Optimizing Budget Allocation for Digital Health Investments Using Metaheuristic Algorithms: A Cost–Impact Analysis for Public Health Systems
Özet
Background: In the era of digital transformation, public health systems increasingly rely on digital technologies to improve accessibility, efficiency, and patient outcomes. However, policymakers face significant challenges in allocating limited resources across competing digital health investments characterized by uncertainty and dynamic impacts. Methods: This study introduces the Adaptive Impact–Cost Optimization Theory (AICOT), a hybrid framework integrating fuzzy logic and genetic algorithms to optimize digital health investment portfolios. The model defines the Investment Priority Score (IPS) as a function of cost, expected impact, and implementation feasibility, enabling structured evaluation under uncertainty. A fuzzy inference system with centroid-based defuzzification is used to convert qualitative assessments into quantitative scores, while optimization techniques identify optimal portfolios across different fiscal scenarios. The empirical analysis covers 15 OECD countries (2018–2024) using publicly available datasets. Sensitivity analyses assess robustness under inflation, cost shocks, and changing system priorities. Results: The findings show that blended investment strategies combining routine digital health tools with pandemic-oriented infrastructures yield the highest resilience-adjusted efficiency. Results remain stable across sensitivity scenarios, with pandemic surveillance consistently ranking as a top priority even under increased cost conditions. The model effectively captures cross-country heterogeneity, demonstrating adaptability to different levels of digital maturity. Conclusions: AICOT provides a transparent and policy-relevant decision-support framework that improves resource allocation efficiency and reduces unnecessary expenditures. These contributions support long-term financial sustainability and align with global health objectives, including Universal Health Coverage and Sustainable Development Goal 3 (Good Health and Well-being).
Anahtar Kelimeler
- Scopus
- 1
- WoS
- 1
- OpenAlex
- 1
Tam Kayıt
| Alan | Değer | Dil |
|---|---|---|
| dc.contributor.author | Dayi, Faruk | |
| dc.contributor.author | Erdogdu, Aylin | |
| dc.contributor.author | Esmer, Yusuf | |
| dc.contributor.author | Yildiz, Ferah | |
| dc.contributor.author | Ganji, Farshad | |
| dc.date.accessioned | 2026-10-29T19:08:32.123183965Z | |
| dc.date.available | 2026-10-29T19:08:32.123183965Z | |
| dc.date.issued | 2026 | |
| dc.description.abstract | Background: In the era of digital transformation, public health systems increasingly rely on digital technologies to improve accessibility, efficiency, and patient outcomes. However, policymakers face significant challenges in allocating limited resources across competing digital health investments characterized by uncertainty and dynamic impacts. Methods: This study introduces the Adaptive Impact–Cost Optimization Theory (AICOT), a hybrid framework integrating fuzzy logic and genetic algorithms to optimize digital health investment portfolios. The model defines the Investment Priority Score (IPS) as a function of cost, expected impact, and implementation feasibility, enabling structured evaluation under uncertainty. A fuzzy inference system with centroid-based defuzzification is used to convert qualitative assessments into quantitative scores, while optimization techniques identify optimal portfolios across different fiscal scenarios. The empirical analysis covers 15 OECD countries (2018–2024) using publicly available datasets. Sensitivity analyses assess robustness under inflation, cost shocks, and changing system priorities. Results: The findings show that blended investment strategies combining routine digital health tools with pandemic-oriented infrastructures yield the highest resilience-adjusted efficiency. Results remain stable across sensitivity scenarios, with pandemic surveillance consistently ranking as a top priority even under increased cost conditions. The model effectively captures cross-country heterogeneity, demonstrating adaptability to different levels of digital maturity. Conclusions: AICOT provides a transparent and policy-relevant decision-support framework that improves resource allocation efficiency and reduces unnecessary expenditures. These contributions support long-term financial sustainability and align with global health objectives, including Universal Health Coverage and Sustainable Development Goal 3 (Good Health and Well-being). | |
| dc.identifier.articlenumber | 1540 | |
| dc.identifier.doi | 10.3390/healthcare14111540 | |
| dc.identifier.eissn | 2227-9032 | |
| dc.identifier.issn | 2227-9032 | |
| dc.identifier.issue | 11 | |
| dc.identifier.pmcid | PMC13256940 | |
| dc.identifier.pmid | 42278795 | |
| dc.identifier.scopus | 2-s2.0-105041409944 | |
| dc.identifier.uri | https://rdlopen.rawdatalibrary.net/r/bayburt/11561 | |
| dc.identifier.volume | 14 | |
| dc.identifier.wos | WOS:001789963000001 | |
| dc.language.iso | en | |
| dc.publisher | Multidisciplinary Digital Publishing Institute (MDPI) | |
| dc.relation.ispartof | Healthcare (Switzerland) | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.subject | AICOT | |
| dc.subject | cost–impact optimization | |
| dc.subject | digital health investment | |
| dc.subject | fuzzy logic | |
| dc.subject | genetic algorithm | |
| dc.subject | health economics | |
| dc.subject | public health system | |
| dc.subject.classification | Health Care Sciences & Services | |
| dc.subject.classification | Health Policy & Services | |
| dc.subject.other | analysis | |
| dc.subject.other | Article | |
| dc.subject.other | artificial intelligence | |
| dc.subject.other | clinical decision support system | |
| dc.subject.other | cost impact analysis | |
| dc.subject.other | digital health | |
| dc.subject.other | electronic health record | |
| dc.subject.other | fuzzy system | |
| dc.subject.other | genetic algorithm | |
| dc.subject.other | health economics | |
| dc.subject.other | hospital admission | |
| dc.subject.other | human | |
| dc.subject.other | metaheuristics | |
| dc.subject.other | particle swarm optimization | |
| dc.subject.other | public health | |
| dc.subject.other | quality adjusted life year | |
| dc.subject.other | quality control | |
| dc.subject.other | sensitivity analysis | |
| dc.title | Optimizing Budget Allocation for Digital Health Investments Using Metaheuristic Algorithms: A Cost–Impact Analysis for Public Health Systems | |
| dc.type | Article | |
| rdl.citation.openalex | 1 | |
| rdl.citation.scopus | 1 | |
| rdl.citation.wos | 1 | |
| rdl.department | Faculty of Economics and Administrative Sciences, Kastamonu University, 37160 Kastamonu, Türkiye | |
| rdl.department | Faculty of Economics and Administrative Sciences, İstanbul Arel University, 34295 İstanbul, Türkiye | |
| rdl.department | Faculty of Applied Sciences, Bayburt University, 69300 Bayburt, Türkiye | |
| rdl.department | Faculty of Management, Kocaeli University, 41350 Kocaeli, Türkiye | |
| rdl.department | Software Development Department, Istanbul Aydin University, 34295 İstanbul, Türkiye | |
| rdl.oa.status | gold | |
| rdl.oa.status | green | |
| rdl.oa.url | https://doi.org/10.3390/healthcare14111540 | |
| rdl.scopus.quartile | Q1 | |
| rdl.sdg | SDG09 | |
| rdl.sdg | SDG03 | |
| rdl.source.index | SCOPUS | |
| rdl.source.index | WOS | |
| rdl.source.index | PUBMED | |
| rdl.wos.index | Science Citation Index Expanded (SCI-EXPANDED) | |
| rdl.wos.index | Social Science Citation Index (SSCI) |


