A Review of the Use of Data Analytics to Address Preeclampsia in Ecuador Between 2020 and 2024

Diagnostics, Journal Year: 2025, Volume and Issue: 15(8), P. 978 - 978

Published: April 11, 2025

Preeclampsia is one of the leading causes maternal and perinatal morbidity mortality worldwide. The incidence preeclampsia in Ecuador approximately 51 cases per 1000 pregnancies. Despite advances medicine, its diagnosis management remain a challenge due to multifactorial nature variability clinical presentation. Data analytics offers an innovative approach address these challenges, allowing for better understanding disease more informed decision-making. This work review examines peer-reviewed studies published during last decade that employed descriptive, diagnostic, predictive, prescriptive evaluate Ecuador. focuses on conducted healthcare institutions across coastal highland regions, with inclusion criterion requiring sample sizes greater than 100 patients. Emphasis placed statistical methods used, main findings, technological capabilities facilities where analyses were performed. Critical evaluation methodology limitations comparative discussion findings global literature are included. synthesis highlights both progress gaps predictive suggests pathways future research.

Language: Английский

---

Prediction of Emergency Room Arrivals of Patients with Preeclampsia Disease Using Artificial Neural Network Model

Published: April 19, 2024

Language: Английский

---

OUCH:Oversampling and Undersampling Cannot Help Improve Accuracy in our Bayesian Classifiers that Predict Preeclampsia

Mathematics, Journal Year: 2024, Volume and Issue: 12(21), P. 3351 - 3351

Published: Oct. 25, 2024

Unbalanced data can have an impact on the machine learning (ML) algorithms that build predictive models. This manuscript studies influence of oversampling and undersampling strategies Bayesian classification models predict risk suffering preeclampsia. Given properties our dataset, only methods operate with numerical categorical attributes will be taken into consideration. In particular, synthetic minority techniques for nominal continuous (SMOTE-NC), SMOTE—Encoded Nominal Continuous (SMOTE-ENC), random examples (ROSE), (UNDER), (OVER) are considered. According to results, when balancing class in training accuracy percentages do not improve. However, test both positive negative cases preeclampsia were accurately classified by models, which built a balanced dataset. contrast, imbalanced dataset good at detecting We conclude while datasets addressed using before building prediction improvement model is always guaranteed. Despite this, sensitivity specificity improve binary problems most cases, such as one we dealing this manuscript.

Language: Английский

---

From Descriptive to Prescriptive Analytics on Time Series: Studying the Number of Preeclampsia Inpatient Beds

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 131576 - 131590

Published: Jan. 1, 2024

Language: Английский

---

DEAR: DEtecting Ambiguous Requirements as a Way to Develop Skills in Requirement Specifications

Electronics, Journal Year: 2024, Volume and Issue: 13(15), P. 3079 - 3079

Published: Aug. 3, 2024

To improve requirement specification skills, it is vital to detect ambiguous requirements in order correct them later. Thus, help software engineering students their capacity identify user (requirements that do not use technical words) while providing with a valuable and engaging educational experience, the current study proposes serious game called DEAR. It consists of didactic exercise which participants must move different left or right indicate whether they are unambiguous. assess improvement students’ abilities perceptions about training class when using DEAR game, we conducted an experiment 62 participants, splitting into two groups: one used other underwent conventional session. was found that, during sessions, both groups became more adept at identifying unambiguous requirements, but there no discernible difference performance between them. However, group expressed stronger preference for session’s engagement quality, as well sense having learned how clearly define requirements. Overall, shows suggested may be helpful teaching tool yields learning outcomes comparable those chalkboard encouraging interactive manner.

Language: Английский

---

Supporting the Characterization of Preeclampsia Patients Through Descriptive and Clustering Analysis

Electronics, Journal Year: 2024, Volume and Issue: 13(23), P. 4854 - 4854

Published: Dec. 9, 2024

One of the most common causes maternal death during pregnancy is preeclampsia. A deeper understanding patient’s features can aid in hospital’s clinical care distribution. However, at IESS Los Ceibos Hospital, these types studies have not been carried out for Therefore, this work, we describe application descriptive and clustering analysis to characterize preeclamptic patients. Preeclamptic patients treated Hospital Guayaquil comprised dataset used study. Descriptive allowed us find that severe preeclampsia (O141) diagnosis when arrive hospitalization unit, representing 79.5% cases. Moreover, women whose age falls between 26 35 years highest prevalence preeclampsia, 55.4% Finally, adult their late 30s or older are often diagnosed with require many hours hospital first two visits. These findings will help generate prevention policies, such as use a low dose aspirin, groups avoid complications cause.

Language: Английский

---

Multidimensional Bayesian Classifier for Predicting the Multi-stage Patient's Response to the BoNT-A Treatment for Migraine

2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 6

Published: July 25, 2024

Language: Английский

---

FRUIT: Fuzzy Representation of Unbounded and Imprecise Terms in Non-Functional Requirements

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 182779 - 182787

Published: Jan. 1, 2024

Language: Английский

---