Early Prediction of Sepsis from Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019

Citations

To refer to the 2019 Challenge, please cite:

Reyna MA, Josef CS, Jeter R, Shashikumar SP, Westover MB, Nemati S, Clifford GD, Sharma A. Early Prediction of Sepsis From Clinical Data: The PhysioNet/Computing in Cardiology Challenge. Critical Care Medicine 48 2: 210-217 (2019). https://doi.org/10.1097/CCM.0000000000004145

Reyna MA, Josef CS, Seyedi S, Jeter R, Shashikumar S, Westover MB, Sharma A, Nemati S, Clifford GD, “Early Prediction of Sepsis from Clinical Data: the PhysioNet/Computing in Cardiology Challenge 2019,” 2019 Computing in Cardiology (CinC), 2019, pp. 1- 4, doi: 10.23919/CinC49843.2019.9005736.

Challenge results

The conference papers for Computing in Cardiology 2019 are available on the CinC and IEEE websites.

The ranks of the teams and their papers and entry code are available in the table below.

Rank Team Name Team Member(s) Code Conference Paper Journal Paper
1 Can I get your signature? James Morrill, Andrey Kormilitzin, Alejo Nevado-Holgado, Sumanth Swaminathan, Sam Howison, Terry Lyons Link (13.5 MB) The Signature-Based Model for Early Detection of Sepsis from Electronic Health Records in the Intensive Care Unit Utilization of the Signature Method to Identify the Early Onset of Sepsis From Multivariate Physiological Time Series in Critical Care Monitoring
2 Sepsyd John Anda Du, Nadi Sadr, Philip de Chazal Link (0.2 MB) Automated Prediction of Sepsis Onset Using Gradient Boosted Decision Trees  
3 Separatrix Morteza Zabihi, Serkan Kiranyaz, Moncef Gabbouj Link (3 MB) Sepsis Prediction in Intensive Care Unit Using Ensemble of XGboost Models  
4 FlyingBubble Xiang Li, Yanni Kang, Xiaoyu Jia, Junmei Wang, Guotong Xie Link (8.2 MB) TASP: A Time-Phased Model for Sepsis Prediction A Time-Phased Machine Learning Model for Real-Time Prediction of Sepsis in Critical Care
5 CTL-Team Janmajay Singh, Kentaro Oshiro, Raghava Krishnan, Masahiro Sato, Tomoko Ohkuma, Noriji Kato Link (0.8 MB) Utilizing Informative Missingness for Early Prediction of Sepsis  
6 SBU Ibrahim Hammoud, IV Ramakrishnan, Mark Henry Link (0.7 MB) Early Prediction of Sepsis Using Gradient Boosting Decision Trees with Optimal Sample Weighting  
7 Ping An Health Technology Xiang Li, Yanni Kang, Xiaoyu Jia, Junmei Wang, Guotong Xie Link (1.5 MB)    
8 prna Yale Chang, Jonathan Rubin, Gregory Boverman, Shruti Vij, Asif Rahman, Annamalai Natarajan, Saman Parvaneh Link (9.2 MB) A Multi-Task Imputation and Classification Neural Architecture for Early Prediction of Sepsis from Multivariate Clinical Time Series  
9 Antanas Kascenas Antanas Kascenas, Alison O’Neil Link (7 MB)    
10 NN-MIH Naoki Nonaka, Jun Seita Link (0.9 MB) Demographic Information Initialized Stacked Gated Recurrent Unit for an Early Prediction of Sepsis  
11 RadAsadi Sepideh Rezaeirad, Atefeh Baniasadi, Mohammad Ghassemi, Habil Zare Link (0.03 MB)   Two-Step Imputation and AdaBoost-Based Classification for Early Prediction of Sepsis on Imbalanced Clinical Data
12 SFAA Sajad Mousavi Link (0.1 MB)    
13 PKU_DLIB Luchen Liu, Haoxian Wu, Zichang Wang, Zequn Liu, Ming Zhang Link (0.6 MB) Early Prediction of Sepsis From Clinical Data via Heterogeneous Event Aggregation  
14 SOS: Searching for Sepsis Ben Sweely, Austin Park, Lia Winter, Longjian Liu, Xiaopeng Zhao Link (1 MB) Time-Padded Random Forest Ensemble to Capture Changes in Physiology Leading to Sepsis Development  
15 CQUPT_Just_Try Yongchao Wang, Bin Xiao, Xiuli Bi, Weisheng Li, Junhui Zhang, Xu Ma Link (17.6 MB) Prediction of Sepsis from Clinical Data Using Long Short-Term Memory and eXtreme Gradient Boosting  
16 UCAS_DataMiner Zhengling He, Xianxiang Chen, Zhen Fang, Chenshuo Wang, Li Jiang, Zhongkai Tong, Zhongrui Bai, Yichen Pan, Yueqi Li Link (23.1 MB) Early Sepsis Prediction Using Ensemble Learning with Features Extracted from LSTM Recurrent Neural Network Early Sepsis Prediction Using Ensemble Learning With Deep Features and Artificial Features Extracted From Clinical Electronic Health Records
17 IADI Benjamin Roussel, Julien Oster Link (8.6 MB) A Recurrent Neural Network for the Prediction of Vital Sign Evolution and Sepsis in ICU  
18 Shivpatidar Shivnarayan Patidar Link (1.5 MB) Diagnosis of Sepsis Using Ratio Based Features Early Prediction of Sepsis From Clinical Data Using Ratio and Power-Based Features
19 R&Hope Lu Meng Link (6.1 MB)    
20 UVA CAMA Douglas Lake Link (0.01 MB)    
21 The Septic Think Tank Simon Lyra, Steffen Leonhardt, Christoph Hoog Antink Link (1 MB) Early Prediction of Sepsis Using Random Forest Classification for Imbalanced Clinical Data  
22 vn Byeong Tak Lee, KyungJae Cho, Oyeon Kwon, Yeha Lee Link (46.2MB) Improving the Performance of a Neural Network for Early Prediction of Sepsis Graph Convolutional Networks-Based Noisy Data Imputation in Electronic Health Record
23 404: Sepsis not found Sven Schellenberger, Kilin Shi, Jan Philipp Wiedemann, Fabian Lurz, Robert Weigel, Alexander Koelpin Link (86.4 MB) An Ensemble LSTM Architecture for Clinical Sepsis Detection  
24 Infolab USC Luan Tran, Cyrus Shahabi, Manh Nguyen Link (57.4 MB) Representation Learning for Early Sepsis Prediction  
25 njuedu Qiang Yu, Xiaolin Huang, Cheng Wang, Qiyuan Wang, Yi Zhang, Yuqi Zhang Link (164.3 MB) Using Features Extracted from Vital Time Series for Early Prediction of Sepsis  
26 ECGuru10 Tomas Vicar, Jakub Hejc, Petra Novotna, Marina Ronzhina, Radovan Smisek Link (46.5 MB) Sepsis Detection in Sparse Clinical Data Using Long Short-Term Memory Network with Dice Loss  
27 ISIBrno Nejedly Petr, Plesinger Filip, Viscor Ivo, Halamek Josef, Jurak Pavel Link (0.7 MB) Prediction of Sepsis Using LSTM with Hyperparameter Optimization with a Genetic Algorithm  
28 QLab Congmin Xu, Peng Qiu, Kuang Chen Link (2 MB) Early Prediction of Sepsis Using LSTM  
29 UHN_rand_num_generator Osvald Nitski, Yuchen Wang, Augustin Toma, Bo Wang Link (0.4 MB)    
30 SepsisFinder Chloé Pou-Prom, Zhen Yang, Maitreyee Sidhaye, David Dai Link (63.3MB) Development of a Sepsis Early Warning Indicator  
31 Terminator_CUET Fahim Mahmud, Naqib Sad Pathan Link (.5 MB)    
32 Doctor Who Michael Moor, Max Horn Link (8 MB)    
33 AI4Sepsis Anamika Paul Rupa, Al Amin, Sanjay Purushotham Link (67.1 MB) Benchmark of Machine Learning Models for Early Sepsis Prediction  
34 BRIC_LB Mohammed Baydoun, Lise Safatly, Hassan Ghaziri, Ali ElHajj Link (42.9 MB) Convolutional Neural Networks Based Model to Provide Early Prediction of Sepsis from Clinical Data  
35 UBC - DHIL Roshan Pawar, Jeffrey Bone, Mark Ansermino, Matthias Görges Link (0.2 MB) An Algorithm for Early Detection of Sepsis Using Traditional Statistical Regression Modeling  
36 ABC Zhaowei Zhu, Zhuoyang Xu, Tingting Zhao Link (8.6 MB) Extreme Gradient Boosting Method for Early Detection of Sepsis  
37 ESL Dionisije Sopic, Tomas Teijeiro, Amir Aminifar, David Atienza Link (10 MB) A Real-Time Technique for Early Prediction of Sepsis Using Wearable Devices  
38 WIN-UAB Edwar Macias, Guillem Boquet, Javier Serrano, Jose Lopez Vicario, Jose Ibeas, Antoni Morell Link (0.6 MB) Novel Imputing Method for the Early Prediction of Sepsis in ICU Using Deep Learning Techniques  
39 AlgTeam Reza Firoozabadi, Saeed Babaeizadeh Link (31.6MB) An Ensemble of Bagged Decision Trees for Early Prediction of Sepsis  
40 Leicester Fox Xin Li, G Andre Ng, Fernando Schlindwein Link (8.2 MB) Convolutional and Recurrent Neural Networks for Early Detection of Sepsis using Hourly Physiological Data from Patients in Intensive Care Unit  
41 ywangda Wang Yiwen Link (7.4 MB) A Large Margin Deep Neural Network for Sepsis Classification  
42 pqlab Yuhan Zhou Link (14.3 MB)    
43 USF-Sepsis-Phys Soodabeh Sarafrazi, Chiral Mehta, Rohini Choudhari, Himanshi Mehta, Patricia Francis-Lyon Link (0.2 MB) Cracking the “Sepsis” Code: Assessing Time Series Nature of EHR Data, and Using Deep Learning for Early Sepsis Prediction  
44 UM Antiseptic Sardar Ansari Link (0.05 MB)    
45 AvivInnovation Tzvika Aviv Link (4.6 MB)    
46 The memristive agents Vasileios Athanasiou, Zoran Konkoli Link (0.2 MB) Memristor Models for Early Detection of Sepsis in ICU Patients  
47 OneMoreSecond Kai Wang, Lei Zuo, Yanxuan Li Link (3 MB) Sample-and-hold/mean Imputation and XGBoost for Sepsis Prediction  
48 Team_Tesseract Shailesh Nirgudkar, Tianyu Ding Link (104 MB) Early Detection of Sepsis Using Ensemblers  
49 AI-Neuroimmune Kaveh Samiee Link (3.1 MB) Prediction of Sepsis in Intensive Care Unit Using Electronic Medical Records and Convolutional Bidirectional Recurrent Neural Networks  
50 IMSAT Saman Noorzadeh, Shahrooz FaghihRoohi, Mojtaba Zarei Link (0.2MB) A Comparative Analysis of HMM and CRF for Early Prediction of Sepsis  
51 PLUX Miquel Alfaras, Rui Varandas, Hugo Gamboa Link (0.3MB) Ring-Topology Echo State Networks for ICU Sepsis Classification  
52 LDBR Lakshman Narayanaswamy, Devendra Garg, Bhargavi Narra, Ramkumar Narayanswamy Link (0.6 MB) Machine Learning Algorithmic and System Level Considerations for Early Prediction of Sepsis  
53 Kriss Ines Krissaane, Kingsley Hampton, Jumanah Alshenaifi, Richard Wilkinson Link (0.6 MB) Anomaly Detection Semi-supervised Framework for Sepsis Treatment  
54 PhysioNet Example PhysioNet Team Link (0.3 MB) Early Prediction of Sepsis from Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019  
55 CIS2216 Shenda Hong, Junyuan Shang, Meng Wu, Yuxi Zhou, Yongyue Sun, Yen Hsiu Chou, Moxian Song, Hongyan Li Link (0.4 MB) Early Sepsis Prediction with Deep Recurrent Reinforcement Learning  
56 anni Annie Zheng Link (5 MB)    
57 Tricog Manmay Nakhashi, Anoop Toffy, Achuth PV, Lingaselvan Palanichamy, Vikas C M Link (0.3 MB) Early Prediction of Sepsis: Using State-of-the-art Machine Learning Techniques on Vital Sign Inputs  
58 USST Wenjie Cai, Danqin Hu, Shuaicong Hu Link (30.1 MB)    
59 ARUL Induparkavi Murugesan, Karthikeyan Murugesan, Lingeshwaran Balasubramanian, Malathi Murugesan Link (0.4 MB) Interpretation of Artificial Intelligence Algorithms in the Prediction of Sepsis  
60 TU Dresden - IBMT Matthieu Scherpf, Miriam Goldammer, Hagen Malberg, Felix Gräßer Link (1.5 MB) Sepsis Onset Prediction Applying a Stacked Combination of a Recurrent Neural Network and a Gradient Boosted Machine  
61 Sepsis ReSepsion Po-Ya Hsu, Chester Holtz Link (36.8 MB) A Comparison of Machine Learning Tools for Early Prediction of Sepsis from ICU Data  
62 Purdue University Aaron Althoff Link (7.3 MB)    
63 Amini-Univ-Tehran Morteza Amini Link (0.01 MB) Early Prediction of Sepsis from Clinical Data Using a Specialized Hidden Markov Model  
64 Py Parivash FahamAzad, Ruhallah Amandi, Mohammad Farhadi Link (40 MB)    
65 Whitaker’s Warriors Erik Gilbertson, Khristian Jones, Abigail Strohl, Bradley Whitaker Link (54.2 MB) Early Detection of Sepsis Using Feature Selection, Feature Extraction, and Neural Network Classification  
66 VGTU Vytautas Abromavicius, Artūras Serackis Link (23.3 MB) Sepsis Prediction Model Based on Vital Signs Related Features  
67 RoBusto Diogo Nunes Link (55.4 MB) Trend and Filtered State Extraction through Savitzky-Golay Filtering for the Early Detection of Sepsis Events  
68 SHODH Aruna Deogire Link (0.4 MB) A Low Dimensional Algorithm for Detection of Sepsis from Electronic Medical Record Data  
69 UND_BERCLAB Soufiane Chami, Guragain Bijay, Hoffmann Bradley, Majumder Shubha, Naima Kaabouche, Kouhyar Tavakolian Link (0.3 MB) Early Prediction of Sepsis From Clinical Data Using Single Light-GBM Model  
70 Sepsis’ debugger Aya Tello, Yazan Shikhani Link (16.5 MB)    
71 claguet Clementine Aguet, Jérôme Van Zaen, Mathieu Lemay Link (0.6 MB) Sepsis Detection Using Missingness Information  
71 CRASHers Marco AF Pimentel, Adam Mahdi, Oliver Redfern, Mauro Santos Link (22.3 MB) Uncertainty-Aware Model for Reliable Prediction of Sepsis in the ICU  
71 PIPI Xiaofeng Tang Link (76.4 MB)    
74 ScuDicaLab Yao Chen, Jiancheng Lv Link (0.1 MB) Contextual LSTM (CLSTM) Models for Early Prediction of Sepsis  
75 cinc_sepsis_pass Mengsha Fu, Jiabin Yuan, Menglin Lu, Pengfei Hong, Mei Zeng Link (0.1 MB) An Ensemble Machine Learning Model for the Early Detection of Sepsis from Clinical Data  
76 CH Kucharski D, Pabian M, Rzepka D Link (25.6 MB)    
77 Kent Ridge AI Shiyu Liu, Ming Lun Ong, Kar Kin Mun, Jia Yao, Mehul Motani Link (2.2 MB) Early Prediction of Sepsis via SMOTE Upsampling and Mutual Information based Downsampling  
78 The Sepsis Detectives Akram Mohammed, Franco van Wyk, Anahita Khojandi, Rishikesan Kamaleswaran Link (0.8 MB) When to Start Sepsis Bundle? A Machine Learning Approach to Earlier Detection Using Electronic Medical Records  
x A_UNSW_Sepsis Unknown      
x Bolloknoon Institute Unknown      
x B-Secur Peter Doggart, Megan Rutherford Link (0.2 MB) Randomly under Sampled Boosted Tree for Predicting Sepsis from Intensive Care Unit Databases  
* CIBIM Oliver Carr, Stefan Bostock, Nicolas Basty, John Prince, Kirubin Pillay, Navin Cooray, Maarten De Vos Link (1.6 MB) Novelty Detection for the Early Prediction of Sepsis  
x Main Lab Unknown      
x MELAB Unknown      
x NCHC-Physionet Tim Huang      
* Rx-LR Edward Ho, Cathy Ong-Ly, Alex Zhou Link (7.8 MB) Developing an Interpretable Predictive Model for Early Diagnosis of Sepsis Using Automatic Feature Extraction  
* SailOcean Meicheng Yang, Hongxiang Gao, Xingyao Wang, Yuwen Li, Jianqing Li, Chengyu Liu Link (0.7 MB) Early Prediction of Sepsis Using Multi-Feature Fusion Based XGBoost Learning and Bayesian Optimization. An Explainable Artificial Intelligence Predictor for Early Detection of Sepsis
x Sepsis_2G Marcus Vollmer, Christian F. Luz, Philipp Sodmann, Bhanu Sinha, Sven-Olaf Kuhn Link (0.2 MB) Time-specific Metalearners for the Early Prediction of Sepsis  
? s(k)eptic Tanuka Bhattacharjee, Sakyajit Bhattacharya, Varsha Sharma, Anirban Dutta Choudhury, Sunil Kumar Kopparapu, Rupayan Chakraborty, Upasana Tiwari, Murali Poduval, Sundeep Khandelwal, Kayapanda Muthana Mandana Link (31.3 MB) Early Sepsis Prediction by Cascaded Classification of Multi-Modal Clinical Parameters  
x SUN Yanbo Xu, Siddharth Biswal, Rahul Duggal, Yu Jing, Jimeng Sun   Hand Crafted Features and an LSTM for Predicting Sepsis  
x thb100 Unknown      
x The Way Code Should Be Clare Bates Congdon   A Naïve Neural-Net Approach to Prediction of Sepsis with Time-Series Data  
* UAlberta Humza Haider Link (7.7 MB)    
? UCAS_BigBird Unknown Link (0.2 MB)    
? ucas-star Unknown Link (0.02 MB)    
x UlsterTeam Pardis Biglarbeigi, Donal McLaughlin, Khaleed Rjoob, Abdullah Abdullah, Niamh McCallan, Alicja Jasinska-Piadlo, Raymond Bond, Dewar Finlay, Mark Kok Yew Ng, Alan Kennedy, James McLaughlin Link (0.2 MB) Early prediction of sepsis considering Early Warning Scoring systems  
? WML Unknown Link (5.6 MB)    
? XLS-IMECAS Unknown Link (9.2 MB)    
* Yuanfang Guan Yuanfang Guan Link (5.9 MB)    
# obama Unknown      
# PATH Unknown      
# smile Unknown      
# snow Unknown      
# strawc Unknown      

(*) Failed to satisfy all conditions of competition.

(x) Failed to submit successful entry.

(?) Did not identify team members.

(#) Disqualified for submitting code substantially similar to another team .

Hakathon results

The ranks of the teams in hakathon are available in the table below.

Rank Team name Team members
1 SailOcean Meicheng Yang, Hongxiang Gao, Xingyao Wang, Yuwen Li, Xing Liu, Jianqing Li, Chengyu Liu
2 prna Jonathan Rubin, Yale Chang, Saman Parvaneh, Gregory Boverman
3 Sepsyd John Anda Du, Miquel Alfaras, Naoki Nonaka, Inès Krissaane, Edwar Hernando Macias Toro, Matthieu Scherpf
4 TAG Xiaopeng Zhao, Simon Lyra, Marcus Vollmer, Christoph Hoog Antink
5 vn ByeongTak Lee, KyungJae Cho, Oyeon Kwon
6 cinc_sepsis_pass Mengsha Fu
7 Ulster University Pardis Biglarbeigi, Donal McLaughlin, Khaled Rjoob, Abdullah Abdullah, Niamh McCallan, Alicja Jasinska-Piadlo, Raymond Bond, Dewar Finlay, Kok Yew Ng, Alan Kennedy, Jim McLaughlin
8 CRASHers Marco AF Pimentel, Adam Mahdi, Oliver Redfern, Mauro Santos
x ARUL Induparkavi Murugesan, Lingeshwaran Balasubramanian, Malathi Murugesan

(x) Failed to submit successful entry.


Supported by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) under NIH grant number R01EB030362.

Back