Skip to main content

Advertisement

SpringerLink
Log in

Automatic Home Medical Product Recommendation

  • Original Paper
  • Published:
Journal of Medical Systems Aims and scope Submit manuscript

Abstract

Web-based personal health records (PHRs) are being widely deployed. To improve PHR’s capability and usability, we proposed the concept of intelligent PHR (iPHR). In this paper, we use automatic home medical product recommendation as a concrete application to demonstrate the benefits of introducing intelligence into PHRs. In this new application domain, we develop several techniques to address the emerging challenges. Our approach uses treatment knowledge and nursing knowledge, and extends the language modeling method to (1) construct a topic-selection input interface for recommending home medical products, (2) produce a global ranking of Web pages retrieved by multiple queries, and (3) provide diverse search results. We demonstrate the effectiveness of our techniques using USMLE medical exam cases.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Luo, G., Thomas, S. B., and Tang, C., Intelligent consumer-centric electronic medical record. Proceedings of MIE’09, pp. 120–124, 2009.

  2. U.S. market for home care products, 5th ed. Kalorama Information, 2007.

  3. Luo, G., Design and evaluation of the iMed intelligent medical search engine. Proceedings of ICDE’09, pp. 1379–1390, 2009.

  4. Fang, H., Tao, T., and Zhai, C., A formal study of information retrieval heuristics. Proceedings of SIGIR’04, pp. 49–56, 2004.

  5. Ponte, J. M., and Croft, B. W., A language modeling approach to information retrieval. Proceedings of SIGIR’98, pp. 275–281, 1998.

  6. Le, T., and Bhushan, V., First aid for the USMLE step 2 CS (clinical skills exam). McGraw-Hill, 2006.

  7. AllegroMedical homepage. http://www.allegromedical.com, 2009.

  8. Luo, G., and Tang, C., Automatic home nursing activity recommendation. Proceedings of AMIA’09, pp. 401–405, 2009.

  9. Johnson, M., Bulechek, G. M., and Dochterman, J. M., et al., NANDA, NOC, and NIC linkages: nursing diagnoses, outcomes, and interventions, 2nd ed. Mosby, 2005.

  10. Ackley, B. J., and Ladwig, G. B., Nursing diagnosis handbook: an evidence-based guide to planning care, 8th ed. Mosby, 2007.

  11. Bulechek, G. M., Butcher, H. K., and Dochterman, J. M., Nursing interventions classification (NIC), 5th ed. Mosby, 2007.

  12. Healthline diseases & conditions A to Z directory. http://www.healthline.com/directory/diseases-and-conditions, 2009.

  13. Medical symptom descriptions. http://www.wrongdiagnosis.com/lists/symptom.htm, 2009.

  14. Luo, G., Intelligent output interface for intelligent medical search engine. Proceedings of AAAI’08, pp. 1201–1206, 2008.

  15. WebMD homepage. http://www.webmd.com, 2009.

  16. Manning, C. D., Raghavan, P., and Schutze, H., Introduction to information retrieval. Cambridge University Press, 2008.

  17. Kushmerick, N., Weld, D. S., and Doorenbos, R. B., Wrapper induction for information extraction. IJCAI (1):729–737, 1997.

  18. Zhai, C., and Lafferty, J. D., A study of smoothing methods for language models applied to ad hoc information retrieval. Proceedings of SIGIR’01, pp. 334–342, 2001.

  19. Luo, G., Tang, C., and Yang, H., et al., MedSearch: a specialized search engine for medical information retrieval. Proceedings of CIKM’08, pp. 143–152, 2008.

  20. Carbonell, J. G., and Goldstein, J., The use of MMR, diversity-based reranking for reordering documents and producing summaries. Proceedings of SIGIR’98, pp. 335–336, 1998.

  21. TREC interactive track homepage. http://trec.nist.gov/data/interactive.html, 2009.

  22. Hidola homepage. http://www.hidola.com, 2010.

  23. Yang, K., Evens, M. W., and Trace, D., Improving the text summaries in the intelligent medical record system. Proceedings of MAICS’06, 2006.

  24. Google product search homepage. http://www.google.com/products, 2009.

  25. Teevan, J., Dumais, S. T., and Liebling, D. J., To personalize or not to personalize: modeling queries with variation in user intent. Proceedings of SIGIR’08, pp. 163–170, 2008.

  26. Baeza-Yates, R. A., and Ribeiro-Neto, B. A., Modern information retrieval. ACM Press/Addison-Wesley, 1999.

  27. Vogeli, C., Shields, A. E., Lee, T. A., et al., Multiple chronic conditions: prevalence, health consequences, and implications for quality, care management, and costs. JGIM 22(Suppl 3):391–395, 2007.

    Article  Google Scholar 

  28. Meyer, M. M., and Derr, P., The comfort of home: a complete guide for caregivers, 3rd ed. CareTrust Publications LLC, 2007.

  29. RxList - the Internet drug index homepage. http://www.rxlist.com, 2009.

  30. Cimino, J. J., Use, usability, usefulness and impact of an Infobutton manager. Proceedings of AMIA’06, pp. 151–155, 2006.

  31. Farfan, F., Hristidis, V., Ranganathan, A., and Weiner, M., XOntoRank: Ontology-aware search of electronic medical records. Proceedings of ICDE’09, pp. 820–831, 2009.

  32. Bickel, P. J., and Doksum, K. A., Mathematical statistics: basic ideas and selected topics, Vol. 1. Prentice Hall, 2001.

Download references

Acknowledgment

We thank Annemarie Credentino, Jiuxing Liu, Ying-li Tian, Jing Wang, and Debra J. Zeitlin for helpful discussions.

Author information

Authors and Affiliations

  1. IBM T.J. Watson Research Center, 19 Skyline Drive, Hawthorne, NY, 10532, USA

    Gang Luo, Selena B. Thomas & Chunqiang Tang

Authors
  1. Gang Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Selena B. Thomas
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chunqiang Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gang Luo.

List of symbols

List of symbols

A, A1, A2 :

nursing activity or HNA

A v :

virtual HNA

c :

medical condition or healthcare need

C :

the collection of crawled Web pages

|C|:

the length of the document collection C in the number of terms

C A :

the essential content of the HNA A

c(A, P):

the number of HNA A’s occurrences in the Web page P

c(q, C):

query term q’s frequency in the document collection C

c(q, D o ):

query term q’s frequency in the document D o

d :

disease

D, D1, D2 :

nursing diagnosis

D o :

document

|D o |:

the length of the document D o in the number of terms

D v :

virtual nursing diagnosis

d_score P :

diversity score for the Web page P

f :

phrase

G :

the complete set of search guide information for all topics in L t , the list of topics of concern by the user

G T :

search guide information of the topic T

I :

I1, I2, nursing intervention

I i :

inverted index

I v :

virtual nursing intervention

K b :

knowledge base

L acute :

list of current acute diseases of the user

L chronic :

list of chronic diseases of the user

L c_care :

list of additional medical conditions and healthcare needs selected and entered by the user

L c_current :

list of current medical conditions of the user

L d_care :

list of diseases selected and entered by the user

L d_current :

list of current diseases of the user

L s_care :

list of symptoms selected and entered by the user

L s_possible :

list of symptoms displayed on the symptom Web page

L t :

list of topics of concern by the user

M, M1, M2 :

medical condition

N :

a constant to control the amount of time spent on search result diversification

N a :

the total number of distinct HNAs appearing in the collection C of crawled Web pages

n a (P):

the length of the Web page P measured in the HNA semantic unit

n_w A :

normalized weight of the nursing activity A

n_w D :

normalized weight of the nursing diagnosis D

n_w I :

normalized weight of the nursing intervention I

n_w M :

normalized weight of the medical condition M

n_w T :

normalized weight of the topic T

O T :

the search guide information compiled for the topic T from sources other than nursing knowledge

p :

HMP

P, P’, P1, P2 :

Web page

|P|:

the length of the Web page P in the number of terms

P l_d :

the Web page in S remaining with the largest diversity score

q :

query term

Q :

query

Q c :

conceptual query representing the user’s need

r :

the uniform rate at which HNAs occur in all Web pages

R all :

the complete set of retrieved HMP Web pages

R M :

the medical condition M’s search guide information compiled using nursing knowledge

s :

symptom

s A :

HNA weight discount factor

S A :

the set of phrases pre-compiled for the HNA A

score P :

the page P’s relevance score

S d_p :

the set of phrases pre-compiled for the disease d

s D :

nursing diagnosis weight discount factor

S D :

the set of nursing interventions linked to the nursing diagnosis D

s I :

nursing intervention weight discount factor

S I :

the set of nursing activities included in the nursing intervention I

S M :

the set of nursing diagnoses linked to the medical condition M

S remaining :

the set of Web pages remaining to be returned to the user

S returned :

the set of Web pages already returned to the user

S s_p :

the set of phrases pre-compiled for the symptom s

s T :

topic weight discount factor

t :

term

T :

topic

u :

a predetermined constant used in language modeling with Dirichlet smoothing

w A :

weight of the nursing activity A

w D :

weight of the nursing diagnosis D

W f :

the set of Web pages retrieved for the phrase f

w H :

a predetermined constant

w I :

weight of the nursing intervention I

w M :

weight of the medical condition M

w T :

weight of the topic T

Rights and permissions

Reprints and permissions

About this article

Cite this article

Luo, G., Thomas, S.B. & Tang, C. Automatic Home Medical Product Recommendation. J Med Syst 36, 383–398 (2012). https://doi.org/10.1007/s10916-010-9483-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10916-010-9483-2

Keywords

Search

Navigation