Machine Learning Presentation

MACHINE LEARNING

IN THE HEALTH SECTOR

David Mata Guerra, Alexis Cardenas Camacho

VI The future of ML

AGENDA

I What is Machine Learning?

II Methodology

III Applications of ML in the health sector

IV Developing ML models

V ML models vs doctors

VII Conclusions

WHAT IS MACHINE LEARNING?

Machine learning is an aspect of artificial intelligence that is an automated learning, where a computer is programmed to learn by itself based on algorithms and data.

METHODOLOGY

EXEMPLIFICATION

ENTAILMENT

CLASSIFICATION

DIFFERENTIATION

CONCEPTUAL CARTHOGRAPHY

NOTION

METHODOLOGY

CATEGORIZATION

CHARACTERIZATION

META ANALYSIS

PHASE 1

We obtained 145 articles from ScienceDirect, 251 from Web of Science, 4 from Elsevier and 50 from Google Academic. In total there were 450 articles.

PHASE 2

After reading the summaries, we discarded 430 articles that did not fulfill our criteria. Based on that criteria, we selected 20 for further review.

META ANALYSIS

PHASE 1

We obtained 145 articles from ScienceDirect, 251 from Web of Science, 4 from Elsevier and 50 from Google Academic. In total there were 450 articles.

The preparation of conceptual cartography based on its 8 components.

PHASE 3

PHASE 2

After reading the summaries, we discarded 430 articles that did not fulfill our criteria. Based on that criteria, we selected 20 for further review.

META ANALYSIS

PHASE 1

We obtained 145 articles from ScienceDirect, 251 from Web of Science, 4 from Elsevier and 50 from Google Academic. In total there were 450 articles.

KEYWORDS

LEARNING MODELS; HEALTH SECTOR; MACHINE LEARNING; HEALTH; CONCEPTUAL CARTOGRAPHY

APPLICATIONS OF ML IN THE HEALTH SECTOR

01

SUPERVISED LEARNING

The model is programmed with continuous review, inputting statistical data through classification algorithms. Used in clinical diagnostics.

02

UNSUPERVISED LEARNING

The model requires minimal developer assistance, mainly in the initial stage. Used in personalized treatments for patients

STEP 6

Implementation for clinical use

evaluate the model for accuracy and effectiveness

STEP 3

04

02

DEVELOPING MODELS

01

STEP 1

collect a large amount of data from medical devices

02

STEP 2

Data preprocessing to ensure data consistency by eliminating bugs, errors, and values.

03

STEP 4

choose an algorithm based on the health topic being addressed.

04

STEP 5

train the model by collecting and preprocessing data.

ML Models vs doctors

According to a previous study and the models we've discussed, Machine Learning models have higher accuracy than doctors. The graph in the next slide illustrates the diagnosis comparison between 100 doctors and one model for hundreds of patients.

DATA POINTS Doctor's accuracy Model accuracy Line that separates the results

THE FUTURE OF ML IN MEDICINE

We found that Machine Learning has significant potential in medicine. It can perform diagnoses, identify images from X-rays, manage a hospital, and even contribute to medical education. However, currently, Machine Learning cannot fully replace a doctor.

In summary, we explored the role of Machine Learning in healthcare, emphasizing its application in diagnoses and personalized treatments. While ML models showed higher accuracy than doctors in certain cases, we acknowledge limitations in handling complex diseases. Although ML has potential in medicine, it cannot entirely replace doctors as it faces challenges in detecting complex diseases and requires specialized skills for development and application.

Conclusions

REFERENCES

Kwekha-Rashid, A. S., Abduljabbar, H. N., & Alhayani, B. (2021). Coronavirus disease (COVID-19) cases analysis using machine-learning applications. Applied Nanoscience, 13(3), 2013-2025. https://doi.org/10.1007/s13204-021-01868-7 Campanile, L., Marrone, S., Marulli, F., & Verde, L. (2022). Challenges and Trends in Federated Learning for Well-being and Healthcare. Procedia Computer Science, 207, 1144-1153. https://doi.org/10.1016/j.procs.2022.09.170** Chuang, I. (2019). The emergence of precision medicine is causing us to redefine value in patient care. Elsevier Connect. https://www.elsevier.com/connect/does-precision-medicine-conflict-with-or-complement-value-based-care Capot, C. (2018). New education technologies will help nursing students prepare for the workforce. https://www.elsevier.com/__data/assets/pdf_file/0008/637481/New-education-technologies-will-help-nursing-students-prepare-for-the-workforce.pdf Géron, A. (2020). Aprende machine learning con scikit-learn, keras y tensorflow. España: Anaya. Javaid, M., Haleem, A., Singh, R. P., Suman, R., & Rab, S. (2022). Significance of Machine learning in healthcare: features, pillars and applications. International Journal of Intelligent Networks, 3, 58-73. https://doi.org/10.1016/j.ijin.2022.05.002

QUESTIONS?...

THANK YOU!