Data mining of digitized health records in a resource-constrained setting reveals that timely immunophenotyping is associated with improved breast cancer outcomes

Pineda, Arturo López; Moran, Mario Felipe Rodriguez; Aguilar, Cleto Alvarez; Valle, Sarah Marlenne Fuentes; Rosales, Roman Acosta; Bhatt, Ami S.; Sheth, Shreya; Bustamante, Carlos D.

doi:10.1101/198721

Cited by 2 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the emergence of virtual randomized clinical trials has shown the value to accelerate results and provide informed guidance to patients (44). The digitization of electronic health records is possible and should be an overall strategy in resource-constrained settings to provide a data-driven approach to public health concerns (45). Machine learning models and data science can be effectively applied to these settings augmenting the capabilities of the healthcare system.…”

Section: Discussionmentioning

confidence: 99%

A Competing Risk Analysis of Early COVID-19 Treatments

Gonzalez-Arroyo

García

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Currently in Mexico, the available clinical guidelines published for COVID-19 treatment recommend symptom treatment and home isolation for mild forms; and other medications for severe and acute forms. The effectiveness of how real-world treatment patterns impact mortality and recovery is still unknown. In this retrospective observational study, we investigated 5,575 medicated patients with COVID-19 treated at two Mexican states seen in the largest healthcare system in Mexico. A survival analysis was performed using death and discharge as primary and secondary outcomes (respectively). Machine learning models were built to predict mortality and discharge. The higher prevalence of obesity, diabetes, and heart disease comorbidities is consistent with Mexico’s epidemiological profile. Mortality occurs around 15-20 days from the start of symptoms. Antivirals in combination with antibiotics present lower survival rates, with patients undertaking neuraminidase inhibitors (NAIs) being the most affected. Our findings recommend against using specific treatment combinations with NAIs, and should help improve the country’s clinical guidelines.

show abstract

Section: Discussionmentioning

confidence: 99%

A Competing Risk Analysis of Early COVID-19 Treatments

Gonzalez-Arroyo

García

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…[52] [52] Quick turnaround time for immunohistochemistry test and precise care of 402 breast cancer patients. [40] Created care procedure to treat genitourinary syndrome of menopause for breast cancer survivors. [41] Assign event date for a second breast cancer.…”

Section: An Evaluation Of Data Science Methods In Solving Women Healt...mentioning

confidence: 99%

The Application of Data Science Techniques and Algorithms in Women’s Health Studies

Akpan

Aguolu

2022

Preprint

View full text Add to dashboard Cite

Objective: Evaluate and map data science methods employed to solve health conditions of women, examine the problems tackled and the effectiveness. Research Method: Text analytics, science mapping, and descriptive evaluation of data science methods utilized in women-related health research. Findings: (i). The trends in scholarships using data science methods indicate gaps between women and men relating to health burden and access to health. (ii). The coronavirus (SARS-CoV-2) outbreak and the ongoing COVID-19 pandemic tend to widen the identified health gaps, increasing the disease burden for women, while reducing access to health. There are noticeable additional health burdens on pregnant women and those with several health conditions (breast cancer, gynecologic oncology, cardiovascular disease, and more). (iii). Over 95% of studies using data science methods (artificial intelligence, machine learning, novel algorithms, predictive, big data, visual analytics, clinical decision support systems, or a combination of the methods) indicate significant effectiveness. (iv). Mapping of the scientific literature to authors, sources, and countries show an upward trend; 997 (16%), 113 (1.33%), and 57 (2.63%) per article, respectively. About 95% of research utilizing data science methods in women's health studies occurred within the last four (4) years. Conclusions: The application of data science methods in tackling different health problems of women is effective and growing, and capable of easing the burden of health in women. The ongoing COVID-19 pandemic tends to compound the health burden for women more than men. Policymakers must do more to improve access to health for women.

show abstract

Data mining of digitized health records in a resource-constrained setting reveals that timely immunophenotyping is associated with improved breast cancer outcomes

Abstract: 23

Cited by 2 publications

References 16 publications

A Competing Risk Analysis of Early COVID-19 Treatments

A Competing Risk Analysis of Early COVID-19 Treatments

The Application of Data Science Techniques and Algorithms in Women’s Health Studies

Contact Info

Product

Resources

About