Healthc Inform Res.  2020 Apr;26(2):146-152. 10.4258/hir.2020.26.2.146.

Monitoring Mental Healthcare Services Using Business Analytics

• Housbane S
• Khoubila A
• Ajbal K
• Serhier Z
• Agoub M
• Battas O
• Othmani MB

• KMID: 2501339
• DOI: http://doi.org/10.4258/hir.2020.26.2.146

Abstract

Monitoring healthcare activities is the first step for health stakeholders and health professionals to improve the quality and performance of healthcare services. However, monitoring remains a challenge for healthcare facilities, especially in developing countries. Fortunately, advances in business analytics address this need. This paper aims to describe the experience of a low-income healthcare facility in a developing country in using business analytics descriptive techniques and to discuss business analytics implementation challenges and opportunities in such an environment.

Business analytics descriptive techniques were applied on 3 years’ electronic medical records of outpatient consultation of the University Psychiatric Centre (CPU) of Casablanca. Statistical analysis was conducted to compare results over years.

Over the 3 monitored years, the monthly number of computerized physician order entries increased significantly (p < 0.001). Physicians improved their personal recording over years. Schizophrenia as well as depressive and bipolar disorders were noted at the top of outpatient mental disorders. Antipsychotics are the most prescribed drugs, and a significant annual decrease in outpatient care wait time was noted (p < 0.001).

Business analytics allowed CPU to monitor mental healthcare outpatient activity and to adopt its business processes according to outcomes. However, challenges mainly in the organizational dimension of the decision-making process and the definition of strategic key metrics, data structuration, and the quality of data entry had to be considered for the optimal use of business analytics.

Keyword

Health Information Systems; Data Science; Mental Health Services; Computer-Assisted Decision Making; Management Decision Support Systems

Figure

• 

  Figure 1 Pentaho ETL Editor showing a drug dimension transformation. ETL: extraction, transformation, and load.

• 

  Figure 2 Pentaho Model Editor showing data modeling.

• 

  Figure 3 Pentaho Report Editor showing drug prescriptions per diagnosis.

• 

  Figure 4 Monthly CPOE number at the University Psychiatric Centre outpatient consultation by year. CPOE: computerized physician order entry.

• 

  Figure 5 Top five diagnoses by year at the University Psychiatric Centre outpatient consultation.

• 

  Figure 6 Top five diagnoses by gender at the University Psychiatric Centre outpatient consultation in 2018.

• 

  Figure 7 Prescribed psychiatric drug at the University Psychiatric Centre outpatient consultation in 2018.

• 

  Figure 8 Monthly number of CPOEs performed by one physician at the University Psychiatric Centre outpatient consultation by year. CPOE: computerized physician order entry.

• 

  Figure 9 Monthly averaged the University Psychiatric Centre outpatient care wait time in minutes over year.

• 

  Figure 10 District-based distribution of prescribed psychiatric drugs weighted by patient count at the University Psychiatric Centre outpatient consultation in 2018. Dots are bigger according to patient count, and dot color is green, yellow, or red for high, medium, or low drug count, respectively.

Reference

References

1. Bayrak T. A review of business analytics: a business enabler or another passing fad. Procedia Soc Behav Sci. 2015; 195:230–9.

2. Khalifa M. Health analytics types, functions and levels: a review of literature. Stud Health Technol Inform. 2018; 251:137–40.

3. Sivarajah U, Kamal MM, Irani Z, Weerakkody V. Critical analysis of Big Data challenges and analytical methods. J Bus Res. 2017; 70:263–86.

4. Galetsi P, Katsaliaki K. Big data analytics in health: an overview and bibliometric study of research activity. Health Info Libr J. 2020; 37(1):5–25.

5. Raghupathi W, Raghupathi V. An empirical study of chronic diseases in the United States: a visual analytics approach. Int J Environ Res Public Health. 2018; 15(3):431.

6. El Morr C, Ginsburg L, Nam S, Cheung W, Brien H, Maloul A, et al. Insight into health care outcomes for persons living with heart failure using health data analytics. Stud Health Technol Inform. 2019; 257:98–102.

7. Riahi S, Fischler I, Stuckey MI, Klassen PE, Chen J. The value of electronic medical record implementation in mental health care: a case study. JMIR Med Inform. 2017; 5(1):e1.

8. Mehta N, Pandit A. Concurrence of big data analytics and healthcare: a systematic review. Int J Med Inform. 2018; 114:57–65.

9. Pentaho from Hitachi Vantara - data integration [Internet]. [place unknown]. Sourceforge.net;2019. [cited at 2019 Feb 21]. Available from: https://sourceforge.net/projects/pentaho/files/Data%20Integration/6.1/.

10. Wu C. Development of a medical informatics data warehouse. AMIA Annu Symp Proc. 2006; 2006:1148.

11. Hitachi Vantara. Pentaho Business Analytics [Internet]. Santa Clara (CA): Hitachi Vantara;c2020. [cited at 2019 Feb 21]. Available from: https://www.hitachivantara.com/en-us/products/big-data-integration-analytics/pentaho-business-analytics.html.

12. GeoNames [Internet]. [place unknown]. GeoNames;c2019. [cited at 2019 Feb 21]. Available from: http://www.geonames.org/.

13. Vidgen R, Shaw S, Grant DB. Management challenges in creating value from business analytics. European Journal of Operational Research. 2017; 261(2):626–39.

14. Loewen L, Roudsari A. Evidence for business intelligence in health care: a literature review. Stud Health Technol Inform. 2017; 235:579–83.

15. Bouayad L, Ialynytchev A, Padmanabhan B. Patient health record systems scope and functionalities: literature review and future directions. J Med Internet Res. 2017; 19(11):e388.

16. Valentine EA, Falk SA. Quality improvement in anesthesiology – leveraging data and analytics to optimize outcomes. Anesthesiol Clin. 2018; 36(1):31–44.

17. Friedman LM, Furberg CD, DeMets DL, Reboussin DM, Granger CB. Reporting and interpreting of results. Fundamentals of clinical trials. Cham: Springer;2015. p. 479–99.

18. Krishnamoorthi S, Mathew SK. Business analytics and business value: a comparative case study. Inf Manag. 2018; 55(5):643–66.

19. Torres R, Sidorova A, Jones MC. Enabling firm performance through business intelligence and analytics: a dynamic capabilities perspective. Inf Manag. 2018; 55(7):822–39.