khan University of Engineering and Technology Taxila, Punjab Pakistan
Auliya Ur Rahman University of Engineering and Technology Taxila, Punjab Pakistan

Keywords:

Sepsis detection; Machine Learning; KNN; MLP; Random Forest; Logistic Regression; decision trees; forward filling technique; backward filling technique.

Abstract

Sepsis is a very fatal disease, causing a lot of causalities all over the world, about 2, 70,000 die of Sepsis annually, thus early detection of Sepsis disease would be a remedy to prevent this disease and it would be a big relief to the family of sepsis patients. Different researchers have worked on sepsis disease detection and its prediction but still the need to have an improved model for Sepsis detection remains. We compared various machine learning algorithms for Sepsis detection and used the dataset publicly available for all the researchers at Physionet.org, the dataset contains many empty or Null values, we applied backward filling and forward filling techniques, and we calculated missing values of MAP using equation (1) which gives more precise results, we divided the 40,336 files of datasets A and B into 80% training set and 20% testing set. We applied the algorithms twice one time using vital signs and clinical values of patients and the second time using only vital signs of the patients; using vital signs only the training accuracy of KNN, Logistic Regression, Random Forest, MLP, and Decision Trees was 0.992, 0.999, 0.981, 0.981, and 0.981 respectively, while the testing accuracy of KNN, Logistic Regression, Random Forest, MLP, and Decision Trees was 0.987, 0.980, 0.983, 0.981, and 0.981 respectively, for Sepsis Label 0, the value of precision for KNN, Random Forest, Decision Trees, Logistic Regression, and MLP was 0.99, 0.98, 0.98, 0.98, and 0.98 respectively, while the value of recall for KNN, Random Forest, Decision Trees, Logistic Regression, and MLP was 1.00, 1.00, 1.00, 1.00, and 1.00 respectively; the comparison of all the above-mentioned algorithms showed that KNN leads over all the competitors regarding the accuracy, precision, and recall.

Full Text

References

Access online at 12/12/2021, Available online at: www.physionet.org.

Reyna; Matthew; Supreeth Prajwal Shashikumar; Benjamin Moody; Ping Gu; Ashish Sharma; shamim nemati; and Gari Clifford 2019. Early Prediction of Sepsis from Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019.

Delahanty; Ryan J.; JoAnn Alvarez; Lisa M. Flynn; Robert L; Sherwin; and Spencer S. Jones. Development and evaluation of a machine learning model for the early identification of patients at risk for sepsis. Annals of emergency medicine 73, Volume 4 (2019), pp. 334-344.

Barton; Christopher; Uli Chettipally; Yifan Zhou; Zirui Jiang; Anna Lynn-Palevsky; Sidney Le; Jacob Calvert; and Ritankar Das. 2019. Evaluation of a Machine Learning Algorithm for up to 48-Hour Advance Prediction of Sepsis Using Six Vital Signs. Computers in Biology and Medicine; Volume 109 (April): 79–84. https://doi.org/10.1016/j.compbiomed.2019.04.027.

Back; Ji Sun; Yinji Jin; Taixian Jin; and Sun Mi Lee. 2016. Development and Validation of an Automated Sepsis Risk Assessment System. Research in Nursing & Health; Volume 39 (5); pp. 317–27; https://doi.org/10.1002/nur.21734.

Shankar-Hari; Manu; Gary S. Phillips; Mitchell L. Levy; Christopher W. Seymour; Vincent X. Liu; Clifford S; Deutschman; Derek C. Angus; Gordon D. Rubenfeld; and Mervyn Singer. Developing a Newdefinition and Assessing Newclinical Criteria for Septic Shock: For the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA - Journal of the American Medical Association; Volume 315 (8); pp. 775–87; https://doi.org/10.1001/jama.2016.0289.

Hsu; Po-Ya; and Chester Holtz. A Comparison of Machine Learning Tools for Early Prediction of Sepsis from ICU Data. 2019 Computing in Cardiology Conference (CinC) Volume 45; pp. 10–13; https://doi.org/10.22489/cinc.

Moor; Michael; Max Horn; Bastian Rieck; Damian Roqueiro; and Karsten Borgwardt. 2019. Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping. ArXiv.

Al-Mualem; Bilal Yaseen; and Lu Lu. A Deep Learning-Based Sepsis Estimation Scheme. Ieee Access; Volume 9 (2020); pp. 5442-5452.

Li; Xiang; Yanni Kang; Xiaoyu Jia; Junmei Wang; and Guotong Xie. TASP: A Time-Phased Model for Sepsis Prediction. 2019 Computing in Cardiology (CinC), IEEE, 2019; pp. 1.

Kiers; h. D; j. M. Hofstra; andj. F. M. Wetzels. Oscillometric blood pressure measurements: differences between measured and calculated

mean arterial pressure."nethjmed66.11 (2008): 474-9.

A. b; m. A; Mahfouz; a. Shoukry; and m. A. Ismail. Eknn; ensemble classifier in corporating connectivity and densityint ok nn with application to cancer diagnosis; artificial intelligence in medicine, Volume. 111; pp. 101985, 2021.Waseem, Muhammad, Zhenzhi Lin, Shengyuan Liu, Zhang Jinai, Mian Rizwan, and Intisar Ali Sajjad. "Optimal BRA based electric demand prediction strategy considering instance‐based learning of the forecast factors." International Transactions on Electrical Energy Systems (2021): e12967.

Waseem, Muhammad, Zhenzhi Lin, and Li Yang. "Data-driven load forecasting of air conditioners for demand response using levenberg– marquardt algorithm-based ANN." Big Data and Cognitive Computing 3, no. 3 (2019): 36.

A.B. A. Chaudhary; S. Kolhe; and R. Kamal. An improved random forest classifier for multi-class classification; Information Processing in Agriculture, Volume. 3, no. 4, pp. 215-222, 2016.

Quinlan; J. R 1986, Induction of Decision Trees, Machine Learning Volume 1 (1); pp. 81–106. https://doi.org/10.1007/bf00116251.

M. R. Özkale; Identification of outlying and influential data with principal components regression estimation in binary logistic regression; Communications in Statistics-Theory and Methods; Volume 50, no. 3; pp. 609-630; 2021.

Shankar-Hari M, Phillips GS, Levy ML, Seymour CW, Liu VX, Deutschman CS, et al.Developing a new de finition and assessing new clinical criteria for septic shock:for the Third International Consensus De finitions for Sepsis and Septic Shock (Sepsis-3). JAMA 2016;315:775 –87. https://doi.org/10.1001/jama.2016.0289.

Moor; Michael; Max Horn; Bastian Rieck; Damian Roqueiro; and Karsten Borgwardt; 2019. Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping; ArXiv.

Arber, Silvia, John J. Hunter, John Ross Jr, Minoru Hongo, Gilles Sansig, Jacques Borg, Jean-Claude Perriard, Kenneth R. Chien, and Pico Caroni. "MLP-deficient mice exhibit a disruption of cardiac cytoarchitectural organization, dilated cardiomyopathy, and heart failure." Cell 88, no. 3 (1997): 393-403.

Calvert, Jacob S., Daniel A. Price, Uli K. Chettipally, Christopher W. Barton, Mitchell D. Feldman, Jana L. Hoffman, Melissa Jay, and Ritankar Das. 2016. “A Computational Approach to Early Sepsis Detection.” Computers in Biology and Medicine 74: 69–73. https://doi.org/10.1016/j.compbiomed.2016.05.003.

Asad Ullah, Huma Qayyum, Muhammad Khateeb Khan, and Fawad Ahmad. "Sepsis Detection Using Extreme Gradient Boost (XGB): A Supervised Learning Approach." In 2021 Mohammad Ali Jinnah University International Conference on Computing (MAJICC), pp. 1-6. IEEE, 2021.

M. Rizwan, L. Hong, M. Waseem, S. Ahmad, M. Sharaf, and M. Shafiq, " A robust adaptive overcurrent relay coordination scheme for wind-farm-integrated power systems based on forecasting the wind dynamics for smart energy systems," Applied Sciences, vol. 10 , no.18, p. 6318, 2020.

M. Waseem, Z. Lin, S. Liu, I. A. Sajjad, and T. Aziz, " Optimal GWCSO-based home appliances scheduling for demand response considering end-users comfort," Electric Power Systems Research, vol. 187, p. 106477, 2020.

M. M. Iqbal, I. Ali Sajjad, A. Manan, M. Waseem, A. Ali, and A. Sohail, "Towards an optimal residential home energy management in presence of pv generation, energy storage and home to grid energy exchange framework," 2020 IEEE 3rd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), Sukkur, Pakistan, Jan. 2020, pp. 1-7.

M. Waseem, Z. Lin, S. Liu, Z. Zhang, T. Aziz, and D. Khan, "Fuzzy compromised solution-based novel home appliances scheduling and demand response with optimal dispatch of distributed energy resources," Applied Energy, vol. 290, p. 116761, 2021.