Skip to main content
main-content

01.12.2018 | Research article | Ausgabe 1/2018 Open Access

BMC Medical Informatics and Decision Making 1/2018

Data to diagnosis in global health: a 3P approach

Zeitschrift:
BMC Medical Informatics and Decision Making > Ausgabe 1/2018
Autoren:
Rahul Krishnan Pathinarupothi, P. Durga, Ekanath Srihari Rangan
Wichtige Hinweise

Electronic supplementary material

The online version of this article (https://​doi.​org/​10.​1186/​s12911-018-0658-y) contains supplementary material, which is available to authorized users.

Abstract

Background

With connected medical devices fast becoming ubiquitous in healthcare monitoring there is a deluge of data coming from multiple body-attached sensors. Transforming this flood of data into effective and efficient diagnosis is a major challenge.

Methods

To address this challenge, we present a 3P approach: personalized patient monitoring, precision diagnostics, and preventive criticality alerts. In a collaborative work with doctors, we present the design, development, and testing of a healthcare data analytics and communication framework that we call RASPRO (Rapid Active Summarization for effective PROgnosis). The heart of RASPRO is Physician Assist Filters (PAF) that transform unwieldy multi-sensor time series data into summarized patient/disease specific trends in steps of progressive precision as demanded by the doctor for patient’s personalized condition at hand and help in identifying and subsequently predictively alerting the onset of critical conditions. The output of PAFs is a clinically useful, yet extremely succinct summary of a patient’s medical condition, represented as a motif, which could be sent to remote doctors even over SMS, reducing the need for data bandwidths. We evaluate the clinical validity of these techniques using SVM machine learning models measuring both the predictive power and its ability to classify disease condition. We used more than 16,000 min of patient data (N=70) from the openly available MIMIC II database for conducting these experiments. Furthermore, we also report the clinical utility of the system through doctor feedback from a large super-speciality hospital in India.

Results

The results show that the RASPRO motifs perform as well as (and in many cases better than) raw time series data. In addition, we also see improvement in diagnostic performance using optimized sensor severity threshold ranges set using the personalization PAF severity quantizer.

Conclusion

The RASPRO-PAF system and the associated techniques are found to be useful in many healthcare applications, especially in remote patient monitoring. The personalization, precision, and prevention PAFs presented in the paper successfully shows remarkable performance in satisfying the goals of 3Ps, thereby providing the advantages of three A’s: availability, affordability, and accessibility in the global health scenario.
Zusatzmaterial
Additional file 1 Moving Window OTS Vs. QTS. The figure shows the F1-score while using a moving window of size 30 mins with varying backward offset from t0. The results show that QTS is always better than OTS in classifying a given window as predictor for AHE or not. (PNG 28 kb)
12911_2018_658_MOESM1_ESM.png
Additional file 2 Moving Window QTS (B=5) Vs. MTS. The figure shows the F1-score comparison of QTS with B=5 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that MTS is better than QTS except in two time slots. (PNG 21 kb)
12911_2018_658_MOESM2_ESM.png
Additional file 3 Moving Window QTS (B=10) Vs. MTS. The figure shows the F1-score comparison of QTS with B=10 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that MTS is better than QTS except in two time slots, and also W=10 and W=15 are better summarization windows. (PNG 22 kb)
12911_2018_658_MOESM3_ESM.png
Additional file 4 Moving Window QTS (B=15) Vs. MTS. The figure shows the F1-score comparison of QTS with B=15 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that MTS is better than QTS except in two time slots, and also W=10 and W=15 are better summarization windows. (PNG 21 kb)
12911_2018_658_MOESM4_ESM.png
Additional file 5 Moving Window QTS (B=20) Vs. MTS. The figure shows the F1-score comparison of QTS with B=20 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that QTS is marginally better than MTS in four time slots. (PNG 22 kb)
12911_2018_658_MOESM5_ESM.png
Literatur
Über diesen Artikel

Weitere Artikel der Ausgabe 1/2018

BMC Medical Informatics and Decision Making 1/2018 Zur Ausgabe