Predictive Analytics in Healthcare Service Delivery

This article discusses the importance of predictive analytics in healthcare service delivery. It covers the theories and practices established in the field of predictive analysis and the benefits it offers to patients and healthcare enterprises. The challenges faced in implementing predictive analytics in the healthcare sector are also discussed.

Predictive
analytics

1 | P a g e P r e d i c ti v e a n a l y ti c s
Table of Contents
Introduction...........................................................................................................................................2
Theories and practices that are established in the field Of Predictive Analysis.....................................2
Conclusion...........................................................................................................................................10
References...........................................................................................................................................11

2 | P a g e P r e d i c ti v e a n a l y ti c s
Introduction
In today’s era, predictive analytics is gaining continuous importance as the
environment is also changing rapidly. The use of predictive analytics in health care service
delivery plays an important role as it supports the doctors to take the decisions by analysing
large set of data. It helps in understanding the trend and then providing prediction regarding
the future uncertainties that might be faced by the patient. In choosing any data collection
instrument, nowadays focus is first given on the prediction. It is a difficult task to reliably
analyse the information especially in health care sector as it is directly related with the life of
a person (Ganjir, Sarkar and Kumar, 2016). In health care industry, predictive analysis
translates opinion based decisions into informed decisions. It analyse the data according to
the trends and then make assumptions so that decisions could save patients and healthcare
enterprise. It makes use of technology as well as some statistical method so that massive
information could be analysed and outcomes could be predicated. It has the potential to make
use of big data so that health of patient could be improved that too at low cost.
Theories and practices that are established in the field Of Predictive
Analysis
Predictive analytics is used for making predications for all the future events. There are
various tools that are available for making predications like statistic modelling and data
mining. Predictive analysis works on gather the information from various sources and then
analysing the data. It is used in every field from health care sector to insurance and property
management. In this report, the focus so on healthcare service delivery. Predictive analysis
plays a crucial role in understanding the information and then taking decisions. In health care
service delivery, predictive analysis is used as it offers ways through which goals could be
accomplished (Ganjir, Sarkar and Kumar, 2016). It uses various theories and models to
predict the outcome of illness. Predictive analysis sis very useful in health care department as
it undertakes are the shortcomings that can arise so that precautions could be taken
beforehand. It is beneficial as it build up new policies so that gap can be resolved.
Predictive analysis is one of the core activities in the scientific field as it hypothetically
checks the entire situation rather than just making empirical predications. In the healthcare
industry, the wide adoption of digital and mobile technologies has made important to predict

3 | P a g e P r e d i c ti v e a n a l y ti c s
the future consequences. Predictive analysis is important in health care sector, as it reduces
cost of treatment by predicting all the outbreaks so that diseases could be prevented. It in
general, improves the overall quality of life (Harris, May and Vargas, 2016). The
application of predictive analysis in healthcare has a positive impact as it works on saving the
life of patients. In case of healthcare, it is difficult to gather huge amount of data as it is
costly and time consuming process. Thus, improved technology that is predictive analysis is
used that improves the decision making power by making predication of all the critical
insights (Harris, May and Vargas, 2016). It predicts the critical situation before making it
too late, the predication analysis make sure that methods and treatments are adopted faster so
that patients health could be empowered (Kankanhalli, Hahn, Tan and Gao, 2016).
It is true that there is a huge need of predictive analysis in healthcare as it safes the overall
cost and assures than quality of service is offered. It predicts the health status of patients so
that staffing could be improved. It removes the possibility of risks by removing unnecessary
costs (Kankanhalli, Hahn, Tan and Gao, 2016). Prediction is a widespread application that
includes demographic, medical history along with the designing future steps that need to be
taken. Predication makes the health care facilities easy to use by integrating eth system and
improving the overall outcome.
Predictive analysis along with machine learning is one of eth most important concept in the
health care analytics (Malik, Abdallah and Ala’raj, 2016). Predictive analysis improves the
overall service delivery as it worked on all the previous care therapies so that supply chain
efficiency could be boosted. It is a useful approach especially in health care sector as
predications are converted into actions (Malik, Abdallah and Ala’raj, 2016). The predictive
modelling works on three main steps. The initial step is defining the problem that could occur
then gather the data that is necessary to design an approach. The second step is refining the
process by checking it under certain cases. The last step is assuring that this model is used in
real world practices. Predictive analysis covers evidences of the past health issue,
recommendations and the actions that need to be taken.
Predictive analytics make use of technology and some statistical ways through which
information is analysed and the outcome of patient’s health is determined. In medicine field,
predication ranges in predicting infections to determining the disease so that future wellness
is identified (Malik, Abdallah and Ala’raj, 2016). Predication modelling makes use of

4 | P a g e P r e d i c ti v e a n a l y ti c s
artificial intelligence so that all the past records are analysed and model is deployed easily so
that predications are taken instantly.
Some of the major benefits of using predictive analysis in health care service delivery are:
 Predictive analytics increases the accuracy of diagnosis- Prediction in health care
help patients to make accurate diagnosis. Like an example could be seen, when a
patient enters hospital with a chest pain the prediction from his past record will help
doctor to make future assessment (Shams, Ajorlou and Yang, 2015).
 Predictive approach will help in preventing medicine and public health issues-
Predictive analytics will help the physician to analyse the risk so that practise
decisions are taken accordingly. Predictive analysis also allows doctors to answer the
questions that are asked from the patients (Shams, Ajorlou and Yang, 2015). It also
provides employees about the overall treatment cost that could occur in the medical
treatment.
 Offers potential benefits to patients- It offers benefits to patients in many ways like it
improves the quality of life b suggesting the best treatments that should be
undertaken. Predictive approach is used so that better accuracy could be offered and
the lifestyle could be improved so that future wellbeing is enhanced (Shams, Ajorlou
and Yang, 2015).
Apart from the benefits, predictive analytics supports the health care department by
informing patients about their responsibility (Wang, Kung and Byrd, 2018). It is seen that in
the health care sector, predictive analysis help in identifying the treatment plan that need to
be taken. The predictive analytics approach is used in health care in many ways as it is used
for aiding the diagnosis. It identifies the treatment plan so that patient’s satisfaction is
achieved. Predicative analytics is not limited to chronic conditions but they make use of
additional data so that related events could be managed (Wang, Kung and Byrd, 2018). They
also make use of monitoring tools so that automatically data could be predicted.
The global healthcare industry is changing thus it is important to predict the data so that
integrated steps are undertaken. The treatment outcomes are improved so that financial
resources are saved (Senthilkumar, Rai, Meshram, Gunasekaran and
Chandrakumarmangalam, 2018). The cost in the healthcare department is increasing, thus
predictive analysis predicts the condition of chronic Illness. The benefits gained by predictive
analysis are improving the overall access, reducing the operating cost and improving the

5 | P a g e P r e d i c ti v e a n a l y ti c s
treatment outcomes so that services gets optimized. It builds up set of recommendations so
that actions are taken according to the prediction. It creates full view of all the activities that
can take place so that action plans are decided accordingly. In health care industry making
decision is a difficult task, thus predicative analysis is a way through which decisions could
be made easily (Parikh, Kakad and Bates, 2016). It analysis all the historical data and then
predicts the future events that may occur.
It is true that designing predictive analysis is difficult as it is important for an organisation to
crossover the technology and business process perceptive. To build predictive analysis
strategy it is important to understand people, process and technology that undergo health care
sessions. The predictive analysis can be applied by managing the data so that decisions could
be taken (Parikh, Kakad and Bates, 2016). A multidisciplinary team is needed that can
analysis the clinical data. The health care analytics make use of statistical tools so that
decisions could be taken rapidly. The technologies that are used in health care analysis is tool
based database, electronic health care record and web applications. This helps doctors to
integrate the data and then diagnosis the treatment. It makes sure that preventive care is
offered to them (Hernandez and Zhang, 2017). The advanced technology while making
predications as it includes all the past records, chronic conditions, issues related with the
patients as well as information that is needed to make any conclusion. Health analytics is
used to analysis the data systematically so all the clinical issues are resolved. Predictive
analysis is majorly used for improving the performance by making decisions (Hernandez and
Zhang, 2017).
It helps in identifying the best wellness plan so that clinical information can be promoted and
diseases could be managed at the right time (Adams and Garets, 2014). The advanced
technology monitors the patients’ health records at regular interval of time so that cost of
health care delivery could be reduced. The advanced technologies also reduce the chances of
errors that are caused due to manual efforts.
In the views of (Tan, Gao and Koch, 2015), predictive analytics is a more advanced
technology that emphasis the information by looking at the past experience. The health data
is analysed by looking at the pattern so that response could be predicated. It anticipates the
risk that is associated with the patients’ health so that decisions are taken accordingly. Some
of the advanced technology that is used in health care service delivery is data mining. It
allows the doctors to figure out the hidden patterns so that segmented data is detected. The

6 | P a g e P r e d i c ti v e a n a l y ti c s
predictive analysis also helps in checking the effect of anticipates drugs on the patient’s body.
The predictive modelling is a real time clinical decision that enhances the patient’s
experience (Suresh, 2016). There are various challenges that are faced in the clinical
department like high cot, poor quality and variation in performance. Thus, these issues can be
overcome by predicting the clinical outcome (Adjekum, Ienca and Vayena, 2017). The
clinical risk models are used to distinguish between risk predications and software system so
that patient’s disease and treatment could be identified. Predictive analytics improves the
overall access as patients can check all the resources so that they can enable the predications
accordingly (Suresh, 2016). The operating cost should be reduced by making sure that
satisfaction could be improved.
From the research, it was found that predictive analytics is one of the most hyped topic in the
healthcare analytics. It allows doctors to learn valuable lessons from all the past records so
that patients care could be improved (Yoo, Kalatzis, Amini, Ye and Pourhomayoun, 2018).
Predications can be waste of time and money but in the healthcare industry it is one of the
valuable tools. The predictive analysis could be started by integrating all the data so that
correct conclusion could be made. The problem of patient is understood by gathering the
information and then evaluating the solution through a model. It is found that with the use of
predictive analysis healthcare industry has become rich in data. The predictive analyses make
use of automatic algorithm that analysis the data and take decisions (Adjekum, Ienca and
Vayena, 2017). In the healthcare service delivery predictive analytics is used to manage and
process the data with the motive to discover hidden relationships, trends and predictions. It
supports the delivery of services in the health care department. It has become very popular as
it reduces the overall cost but increases the profit margins (Miner, et. al, 2014). It is seen that
predictive analysis detects the problem at early stage so that safety could be improved and
passengers experience could be optimized (Adams and Garets, 2014).
Implementing predictive analysis in the health care service delivery is not an easy task. There
are various challenges for implementing predictive analytics in the healthcare sector. Many
hospitals suffer due to the failure of IT concerns. Predictive analytics consider all the past
data sets so that predications bring out all the changes that need to be made. It can be said that
predictive analytics is not about analysing the results, but it is about combining new datasets
so that decisions could be accelerated. It ultimately results in enhancing the clinical pathway
with the personalized care (Yoo, Kalatzis, Amini, Ye and Pourhomayoun, 2018). It learns
from the historical data and then makes assumptions about the future results. In the health

7 | P a g e P r e d i c ti v e a n a l y ti c s
care department, predictive analytics allow doctors to take best decisions by offering
personalised care (Bates, Saria, Ohno-Machado, Shah and Escobar, 2014). It directly
impacts the patient care as it help doctors to make clinical decisions so that readmissions are
avoided. It is not just offering customer satisfaction but matching the issues of patients
(Miner, et. al, 2014).
Considering an example,
It can be said that predications start from small scale and end up in making predications so
that uncertainty is resolved (Boukenze, Mousannif and Haqiq, 2016). Predications are correct
always but it increases the power and confidence to make health related decisions (Lin, Chen,
Brown, Li and Yang, 2017). The goal of undertaking predictive analysis is widening the
training data set so that individuals experience is improved and patients are treated in a better
way. Predictive analysis is detecting the concern at early or initial stage so all the genetic and
non-genetic factors are considered (Kohli and Tan, 2016).
Predictive analytics is basically used to improve the certainty of prediction. It opens up the
chances of personalized care so that health outcomes could be improved. However, it builds
models with the objective to reduce uncertainty. This could be done by building new data
types so that reliable decisions could be taken (Al Mayahi, Al-Badi and Tarhini, 2018). The
importance of predictive analysis is to see the consequences clearly so that care, surgery and

8 | P a g e P r e d i c ti v e a n a l y ti c s
quick actions could be taken so that patient’s life could be saved (Wills, 2014). The use of
predictive analysis helps in understanding eh entire ecosystem so that real time alerts could
be understood. It is seen that predication and prevention are closely related to each other and
they go hand in hand (Boukenze, Mousannif and Haqiq, 2016). Thus, risks are identified in
an organisation so at early actions could be taken for the disease so that problems are no
extended for long term and treatment is taken on time. It saves the overall cost that may be
involved in the health care service. It is true, that predictive analysis is used to improve the
overall care transactions so that strategies could be developed according to the predications
(Al Mayahi, Al-Badi and Tarhini, 2018). It helps the doctors to identify the upcoming issues
so that quick reactions could be offered. It is used to identify the patients cut downs and
losses so that opportunities could be offered to the patient by increasing access
(Chennamsetty, Chalasani and Riley, 2015).
In addition to just help patients it predicates the utilization pattern of patients. Various
technologies are used like visualization tool that analyses the patents patter so that
preventions and risks could be highlighted (Chennamsetty, Chalasani and Riley, 2015). The
supply chain is one of the largest cost centres in the health care organisation so that efficiency
could be improved (Belle, et. al, 2015). These tools are in high demand these days,
especially in hospitals as they reduce the variation by offering action plans so that
unnecessary actions could be trimmed. It helps in developing the precision about the
medicines and new therapy that should be taken. It makes all the clinical predications so that
treatment could be optimized accordingly (Eswari, Sampath and Lavanya, 2015).
One of the key reasons of using predictive analytics is rapid growth of health care data so that
patient clinical data could be evaluated and lab decisions are taken according to the result
(Belle, et. al, 2015). Predictive analysis uses software’s that can deal with the demographic
data so that past records of patients could be found (Cohen, Amarasingham, Shah, Xie and
Lo, 2014). These software help the doctors to take proper decisions so that health could be
predict and risks are minimised (Eswari, Sampath and Lavanya, 2015).
Falling risk is a common issue every individual face, in that case predictive analysis help in
analysing all the past record of patient so that correct treatment could be taken. The objective
of predictive analysis is transforming all the data that is gained into actions so that decisions
could be improved (Cohen, Amarasingham, Shah, Xie and Lo, 2014). They make use of
analytical approach so that new insights could be found. Clinical care interventions are used

9 | P a g e P r e d i c ti v e a n a l y ti c s
to reduce patients risk so that complications could be removed. It also supports in making
clinical decision support so that real time actions could be done. It also optimizes the
healthcare cost by detection all the fraud and unhealthy measures. It helps in designing the
prevention by gathering all the patients’ specific condition so that personalized design care is
offered and effective treatment plans are designed (Gandomi and Haider, 2015).

10 | P a g e P r e d i c ti v e a n a l y ti c s
Conclusion
In the limelight of above discussion, it can be concluded that various changes need to be
made according to the station that so that patient’s health could be improved. . There are
various challenges that are faced in the clinical department like high cot, poor quality and
variation in performance. Thus, these issues can be overcome by predicting the clinical
outcome. There are different departments in the organization so that past records are used so
that predictions are made. Predictive analysis also helps in checking the effect of anticipates
drugs on the patient’s body. The predictive modelling is a real time clinical decision that
enhances the patient’s experience. In this report, the theories and practices that are used in the
predictive analysis are discussed.

11 | P a g e P r e d i c ti v e a n a l y ti c s
References
Adams, J. and Garets, D., 2014. The healthcare analytics evolution: moving from descriptive
to predictive to prescriptive. In Analytics in Healthcare (pp. 24-31). HIMSS Publishing.
Adjekum, A., Ienca, M. and Vayena, E., 2017. What is trust? Ethics and risk governance in
precision medicine and predictive analytics. Omics: a journal of integrative biology, 21(12),
pp.704-710.
Al Mayahi, S., Al-Badi, A. and Tarhini, A., 2018, August. Exploring the Potential Benefits of
Big Data Analytics in Providing Smart Healthcare. In International Conference for Emerging
Technologies in Computing (pp. 247-258). Springer, Cham.
Bates, D.W., Saria, S., Ohno-Machado, L., Shah, A. and Escobar, G., 2014. Big data in health
care: using analytics to identify and manage high-risk and high-cost patients. Health
Affairs, 33(7), pp.1123-1131.
Belle, A., Thiagarajan, R., Soroushmehr, S.M., Navidi, F., Beard, D.A. and Najarian, K.,
2015. Big data analytics in healthcare. BioMed research international, 2015.
Boukenze, B., Mousannif, H. and Haqiq, A., 2016. Predictive analytics in healthcare system
using data mining techniques. Comput Sci Inf Technol, 1, pp.1-9.
Chennamsetty, H., Chalasani, S. and Riley, D., 2015, March. Predictive analytics on
Electronic Health Records (EHRs) using Hadoop and Hive. In Electrical, Computer and
Communication Technologies (ICECCT), 2015 IEEE International Conference on (pp. 1-5).
IEEE.
Cohen, I.G., Amarasingham, R., Shah, A., Xie, B. and Lo, B., 2014. The legal and ethical
concerns that arise from using complex predictive analytics in health care. Health
affairs, 33(7), pp.1139-1147.
Eswari, T., Sampath, P. and Lavanya, S., 2015. Predictive methodology for diabetic data
analysis in big data. Procedia Computer Science, 50(2), pp.203-208.
Gandomi, A. and Haider, M., 2015. Beyond the hype: Big data concepts, methods, and
analytics. International Journal of Information Management, 35(2), pp.137-144.

12 | P a g e P r e d i c ti v e a n a l y ti c s
Ganjir, V., Sarkar, B.K. and Kumar, R., 2016. Big data analytics for healthcare. International
Journal of Research in Engineering, Technology and Science, 6(1), pp.1-6.
Harris, S.L., May, J.H. and Vargas, L.G., 2016. Predictive analytics model for healthcare
planning and scheduling. European Journal of Operational Research, 253(1), pp.121-131.
Hernandez, I. and Zhang, Y., 2017. Using predictive analytics and big data to optimize
pharmaceutical outcomes. American Journal of Health-System Pharmacy, 74(18), pp.1494-
1500.
Kankanhalli, A., Hahn, J., Tan, S. and Gao, G., 2016. Big data and analytics in healthcare:
introduction to the special section. Information Systems Frontiers, 18(2), pp.233-235.
Kohli, R. and Tan, S.S.L., 2016. Electronic health records: how can IS researchers contribute
to transforming healthcare?. Mis Quarterly, 40(3), pp.553-573.
Lin, Y.K., Chen, H., Brown, R.A., Li, S.H. and Yang, H.J., 2017. Healthcare predictive
analytics for risk profiling in chronic care: a bayesian multitask learning approach. MIS
Quarterly, 41(2).
Malik, M.M., Abdallah, S. and Ala’raj, M., 2016. Data mining and predictive analytics
applications for the delivery of healthcare services: a systematic literature review. Annals of
Operations Research, pp.1-26.
Miner, L., Bolding, P., Hilbe, J., Goldstein, M., Hill, T., Nisbet, R., Walton, N. and Miner,
G., 2014. Practical predictive analytics and decisioning systems for medicine: Informatics
accuracy and cost-effectiveness for healthcare administration and delivery including medical
research. Academic Press.
Parikh, R.B., Kakad, M. and Bates, D.W., 2016. Integrating predictive analytics into high-
value care: the dawn of precision delivery. Jama, 315(7), pp.651-652.
Senthilkumar, S.A., Rai, B.K., Meshram, A.A., Gunasekaran, A. and
Chandrakumarmangalam, S., 2018. Big Data in Healthcare Management: A Review of
Literature. American Journal of Theoretical and Applied Business, 4(2), pp.57-69.
Shams, I., Ajorlou, S. and Yang, K., 2015. A predictive analytics approach to reducing 30-
day avoidable readmissions among patients with heart failure, acute myocardial infarction,
pneumonia, or COPD. Health care management science, 18(1), pp.19-34.

13 | P a g e P r e d i c ti v e a n a l y ti c s
Suresh, S., 2016. Big data and predictive analytics: applications in the care of
children. Pediatric Clinics, 63(2), pp.357-366.
Tan, S.L., Gao, G. and Koch, S., 2015. Big data and analytics in healthcare. Methods of
information in medicine, 54(06), pp.546-547.
Wang, Y., Kung, L. and Byrd, T.A., 2018. Big data analytics: Understanding its capabilities
and potential benefits for healthcare organizations. Technological Forecasting and Social
Change, 126, pp.3-13.
Wills, M.J., 2014. Decisions through data: Analytics in healthcare. Journal of Healthcare
Management, 59(4), pp.254-262.
Yoo, S., Kalatzis, A., Amini, N., Ye, Z. and Pourhomayoun, M., 2018, June. Interactive Predictive
Analytics for Enhancing Patient Adherence in Remote Health Monitoring. In Proceedings of the 8th
ACM MobiHoc 2018 Workshop on Pervasive Wireless Healthcare Workshop pp. 1-19,ACM.