Machine Learning and Deep Learning Approaches to Quantify Respiratory Distress Severity and Predict Critical Alarms

Rohit Pardasani, Rupanjali Chaudhuri, Navchetan Awasthi, Mansi Goel

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review


Respiratory distress (RD) is often the premonition and accompanying symptom of many critical conditions that may eventually lead to mortality among patients admitted in intensive care units (ICUs). The contemporary monitoring and alarm systems often fail to give timely and assertive alert of dangerously soaring RD, thus obscuring accurate prognosis. These systems do not capture the information provided by multiple parameters, which is important to predict and track patient health deterioration due to RD over time. Also, the repeated occurrence of false alarms in present systems leads to alarm fatigue. Our method addresses these issues by quantifying RD condition with a `Severity Index (SI)' based on trend and value of respiratory rate (RR) and peripheral capillary oxygen saturation (SpO2) for 24 hours segment in a streaming monitor arrangement. We work on 912 records extracted from MIMIC-III Clinical and Waveform Database. We mapped our task as a classification problem and explored multiple machine learning and deep learning models in order to propose the best solution. The trend and value features were used for classification to train logistic regression, decision tree, support vector machine and multi-layer perceptron for quantification of RD severity on segment. We also use convolutional neural network (CNN) and long-short term memory (LSTM) for segment classification since they have capability to capture the temporal pattern of RD. All the models gave AUC (Area Under Curve for Receiver Operating Characteristic (ROC)) either close to or above 0.90 for classification task. We later used these models for raising clinical alarm for RD. We conclude that CNN model is marginally better than other models if we aggregate performance on all metrics. We can trigger an alarm based on SI of RD as evaluated by our CNN model instead of contemporary threshold based alarms of RR and SpO2. This RD alarm gives sensitivity and specificity of 86% and 85% respectively and achieves an average lead time of 5.5 hours without contributing to alarm fatigue. The dataset, code, trained models and the GUI are available at
Original languageEnglish
Title of host publication2020 IEEE International Conference on Healthcare Informatics, ICHI 2020
Number of pages11
ISBN (Electronic)9781728153827
ISBN (Print)978-1-7281-5383-4
Publication statusPublished - Nov 2020
Event2020 IEEE International Conference on Healthcare Informatics (ICHI) - Oldenburg, Germany
Duration: 30 Nov 20203 Dec 2020


Conference2020 IEEE International Conference on Healthcare Informatics (ICHI)


  • Deep learning
  • Support vector machines
  • Sensitivity and specificity
  • Market research
  • Fatigue
  • Task analysis
  • Monitoring
  • peripheral capillary oxygen saturation (SpO )
  • alarm fatigue
  • severity index
  • machine learning
  • deep learning
  • Respiratory distress
  • respiratory rate (RR)
  • unexpected in-hospital death
  • clinical alarm


Dive into the research topics of 'Machine Learning and Deep Learning Approaches to Quantify Respiratory Distress Severity and Predict Critical Alarms'. Together they form a unique fingerprint.

Cite this