Application of random forest model to predict the demand of essential medicines for noncommunicable diseases management in public health facilities

Mbonyinshuti, François; Nkurunziza, Joseph; Niyobuhungiro, Japhet; Kayitare, Egide

doi:10.11604/pamj.2022.42.89.33833

Cited by 14 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evolution mechanism of various public emergencies of online public opinion provides countermeasures and suggestions for the government to guide and manage network public opinion [29]. Even at the operational level, AI can optimize health supply chain planning and operational management by predicting the demand trend for NCD essential medicines [30].…”

Section: Discussionmentioning

confidence: 99%

The Application of Artificial Intelligence in Health Policy: A Scoping Review

Ramezani

Takian

Bakhtiari

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Policymakers require precise, in-time information to make informed decisions in complex environments such as health systems. Artificial intelligence (AI) is a novel approach that makes collecting and analyzing data in complex systems more accessible. This study highlights recent research on AI's application and capabilities in health policymaking. Method PubMed, Scopus, and the Web of Science databases were investigated to find relevant studies from 2000 to 2023 using the keywords of "artificial intelligence" and "policymaking." Walt and Gilson's policy triangle framework was used for charting the data. Results The results revealed that using AI in health policy paved the way for novel analyses and innovative solutions for intelligent decision-making and data collection, potentially enhancing policymaking capacities, particularly in the evaluation phase. Moreover, it can be used to develop creative agendas with fewer political limitations and higher rationality, leading to better policies. Furthermore, AI provides the opportunity to make evidence-informed decisions by developing new platforms and toolkits. Most of the suggested AI solutions for health policy are not meant to replace experts but to make decision-making smarter. Conclusion Numerous approaches exist for AI to influence the health policymaking process. Leading health systems can benefit from AI's potential to expand the use of evidence-based policymaking in health systems.

show abstract

Section: Discussionmentioning

confidence: 99%

The Application of Artificial Intelligence in Health Policy: A Scoping Review

Ramezani

Takian

Bakhtiari

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…While Decision Tree provides transparency, Random Forests enhance predictive accuracy by leveraging the strength of multiple trees and introducing randomness during the training process. These models find applications in diverse domains, including finance, healthcare, and engineering fields [25] [26].…”

Section: Methodsmentioning

confidence: 99%

A Comparative Study of Two Tree-Based Models for Predicting Flyrock Velocity at Open Pit Bench Mining

Rawnaq,

Esmatyar,

Hamanaka

et al. 2024

OJAppS

View full text Add to dashboard Cite

Blasting is a cost-effective technique to break hard rock volumes by using explosives in the mining and civil engineering realms. Moreover, although blasting is a designed process and plays an indispensable role in these industries, it can also have multiple adverse environmental impacts. One such effect is flyrock, which poses risks to nearby machinery, and residential structures, and can even lead to injuries or fatalities. To optimize blasting efficiency as well as restrict side effects, prediction of the blast aftereffects is vital. Therefore, the present work focuses on using two machine learning methods to predict the velocity of flyrock in the open pit mine. To address this issue, a comprehensive dataset was gathered from the open pit mine. Then, Decision Tree and Random Forest algorithms were employed to predict flyrock velocity. The Random Forest model demonstrated superior performance compared to the Decision Tree model. Nonetheless, the performance of the Decision Tree model was deemed satisfactory, as evidenced by its coefficient of determination value of 0.83, mean squared error (MSE) of 4.2, and mean absolute percentage error (MAPE) of 5.6%. Considering these metrics, it is reasonable to conclude that tree-based algorithms can be effective in predicting flyrock velocity.

show abstract

“…The random forest algorithm has been used for the study purpose. This ML technique is based on creating a multitude of decision trees and producing average predictions based on the individual tree (Mbonyinshuti et al, 2022). The algorithm was implemented using the Random Forest package in SAS Viya.…”

Section: Predictive Analysismentioning

confidence: 99%

“…Over the past few years, diverse machine learning methodologies have been employed to address health issues, showcasing high-quality and valid predictive outcomes. A wide array of models has been used for early disease prediction, medicine demand, and healthcare services (Gupta et al, 2014;Mbonyinshuti et al, 2022). Generating estimates from the machine learning model from a limited set of SED characteristics will help fill the data gap and be cost-effective for the smaller geographical regions, compared to the traditional survey-based estimates.…”

Section: Introductionmentioning

confidence: 99%

Unveiling non-communicable disease trends among Indian states: predicting health outcomes with socioeconomic and demographic factors

Shukla,

Arora,

Gupta

2024

IJSSP

View full text Add to dashboard Cite

PurposeThe present study examines the fluctuations in Socioeconomic and demographic (SED) factors and the prevalence of Non-Communicable Diseases (NCDs) across clusters of states in India. Further, it attempts to analyze the extent to which the SED determinants can serve as predictive indicators for the prevalence of NCDs.Design/methodology/approachThe study uses three rounds of unit-level National Sample Survey self-reported morbidity data for the analysis. A machine learning model was constructed to predict the prevalence of NCDs based on SED characteristics. In addition, probit regression was adopted to identify the relevant SED variables across the cluster of states that significantly impact disease prevalence.FindingsOverall, the study finds that the disease prevalence can be reasonably predicted with a given set of SED characteristics. Also, it highlights age as the most important factor across a cluster of states in understanding the distribution of disease prevalence, followed by income, education, and marital status. Understanding these variations is essential for policymakers and public health officials to develop targeted strategies that address each state’s unique challenges and opportunities.Originality/valueThe study complements the existing literature on the interplay of SEDs with the prevalence of NCDs across diverse state-level dynamics. Its predictive analysis of NCD distribution through SED factors adds valuable depth to our understanding, making a notable contribution to the field.

show abstract

Application of random forest model to predict the demand of essential medicines for noncommunicable diseases management in public health facilities

Cited by 14 publications

References 13 publications

The Application of Artificial Intelligence in Health Policy: A Scoping Review

The Application of Artificial Intelligence in Health Policy: A Scoping Review

A Comparative Study of Two Tree-Based Models for Predicting Flyrock Velocity at Open Pit Bench Mining

Unveiling non-communicable disease trends among Indian states: predicting health outcomes with socioeconomic and demographic factors

Contact Info

Product

Resources

About