Advertisement

Automated Drug Suggestion Using Machine Learning

  • Vikrant Doma
  • Sahil Singh
  • Nikita Arora
  • Gabriel Ortiz
  • Parneet Kaur Saran
  • Salvador Chavarin
  • Matin PirouzEmail author
Conference paper
  • 9 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1130)

Abstract

The growing healthcare industry generates a large amount of data on patient health conditions, demographic plans, and drugs required for such conditions. These attract the attention of the medical professionals and the data scientists alike. In this paper, we propose a drug recommendation assistant built using machine learning techniques and natural language processing, which draws its accuracy from several major datasets. The proposed system makes it possible to manifest the contrasting effects, reviews, ratings, and then recommend the most “effective” drug for a given individual. The results of the predictive analysis were that from 2005–2015, between the ages 55 and 80, the death rates of the top deadliest diseases in the U.S. all increased drastically. Based on the current trends, with some level of accuracy, it is possible to predict the next top five medical conditions (Birth Control, Depression, Pain, Anxiety, Acne) which will be prevalent in the near future and the top five drugs for used to treat them.

Keywords

Drug recommendation Confusion matrix Data visualization Data manipulation 

Notes

Acknowledgement

This research is partially supported by a grant from Amazon Web Services.

References

  1. 1.
    Gräßer, F., Kallumadi, S., Malberg, H., Zaunseder, S.: UCI Machine Learning Repository (2019). http://archive.ics.uci.edu/ml, https://archive.ics.uci.edu/ml/datasets/Drug+Review+Dataset+%28Drugs.com%29#Irvine. Accessed 08 Apr 2019
  2. 2.
    National Center for Health Statistics. NCHS Data Visualization. Gallery - Potentially Excess Deaths in the United States. Centers for Disease and Control and Prevention, 28 August 2017. https://www.cdc.gov/nchs/data-visualization/potentially-excess-deaths/. Accessed 27 Apr 2019
  3. 3.
    Larmuseau, P.: Licence Public Last updated ‘2017-03-10’, Date created ‘2017-03-04’, Current version: Version 4, Symptom Disease sorting. https://www.kaggle.com/plarmuseau/sdsort/metadata
  4. 4.
    Viveka, S., Kalaavathi, B.: Review on clinical data mining with psychiatric adverse drug reaction. In: 2016 World Conference on Futuristic Trends in Research and Innovation for Social Welfare (Startup Conclave), Coimbatore, pp. 1–3 (2016). http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7583945&isnumber=7583750
  5. 5.
    ACC News Story. CDC Report Shows CVD Still #1 Killer in US - American College of Cardiology. American College of Cardiology, 3 December 2018. https://www.acc.org/latest-in-cardiology/articles/2018/12/03/16/11/cdc-report-shows-cvd-still-1-killer-in-us. Accessed 8 May 2019
  6. 6.
    Rosenburg, J.: Cancer Surpasses CVD as Leading Cause of Death in High-Income Counties. Ajmc.com, 13 November 2018. https://www.ajmc.com/focus-of-the-week/cancer-surpasses-cvd-as-leading-cause-of-death-in-highincome-counties. Accessed 8 May 2019
  7. 7.
    Syverson, P., Reed, M., Goldschlag, D.: Private medical instances. J. Comput. Med. Data (JCS) 5(3), 237–248 (1997)Google Scholar
  8. 8.
    Saint-Jean, F., Johnson, A., Boneh, D., Feigenbaum, J.: Private web search. In: Proceedings of the 6th ACM Workshop on Privacy in the Electronic Society (WPES) (2007)Google Scholar
  9. 9.
    Levy, S., Gutwin, C.: Improving understanding of website privacy policies with fine-grained policy anchors. In: Proceedings of the Conference on the World-Medical Data, pp. 480–488 (2005)Google Scholar
  10. 10.
    Romanosky, S.: FoxTor: helping protect your health while browsing online for conditions. cups.cs.cmu.edu/foxtor
  11. 11.
    Khalid, S., Ali, M.S., Prieto-Alhambra, D.: Cluster analysis to detect patterns of drug use from routinely collected medical data. In: 2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS), Karlstad, pp. 194–198 (2018). http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8417236&isnumber=8417175
  12. 12.
    Kanchan, B.D., Kishor, M.M.: Study of machine learning algorithms for special disease prediction using principal of component analysis. In: 2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC), Jalgaon, pp. 5–10 (2016). http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7955260&isnumber=7955253
  13. 13.
    Gaydhani, A., Doma, V., Kendre, S., Bhagwat, L.: Detecting hate speech and offensive language on twitter using machine learning: an N-gram and TFIDF, CoRR, Volume is abs/1809.08651 (2018)Google Scholar
  14. 14.
    Kanchan, B.D., Kishor, M.M.: Study of machine learning algorithms for special disease prediction using principal of component analysis. In: 2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC). IEEE (2016).  https://doi.org/10.1109/icgtspicc.2016.7955260
  15. 15.
    Scikit-learn developers (BSD License). SVM Example—scikit-learn 0.20.3 documentation. Scikit-learn.org (n.d.). https://scikit-learn.org/stable/auto_examples/linear_model/plot_ols.html#sphx-glr-auto-examples-linear-model-plot-ols-py. Accessed 20 Apr 2019
  16. 16.
    The SciPy community. Quickstart tutorial—NumPy v1.16 Manual. Scipy.org Sponsored by Enthought (2019). https://docs.scipy.org/doc/numpy/user/quickstart.html. Accessed 30 Apr 2019
  17. 17.
    Hunter, J., Dale, D., Firing, E., Droettboom, M., Matplotlib Development Team: Beginner’s Guide—Matplotlib 1.5.3 documentation. Matplotlib.org (2016). https://matplotlib.org/users/beginner.html. Accessed 19 Apr 2019
  18. 18.
    Hunter, J., Dale, D., Firing, E., Droettboom, M., Matplotlib Development Team: Matplotlib Pyplot Semilogx—Matplotlib 3.0.3 Documentation. Matplotlib.org (n.d.). https://matplotlib.org/api/_as_gen/matplotlib.pyplot.semilogx.html. Accessed 26 Apr 2019
  19. 19.
    Droettboom, M., Matplotlib Development Team: Matplotlib Pyplot Semilogx—Matplotlib 3.0.3 Documentation. Matplotlib.org (n.d.). https://matplotlib.org/api/_as_gen/matplotlib.pyplot.semilogx.html. Accessed 26 Apr 2019
  20. 20.
    Dateutil. Parser—dateutil 2.8.0 documentation. Readthedocs.io (2016). https://dateutil.readthedocs.io/en/stable/parser.html. Accessed 30 Apr 2019

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Vikrant Doma
    • 1
  • Sahil Singh
    • 1
  • Nikita Arora
    • 1
  • Gabriel Ortiz
    • 1
  • Parneet Kaur Saran
    • 1
  • Salvador Chavarin
    • 1
  • Matin Pirouz
    • 1
    Email author
  1. 1.California State UniversityFresnoUSA

Personalised recommendations