AIDEx - An Open-source Platform for Real-Time Forecasting Sepsis and A Case Study on Taking ML Algorithms to Production

Amrollahi, Fatemeh; Shashikumar, Supreeth P.; Kathiravelu, Pradeeban; Sharma, Ashish; Nemati, Shamim

doi:10.1109/embc44109.2020.9175947

Cited by 12 publications

(18 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A significant proportion of included studies focused on the development of CDS for genomics lab result interpretation (n=7). Similarly, the analysis of risk factors was an important focus of work (n=6), including work on sepsis risk [ 23 24 ], familial cancers [ 25 ], drug-gene interactions [ 14 ], and CHA2DS2-VASc scores [ 26 ]. Tools intended to assist clinicians or patients by monitoring particular health metrics, whether for inpatient or outpatient care, constituted a fifth category (n=5).…”

Section: Resultsmentioning

confidence: 99%

“…Condition Management and Treatment (n=15) [12,27,28,30,31,35,36,42,44,45,50,53,54,56,58] CDS Infrastructure (n=7) [15,33,40,41,52,60,63] Lab Result Interpretation --Genomics (n=7) [29,32,46,48,49,58,59] Risk Factor Analysis (n=6) [14,[23][24][25][26]39] Health Metric Monitoring (n=5) [34,37,43,51,61] Lab Result Interpretation --Other (n=3) [38,57,62] HIV Screening (n=1) [55] FHIR n (%) Standards was observational (n=8; 67%), with three studies (25%) reporting CDS needs evaluations. We identified only two studies with randomized components reporting on the use of any of the standards of interest (Curran et al [27] and Kawamoto et al [28]).…”

Section: Topicmentioning

confidence: 99%

See 1 more Smart Citation

New Standards for Clinical Decision Support: A Survey of The State of Implementation

et al. 2021

View full text Add to dashboard Cite

Summary Objectives: To review the current state of research on designing and implementing clinical decision support (CDS) using four current interoperability standards: Fast Healthcare Interoperability Resources (FHIR); Substitutable Medical Applications and Reusable Technologies (SMART); Clinical Quality Language (CQL); and CDS Hooks. Methods: We conducted a review of original studies describing development of specific CDS tools or infrastructures using one of the four targeted standards, regardless of implementation stage. Citations published any time before the literature search was executed on October 21, 2020 were retrieved from PubMed. Two reviewers independently screened articles and abstracted data according to a protocol designed by team consensus. Results: Of 290 articles identified via PubMed search, 44 were included in this study. More than three quarters were published since 2018. Forty-three (98%) used FHIR; 22 (50%) used SMART; two (5%) used CQL; and eight (18%) used CDS Hooks. Twenty-four (55%) were in the design stage, 15 (34%) in the piloting stage, and five (11%) were deployed in a real-world setting. Only 12 (27%) of the articles reported an evaluation of the technology under development. Three of the four articles describing a deployed technology reported an evaluation. Only two evaluations with randomized study components were identified. Conclusion: The diversity of topics and approaches identified in the literature highlights the utility of these standards. The infrequency of reported evaluations, as well as the high number of studies in the design or piloting stage, indicate that these technologies are still early in their life cycles. Informaticists will require a stronger evidence base to understand the implications of using these standards in CDS design and implementation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Topicmentioning

confidence: 99%

New Standards for Clinical Decision Support: A Survey of The State of Implementation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The proposed algorithm provides a foundational building block for the design of future generalizable and trustworthy prediction tools potentially useful in other clinical syndromes and disease processes. A real-time HL7 FHIR 45,46 compatible software pipeline has been developed to enable interoperable multi-center deployment of this algorithm (See Supplementary Note 10 for more details). Future work includes performing prospective clinical trials to validate COMPO-SER's predictions in a real-time clinical setting.…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence sepsis prediction algorithm learns to say “I don’t know”

et al. 2021

Self Cite

View full text Add to dashboard Cite

Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as indeterminate rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925–0.953; ED: 0.938–0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as indeterminate amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.

show abstract

“…A real-time HL7 FHIR 29,30 compatible software pipeline has been developed to enable interoperable multi-center deployment of this algorithm (See Appendix H of Supplementary Material for more details). Future work includes performing prospective clinical trials to validate COMPOSER's predictions in a real-time clinical setting.…”

Section: Analysis Of Missed-detectionsmentioning

confidence: 99%

“…The proposed algorithm provides a foundational building block for the design of future generalizable and trustworthy prediction tools potentially useful in other clinical syndromes and disease processes. A real-time HL7 FHIR 29,30 compatible software pipeline has been developed to enable interoperable multi-center deployment of this algorithm (See Appendix H of Supplementary Material for more details). Future work includes performing prospective clinical trials to validate COMPOSER’s predictions in a real-time clinical setting.…”

Section: Analysis Of Missed-detectionsmentioning

confidence: 99%

Artificial Intelligence Sepsis Prediction Algorithm Learns to Say “I don’t know”

Shashikumar

Wardi

Malhotra

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as 'indeterminate' rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925-0.953; ED: 0.938-0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as 'indeterminate' amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.

show abstract

AIDEx - An Open-source Platform for Real-Time Forecasting Sepsis and A Case Study on Taking ML Algorithms to Production

Cited by 12 publications

References 17 publications

New Standards for Clinical Decision Support: A Survey of The State of Implementation

New Standards for Clinical Decision Support: A Survey of The State of Implementation

Artificial intelligence sepsis prediction algorithm learns to say “I don’t know”

Artificial Intelligence Sepsis Prediction Algorithm Learns to Say “I don’t know”

Contact Info

Product

Resources

About