Limits...
Toward a Learning Health-care System - Knowledge Delivery at the Point of Care Empowered by Big Data and NLP.

Kaggal VC, Elayavilli RK, Mehrabi S, Pankratz JJ, Sohn S, Wang Y, Li D, Rastegar MM, Murphy SP, Ross JL, Chaudhry R, Buntrock JD, Liu H - Biomed Inform Insights (2016)

Bottom Line: Additionally, significant clinical information is embedded in the free text, making natural language processing (NLP) an essential component in implementing an LHS.We compared the advantages of big data over two other environments.Big data infrastructure significantly outperformed other infrastructure in terms of computing speed, demonstrating its value in making the LHS a possibility in the near future.

View Article: PubMed Central - PubMed

Affiliation: Division of Information Management and Analytics, Mayo Clinic, Rochester, MN, USA.; Biomedical Informatics and Computational Biology, University of Minnesota, Rochester, MN, USA.

ABSTRACT
The concept of optimizing health care by understanding and generating knowledge from previous evidence, ie, the Learning Health-care System (LHS), has gained momentum and now has national prominence. Meanwhile, the rapid adoption of electronic health records (EHRs) enables the data collection required to form the basis for facilitating LHS. A prerequisite for using EHR data within the LHS is an infrastructure that enables access to EHR data longitudinally for health-care analytics and real time for knowledge delivery. Additionally, significant clinical information is embedded in the free text, making natural language processing (NLP) an essential component in implementing an LHS. Herein, we share our institutional implementation of a big data-empowered clinical NLP infrastructure, which not only enables health-care analytics but also has real-time NLP processing capability. The infrastructure has been utilized for multiple institutional projects including the MayoExpertAdvisor, an individualized care recommendation solution for clinical care. We compared the advantages of big data over two other environments. Big data infrastructure significantly outperformed other infrastructure in terms of computing speed, demonstrating its value in making the LHS a possibility in the near future.

No MeSH data available.


Processing time using 16 threads on varying number of documents. As the number of documents processing doubles, the processing time increases almost linearly.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4920204&req=5

f8-bii-suppl.1-2016-013: Processing time using 16 threads on varying number of documents. As the number of documents processing doubles, the processing time increases almost linearly.

Mentions: We also studied the performance behavior of the big data with varying data size. We did this in order to ascertain the limits of gain in performance due to parallelism with increasing data. In Figure 7, we saw that for a fixed number of documents (20,000) the system achieved the best performance at 16 parallel instances. Keeping the parallel instance constant (at 16), we computed the time taken by the MEA algorithm to process 20,000 (335.08 MB of data), 40,000 (635.22 MB of data), 80,000 (1,270 MB of data), and 160,000 (2,792.99 MB of data) documents, essentially doubling the number of documents. Figure 8 shows the performance of the MEA algorithm while increasing the number of documents in big data. From Figure 8, we can infer that the processing time increases linearly with increasing number of documents. We can infer that further optimization of the number of parallel instances may be required with increasing amounts of data. At a fixed parallel instance (16 in this case), the performance of the MEA algorithm in big data may become a rate-limiting one. We believe that by adding additional nodes in big data infrastructure and increased parallelism of the Storm architecture the performance of MEA algorithm will ramp up to appreciable levels (as seen in Fig. 7).


Toward a Learning Health-care System - Knowledge Delivery at the Point of Care Empowered by Big Data and NLP.

Kaggal VC, Elayavilli RK, Mehrabi S, Pankratz JJ, Sohn S, Wang Y, Li D, Rastegar MM, Murphy SP, Ross JL, Chaudhry R, Buntrock JD, Liu H - Biomed Inform Insights (2016)

Processing time using 16 threads on varying number of documents. As the number of documents processing doubles, the processing time increases almost linearly.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4920204&req=5

f8-bii-suppl.1-2016-013: Processing time using 16 threads on varying number of documents. As the number of documents processing doubles, the processing time increases almost linearly.
Mentions: We also studied the performance behavior of the big data with varying data size. We did this in order to ascertain the limits of gain in performance due to parallelism with increasing data. In Figure 7, we saw that for a fixed number of documents (20,000) the system achieved the best performance at 16 parallel instances. Keeping the parallel instance constant (at 16), we computed the time taken by the MEA algorithm to process 20,000 (335.08 MB of data), 40,000 (635.22 MB of data), 80,000 (1,270 MB of data), and 160,000 (2,792.99 MB of data) documents, essentially doubling the number of documents. Figure 8 shows the performance of the MEA algorithm while increasing the number of documents in big data. From Figure 8, we can infer that the processing time increases linearly with increasing number of documents. We can infer that further optimization of the number of parallel instances may be required with increasing amounts of data. At a fixed parallel instance (16 in this case), the performance of the MEA algorithm in big data may become a rate-limiting one. We believe that by adding additional nodes in big data infrastructure and increased parallelism of the Storm architecture the performance of MEA algorithm will ramp up to appreciable levels (as seen in Fig. 7).

Bottom Line: Additionally, significant clinical information is embedded in the free text, making natural language processing (NLP) an essential component in implementing an LHS.We compared the advantages of big data over two other environments.Big data infrastructure significantly outperformed other infrastructure in terms of computing speed, demonstrating its value in making the LHS a possibility in the near future.

View Article: PubMed Central - PubMed

Affiliation: Division of Information Management and Analytics, Mayo Clinic, Rochester, MN, USA.; Biomedical Informatics and Computational Biology, University of Minnesota, Rochester, MN, USA.

ABSTRACT
The concept of optimizing health care by understanding and generating knowledge from previous evidence, ie, the Learning Health-care System (LHS), has gained momentum and now has national prominence. Meanwhile, the rapid adoption of electronic health records (EHRs) enables the data collection required to form the basis for facilitating LHS. A prerequisite for using EHR data within the LHS is an infrastructure that enables access to EHR data longitudinally for health-care analytics and real time for knowledge delivery. Additionally, significant clinical information is embedded in the free text, making natural language processing (NLP) an essential component in implementing an LHS. Herein, we share our institutional implementation of a big data-empowered clinical NLP infrastructure, which not only enables health-care analytics but also has real-time NLP processing capability. The infrastructure has been utilized for multiple institutional projects including the MayoExpertAdvisor, an individualized care recommendation solution for clinical care. We compared the advantages of big data over two other environments. Big data infrastructure significantly outperformed other infrastructure in terms of computing speed, demonstrating its value in making the LHS a possibility in the near future.

No MeSH data available.