Prescriptive Analytics in Healthcare:Advanced Decision Making for Optimal Treatment
Fernandes, Daniel (2024)
2024
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2024060621539
https://urn.fi/URN:NBN:fi:amk-2024060621539
Tiivistelmä
This thesis explored the potential of prescriptive analytics to revolutionize healthcare decision-making. It began by highlighting the limitations of traditional, one-size-fits-all treatment approaches and the growing emphasis on personalized medicine based on patient data. The research addressed the challenges and opportunities of implementing prescriptive analytics in healthcare.
A proof-of-concept prescriptive model for drug classification was developed using a decision tree algorithm trained on a sample dataset. The model considered five patient characteristics: age, sex, blood pressure, cholesterol level, and sodium-to- potassium ratio. It demonstrated the potential for prescriptive analytics to provide tailored treatment recommendations based on individual patient data.
The thesis also addressed the ethical considerations and data privacy concerns surrounding prescriptive analytics in healthcare. Mitigating data bias was identified as a critical factor for ensuring the fairness and effectiveness of these models.
The research concluded by emphasizing the transformative potential of prescriptive analytics to improve diagnostic accuracy, optimize treatment plans, and ultimately enhance patient outcomes. It highlighted the need for further research to address implementation challenges, ensure data privacy, and continuously improve the accuracy and precision of prescriptive models. Overall, the thesis suggests that prescriptive analytics has the potential to revolutionize healthcare delivery by enabling more personalized, efficient, and effective patient care.
A proof-of-concept prescriptive model for drug classification was developed using a decision tree algorithm trained on a sample dataset. The model considered five patient characteristics: age, sex, blood pressure, cholesterol level, and sodium-to- potassium ratio. It demonstrated the potential for prescriptive analytics to provide tailored treatment recommendations based on individual patient data.
The thesis also addressed the ethical considerations and data privacy concerns surrounding prescriptive analytics in healthcare. Mitigating data bias was identified as a critical factor for ensuring the fairness and effectiveness of these models.
The research concluded by emphasizing the transformative potential of prescriptive analytics to improve diagnostic accuracy, optimize treatment plans, and ultimately enhance patient outcomes. It highlighted the need for further research to address implementation challenges, ensure data privacy, and continuously improve the accuracy and precision of prescriptive models. Overall, the thesis suggests that prescriptive analytics has the potential to revolutionize healthcare delivery by enabling more personalized, efficient, and effective patient care.