Allocation Of Health Care Resources Research Articles

Application of Data Mining Techniques in Healthcare: Identifying Inter-Disease Relationships through Association Rule Mining

This research focuses on the application of data mining techniques in a healthcare environment by utilizing patient visit data from Hospital X, coded with ICD-10 diagnoses. The purpose of this study is to explore the application of data mining techniques in a healthcare environment, specifically to identify the relationship between diseases using patient visit data from X Hospital. This research utilizes the FP-Growth algorithm method followed by Association Rule Mining to find frequent occurrences of diseases in the data set. The research process involved data pre-processing, transformation into binary format, and careful parameter setting (minimum support 0.95 and confidence 0.9). The results showed a strong association between chronic conditions such as hypertension and diabetes, which are prevalent in the patient population. This association provides insight into potential comorbidities and may assist healthcare providers in improving diagnosis accuracy and treatment effectiveness. This research has implications for the application of data mining techniques, demonstrating its potential in improving predictive analytics in healthcare and strategic planning. This approach not only aids in the efficient allocation of healthcare resources, but also aligns with the broader goal of improving personalized patient care.

Final assessment of the COVID-19 pandemic impact between the different social and economic strata population of the city of Buenos Aires

BackgroundDuring the pandemic, epidemiological communications reported an estimation of excess deaths. However, the final calculation requires a detailed analysis. The study aim was to ascertain the number and distribution of COVID-19 fatalities among various socio-economic strata in a large, moderate to low-income city. Study designObservational time series analysis in a large city, treated as a natural experiment. MethodsAnalysis of death certificates, demographic data, and health system records of positive RT-PCR COVID-19 tests from 2015 to 2021, categorizing by age, sex, and place of residence. The study measured the pandemic's impact on mortality, including COVID and non-COVID deaths, using corrected Poisson regression models for different demographics and assessing socio-economic status impact via ecological community-level analysis. ResultsCompared to the pre-pandemic period (2015–2019, IRR = 1.00), the sex- and age-adjusted rate of all-cause death increased significantly during the pandemic (2020–2021) IRR = 1.109 [1.054–1.167], p < 0.0001. This was observed in both males (IRR = 1.158 [1.1–1.219], p < 0.0001) and females (IRR = 1.068 [1.016–1.124], p = 0.01). There was no observed effect of the pandemic on the historical trend in the progressive reduction of mortality in people under 35 years of age. The increase in deaths was at the expense of COVID (+11,175 deaths) and cardiovascular causes (IRR = 1.114 [1.020–1.217] p = 0.017). During the pandemic, there was a significant increase in deaths at home (IRR = 1.219 [1197–1.242], p < 0.0001), especially in people dying of cardiovascular causes (IRR = 1.391 [1.360–1.422], p < 0.0001). The increase in the adjusted mortality rate during the pandemic was socially conditioned. ConclusionsThe pandemic not only led to increased COVID-19 mortality but also heightened fatalities from non-COVID causes, reflecting a potential bias in healthcare resource allocation towards SARS-CoV-2 at the expense of chronic pathologies care.

Stroke 5.0: A Technology Ecosystem to Support Acute Stroke Integrated Clinical Management.

Stroke remains a significant global health burden, with substantial costs and morbidity associated with its occurrence. To address this challenge, STROKE 5.0 proposes a comprehensive approach to stroke care management, integrating advanced digital technologies and clinical expertise. This paper presents the rationale, design, and potential impact of the STROKE 5.0 platform, which aims to optimize stroke care delivery from pre-hospital assessment through acute hospitalization. The platform facilitates early symptom recognition, efficient emergency response, and streamlined hospital management through intelligent decision support systems. By leveraging predictive analytics and personalized care pathways, STROKE 5.0 seeks to enhance clinical outcomes while providing a platform capable of optimizing the efficiency of service delivery. This innovative model represents a proactive shift towards evidence-based, patient-centered stroke care, with implications for healthcare quality improvement and resource allocation in the digital health domain.

#2628 A haemodialysis patient-centred model of care with a multidisciplinary programme: what is its clinical and health efficiency impact?

Abstract Background and Aims Chronic kidney disease (CKD) constitutes a public health concern due to its notable morbidity &amp; mortality and associated costs. The Patient Care Coordination program (PCC) provides comprehensive and personalized care to haemodialysis (HD) patients. This study evaluated the cost-effectiveness of PCC compared to standard of care (SoC). Method The study included patients in 9 HD clinics (5 PCC, 4 SoC) in Catalonia, Spain, in 2020-2021. A comparative effectiveness evaluation was conducted to compare change in Individual Patient Performance Score (IPPS, score 0-100, evaluates parameters such as vascular access, adequacy of HD, anaemia, mineral bone disease, arterial hypertension, nutrition/hydration status) and number of hospitalisations of PCC patients vs SoC during the first year in the program. Instrumental variables (IV) regression analysis was performed to address potential confounding; number of interactions with program specialists was a valid IV to estimate degree of PCC use. An incremental cost-effectiveness analysis (iCEA) through microsimulation was performed using the effectiveness data from the previous step, population data from the renal patient registry of Catalonia, and the cost of hospitalisations obtained from the Public Health System. Results 127 patients in PCC and 363 patients in SoC were included. The degree of PCC use had a positive impact on IPPS variation during the first year of the program (p = 0.012). In the iCEA the PCC program resulted in a mean gain of 3.4 additional IPPS points, a reduction of 0.2 hospitalisations per patient, and reduced mean costs of €1,265 per patient in the first year compared to SoC, resulting to be a dominant alternative (Fig. 1). Conclusion The holistic and interdisciplinary approach to the patient has further highlighted the relevance of programme use and not only belonging to the programme in achieving clinical goals. The PCC program represents thus a dominant alternative, with greater effectiveness and total cost savings that could sum up to €5.5 million per year in the region due to reduced hospitalizations. This approach may be an alternative to address the challenges of CKD and optimise the allocation of healthcare resources.

Clinical prediction model for MODY type diabetes mellitus in children

BACKGROUND: MODY (maturity-onset diabetes of the young) is a rare monogenic form of diabetes mellitus, the gold standard of diagnosis is mutations detection in the genes responsible for the development of this form diabetes. Genetic test is expensive and takes a lot of time. The diagnostic criteria for MODY are well known. The development of clinical decision support system (CDSS) which allows physicians based on clinical data to determine who should have molecular genetic testing is relevant.AIM: Provided a retrospective analysis of clinical data of the patients with T1DM and MODY, from 0 to 18 years old, regardless of the duration of the disease to develop the model. Based on clinical data, a feedforward neural network (NN) was implemented - a multilayer perceptron.MATERIALS AND METHODS: Development of the most effective algorithm for predicting MODY in children based on available clinical indicators of 1710 patients with diabetes under the age of 18 years using a multilayer feedforward neural network.RESULTS: The sample consisted of 1710 children under the age of 18 years with T1DM (78%) and MODY (22%) diabetes. For the final configuration of NS the following predictors were selected: gender, age at passport age, age at the diagnosis with DM, HbA1c, BMI SDS, family history of DM, treatment. The performance (quality) assessment of the NN was carried out on a test sample (the area under the ROC (receiver operating characteristics) curve reached 0.97). The positive predictive value of PCPR was achieved at a cut-off value of 0.40 (predicted probability of MODY diabetes 40%). At which the sensitivity was 98%, specificity 93%, PCR with prevalence correction was 78%, and PCR with prevalence correction was 99%, the overall accuracy of the model was 94%.Based on the NN model, a CDSS was developed to determine whether a patient has MODY diabetes, implemented as an application.CONCLUSION: The clinical prediction model MODY developed in this work based on the NN, uses the clinical characteristic available for each patient to determine the probability of the patient having MODY. The use of the developed model in clinical practice will assist in the selection of patients for diagnostic genetic testing for MODY, which will allow for the efficient allocation of healthcare resources, the selection of personalized treatment and patient monitoring.

Cluster analysis in fibromyalgia: a systematic review.

The multifaceted nature of Fibromyalgia syndrome (FM) symptoms has been explored through clusters analysis. To synthesize the cluster research on FM (variables, methods, patient subgroups, and evaluation metrics). We performed a systematic review following the PRISMA recommendations. Independent searches were performed on PubMed, Embase, Web of Science, and Cochrane Central, employing the terms "fibromyalgia" and "cluster analysis". We included studies dated to January 2024, using the cluster analysis to assess any physical, psychological, clinical, or biomedical variables in FM subjects, and descriptively synthesized the studies in terms of design, cluster method, and resulting patient profiles. We included 39 studies. Most with a cross-sectional design aiming to classify subsets based on the severity, adjustment, symptomatic manifestations, psychological profiles, and response to treatment, based on demographic and clinical variables. Two to four different profiles were found according to the levels of severity and adjustment to FMS. According to symptom manifestation, two to three clusters described the predominance of pain versus fatigue, and thermal pain sensitivity (less versus more sensitive). Other clusters revealed profiles of personality (pathological versus non-pathological) and psychological vulnerability (suicidal ideation). Additionally, studies identified different responses to treatment (pharmacological and multimodal). Several profiles exist within FMS population, which point out to the need for specific treatment options given the different profiles and an efficient allocation of healthcare resources. We notice a need towards more objective measures, and the validation of the cluster results. Further research might investigate some of the assumptions of these findings, which are further discussed in this paper.

Precision healthcare: A deep dive into machine learning algorithms and feature selection strategies for accurate heart disease prediction

This paper presents a comprehensive exploration of machine learning algorithms (MLAs) and feature selection techniques for accurate heart disease prediction (HDP) in modern healthcare. By focusing on diverse datasets encompassing various challenges, the research sheds light on optimal strategies for early detection. MLAs such as Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM), Gaussian Naive Bayes (NB), and others were studied, with precision and recall metrics emphasized for robust predictions. Our study addresses challenges in real-world data through data cleaning and one-hot encoding, enhancing the integrity of our predictive models. Feature extraction techniques—Recursive Feature Extraction (RFE), Principal Component Analysis (PCA), and univariate feature selection—play a crucial role in identifying relevant features and reducing data dimensionality. Our findings showcase the impact of these techniques on improving prediction accuracy. Optimized models for each dataset have been achieved through grid search hyperparameter tuning, with configurations meticulously outlined. Notably, a remarkable 99.12 % accuracy was achieved on the first Kaggle dataset, showcasing the potential for accurate HDP. Model robustness across diverse datasets was highlighted, with caution against overfitting. The study emphasizes the need for validation of unseen data and encourages ongoing research for generalizability. Serving as a practical guide, this research aids researchers and practitioners in HDP model development, influencing clinical decisions and healthcare resource allocation. By providing insights into effective algorithms and techniques, the paper contributes to reducing heart disease-related morbidity and mortality, supporting the healthcare community's ongoing efforts.

Resisting the heat wave: Revealing inequalities in matching between heat exposure risk and healthcare services in a megacity

Climate warming and the growing urban heat island effect are exacerbating the unequal public health crisis in megacities, and thus it is important to assess the equity of matching relationship between the healthcare services and the heat exposure risk. We selected 255 census units in Tianjin city for the study, and calculated a heat exposure index based on the universal thermal climate index (UTCI) and constructed a comprehensive urban healthcare services evaluation system to measure the degree of mismatch between the two. The results showed the following. (1) The heat exposure risk and healthcare services followed an increasing pattern from the Outer suburb area (OSA) to the Metropolitan development area (MDA) and then to the Main urban area (MUA). (2) The overall imbalance in matching was low in the OSA, whereas the healthcare services were relatively insufficient in the MDA, and the heat exposure risk and healthcare services were relatively balanced in the MUA. (3) The degree of matching between the core and peripheral parts of the MUA was severely polarized, with an overall pattern of excess healthcare in the core area and a high risk of heat exposure in the peripheral areas. The results can provide effective guidance for rationalizing the allocation of healthcare resources from a heat exposure perspective, and provide a policy basis for risk management and fund investment.

Primary care clinic visits in formerly evacuated areas due to radiation disaster following the Great East Japan Earthquake: A retrospective descriptive study.

Radiation disasters pose distinctive medical challenges, requiring diverse care approaches. Beyond radiation exposure assessment, addressing health impacts due to lifestyle changes, especially among vulnerable populations, is vital. Evacuation orders issued in radiation-affected areas introduce unique healthcare dynamics, with their duration significantly influencing the recovery process. Understanding evolving patient demographics and medical needs after lifting evacuation orders is crucial for post-disaster care planning. Minamisoma Municipal Odaka Hospital, located 13 to 20 km from Fukushima Daiichi Nuclear power plant in a post-evacuation zone, was greatly affected by the Great East Japan Earthquake and subsequent radiation disaster. Data were retrospectively collected from patient records, including age, gender, visit date, diagnoses, and addresses. Patient records from April 2014 to March 2020 were analyzed, comparing data before and after the July 2016 evacuation order lift. Data was categorized into pre and post-evacuation order lifting periods, using International Classification of Diseases, Tenth Edition codes, to identify the top diseases. Statistical analyses, including χ-square tests, assessed changes in disease distributions. Population data for Odaka Ward and Minamisoma City fluctuated after lifting evacuation orders. As of March 11, 2011, Odaka Ward had 12,842 residents (27.8% aged 65+ years), dropping to 8406 registered residents and 2732 actual residents by April 30, 2018 (49.7%). Minamisoma City also saw declines, with registered residents decreasing from 71,561 (25.9%) to 61,049 (34.1%). The study analyzed 11,100 patients, mostly older patients (75.1%), between 2014 and 2020. Post-lifting, monthly patient numbers surged from an average of 55.2 to 213.5, with female patients increasing from 33.8% to 51.7%. Disease patterns shifted, with musculoskeletal cases declining from 23.8% to 13.0%, psychiatric disorders increasing from 9.3% to 15.4%, and trauma-related cases decreasing from 14.3% to 3.9%. Hypertension (57.1%) and dyslipidemia (29.2%) prevailed post-lifting. Urgent cases decreased from 1.3% to 0.1%. This study emphasizes the importance of primary care in post-evacuation zones, addressing diverse medical needs, including trauma, noncommunicable diseases, and psychiatric disorders. Changing patient demographics require adaptable healthcare strategies and resource allocation to meet growing demands. Establishing a comprehensive health maintenance system tailored to these areas' unique challenges is crucial for future disaster recovery efforts.

TEMPORAL TRENDS AND REGIONAL VARIATION OF HIP ARTHROSCOPY AND PELVIC OSTEOTOMY IN ENGLAND FROM 2010 TO 2023

Hip arthroscopy (HA) and pelvic osteotomy (PO) are surgical procedures used to treat a variety of hip pathology affecting young adults, including femoroacetabular impingement and hip dysplasia respectively. This study aimed to investigate the trends and regional variation in the provision of HA and PO across England from 2010 to 2023 to inform healthcare resource allocation.We analysed the National Hospital Episode Statistics database for all HA and PO procedures in NHS England using specific OPCS-4 codes: HA: ‘W83+Z843’ or ‘W84+Z843’; PO: ‘X222+Z75’. We collected patient demographics, age, sex, and region of treatment. We performed descriptive and regression analyses to evaluate temporal trends in PO volume, age, sex and regional variation.22,401 HAs and 1,348 POs were recorded between 2010 and 2023. The annual number of HAs declined by 28.4%, whilst the number of POs increased by 64% (p&lt;0.001). Significantly more females underwent PO vs HA (90% vs 61.3%) and were older than males undergoing the same procedure (PO: 29.0±8.7 vs 25.8±9.2 years; HA: 36.8±12.0 years vs 35.8±11.2 years, p&lt;0.001). For HA, the mean age of both sexes decreased by 3.3 and 2.9 years respectively (p&lt;0.001), whereas the age of PO patients did not change significantly over the study period. There were significant regional variations with a mean incidence of 1.60/100,00 for HA (ranging from 0.70–2.66 per 100,000) and 0.43/100,000 for PO (ranging from 0.08–2.07 per 100,000).We have observed a decline in HA volume in England, likely due to improved patient selection and the impact of COVID-19, whilst PO volume has significantly increased, with regional variation persisting for both procedures. These trends highlight the need for equitable HA and PO access to improve patient outcomes and call for strategic healthcare planning and resource allocation to reduce disparities and improve training opportunities.

Projecting the economic burden of chronic kidney disease at the patient level (Inside CKD): a microsimulation modelling study

The growing burden of chronic kidney disease (CKD) places substantial financial pressures on patients, healthcare systems, and society. An understanding of the costs attributed to CKD and kidney replacement therapy (KRT) is essential for evidence-based policy making. Inside CKD maps and projects the economic burden of CKD across 31 countries/regions from 2022 to2027. A microsimulation model was developed that generated virtual populations using national demographics, relevant literature, and renal registries for the 31 countries/regions included. Patient-level country/region-specific cost data were extracted via a pragmatic local literature review and under advisement from local experts. Direct cost projections were generated for diagnosed CKD (by age, stage 3a-5), KRT (by modality), cardiovascular complications (heart failure, myocardial infarction, stroke), and comorbidities (hypertension, type 2 diabetes). For the 31 countries/regions, Inside CKD projected that annual direct costs (US$) of diagnosed CKD and KRT would increase by 9.3% between 2022 and 2027, from $372.0 billion to $406.7 billion. Annual KRT-associated costs were projected to increase by 10.0% from $169.6 billion to $186.6 billion between 2022 and 2027. By 2027, patients receiving KRT are projected to constitute 5.3% of the diagnosed CKD population but contribute 45.9% of the total costs. The economic burden of CKD is projected to increase from 2022 to 2027. KRT contributes disproportionately to this burden. Earlier diagnosis and proactive management could slow disease progression, potentially alleviating the substantial costs associated with later CKD stages. Data presented here can be used to inform healthcare resource allocation and shape future policy. AstraZeneca.

Spatial distribution and influencing factors of CDC health resources in China: a study based on panel data from 2016-2021.

Measuring the development of Chinese centers for disease control and prevention only by analyzing human resources for health seems incomplete. Moreover, previous studies have focused more on the quantitative changes in healthcare resources and ignored its determinants. Therefore, this study aimed to analyze the allocation of healthcare resources in Chinese centers for disease control and prevention from the perspective of population and spatial distribution, and to further explore the characteristics and influencing factors of the spatial distribution of healthcare resources. Disease control personnel density, disease control and prevention centers density, and health expenditures density were used to represent human, physical, and financial resources for health, respectively. First, health resources were analyzed descriptively. Then, spatial autocorrelation was used to analyze the spatial distribution characteristics of healthcare resources. Finally, we used spatial econometric modeling to explore the influencing factors of healthcare resources. The global Moran index for disease control and prevention centers density decreased from 1.3164 to 0.2662 (p < 0.01), while the global Moran index for disease control personnel density increased from 0.4782 to 0.5067 (p < 0.01), while the global Moran index for health expenditures density was statistically significant only in 2016 (p < 0.1). All three types of healthcare resources showed spatial aggregation. Population density and urbanization have a negative impact on the disease control and prevention centers density. There are direct and indirect effects of disease control personnel density and health expenditures density. Population density and urbanization had significant negative effects on local disease control personnel density. Urbanization has an indirect effect on health expenditures density. There were obvious differences in the spatial distribution of healthcare resources in Chinese centers for disease control and prevention. Social, economic and policy factors can affect healthcare resources. The government should consider the rational allocation of healthcare resources at the macro level.

Clinical and Epidemiological Profile of Otorhinolaryngology Diseases at a Tertiary Hospital in Morang District: A Descriptive Cross-Sectional Study

Introduction: Otorhinolaryngology, dealing with disorders of the ears, nose, throat, and related structures, poses significant health challenges. However, there is a dearth of extensive clinical and epidemiological data on these ailments in the specific geographic area under study. Understanding the characteristics of otorhinolaryngology diseases is crucial for effective healthcare planning and resource allocation. Objective: This study aimed to determine the clinical and epidemiological profile of otorhinolaryngology diseases at a tertiary hospital in Morang District, Nepal. Methodology: An observational descriptive cross-sectional study was conducted at the Otorhinolaryngology department of a tertiary hospital in eastern Nepal from January 15 to February 15, 2024. Data from 600 patients presenting at the department over one month were meticulously analyzed. Results: The median age of patients was 28 years, with the most prevalent age group being 21- 30 years (23%). A majority (56%) were male, and belonged to the Brahmin/Chhetri caste (44.3%). Most patients (85%) initially visited the hospital through OPD, with ear-related issues (35.2%) being the most common complaint. Epistaxis (10.3%) was the most frequent diagnosis, followed by allergic rhinitis (9%) and ear wax issues (8.2%). The prevalence of carcinoma was 12(2%). The majority (77.3%) underwent medical treatment. Outpatient admissions were observed in 68(13.3%) of cases, with emergency admissions accounting for 42(62.6%). Conclusion: Epistaxis, allergic rhinitis, and ear wax problems were commonly encountered. Most patients underwent medical treatment, with only a minority requiring hospital admission, primarily through outpatient services.

Academic Productivity in Ophthalmology and Its Correlation to National Economic Indicators Among the OECD Countries: A Bibliometric Analysis

ABSTRACT Purpose Prompted by the clinical concern that limited healthcare resources allocation affects physicians’ research productivity, this study examines the association between bibliometric indices of ophthalmologic research and national economic indicators in Organisation for Economic Co-operation and Development (OECD) countries. Methods The Scimago Journal and Country rank source was searched for research productivity data in ophthalmology among OECD countries between 1996 and 2019. Bibliometric indices included: documents number, number and percent of citable documents, citations number, citations per document, and H-index. The updated economic indicators of each country (gross domestic product [GDP] per capita, health spending as percent of GDP (health expenditure), gross domestic expenditure on research, and development as percent of GDP [GERD]) were collected from the World Bank and the OECD websites. Correlation between economic and bibliometric metrics and multivariate linear regression analyses were performed. Results Among 267,444 documents analyzed, correlation analysis found a strong correlation between health expenditure and H index (r = 0.711, p < 0.001); a moderate correlation between health expenditure and documents number (r = 0.589, p < 0.001), number of citable document (r = 0.593, p < 0.001) and citations number (r = 0.673, p < 0.001); and a moderate correlation between GERD and H index (r = 0.564, p < 0.001). Multivariate regression analysis controlling for economic factors, population and language showed the independent association of these parameters with bibliometric indices. Conclusions This study demonstrates a positive correlation between bibliometric indicators of ophthalmology research and economic factors, particularly health expenditure, among the OECD countries. Our results suggest an advantage of domestic investment in health to expand academic productivity in the field of ophthalmology.

Effectiveness and Satisfaction with Telemedicine in Geriatric Patients at High Risk of Fragility Fractures.

Background: Telemedicine has increasingly widespread to improve the monitoring of patients with chronic diseases. Secondary prevention of fragility fractures is an urgent matter to be addressed by means of available technology, although supported by little evidence so far. We investigated the feasibility, efficacy, and satisfaction of managing older adults at high risk of fragility fractures during the COVID-19 lockdown. Methods: During the period January to July 2021, a prospective observational study for safety and adherence purposes was conducted among older adults (n = 407) with ongoing treatments for secondary prevention of fragility fractures. The study procedures comply with national and regional resolutions related to telemedicine service (TS), including equipment, staff behaviors, and patient reports. Results: A majority (86.48% [n = 352]) of the eligible patients joined the remote visits, mainly women (88.2%), 81.4 ± 8.8 years of age, 49.6% independent in 5 out of 6 BADL, despite high comorbidity (4.9 ± 1.5), and polypharmacy (4.9 ± 3.1). Almost all were on second-line antifracture treatments (95.58%) due to previous major (84.03%) and minor (42.5%) fragility fractures. About 58% reported good and very good reliability of the internet network, allowing easy access to the TS platform, and 54% declared the degree of satisfaction with TS as good and very good. About 75% of clinicians acknowledged the efficacy of TS and expressed willingness to recommend the use of TS to colleagues. Ultimately, 68% of specialists defined the time allocated for patients' remote visits as acceptable. Conclusion: TS may be an opportunity to improve the availability of appropriate health care services to satisfy patients' needs and optimize health care resource allocation.

Healthcare Resource Allocation Optimization

Assuring high-quality patient care and making the best use of the resources at hand requires the efficient allocation of healthcare resources. This study uses a thorough examination of patient admission data, treatment plans, and staff availability to tackle the complex problem of optimizing healthcare resource allocation. We want to reduce wait times, optimize resource use, and eventually improve patient outcomes in healthcare facilities by integrating these essential elements. Our strategy makes use of cutting-edge data analytics tools, such as optimization algorithms and predictive modelling, to find underlying patterns and trends in patient demand, treatment regimens, and staffing needs. Our goal is to create prediction models that anticipate patient admissions, treatment requirements, and staffing levels by analysing historical data and real-time inputs. This will allow for proactive resource allocation techniques. The study's conclusions have important ramifications for healthcare administration since they provide practical advice on how to improve patient care delivery, cut wait times, and make the most use of the resources at hand. Healthcare institutions can enhance resource allocation procedures to meet the changing demands of patient care while guaranteeing the optimal use of resources by integrating technology, data-driven decision-making, and evidence-based practices. In summary, this study lays the groundwork for future investigations and innovations in hospital administration and operations while also supporting current initiatives to enhance healthcare resource allocation procedures. Healthcare organizations can improve patient outcomes and achieve operational excellence while providing high-quality, patient-centred care by adopting data-driven approaches and utilizing technology.

A cost-effectiveness analysis of fluoride varnish application in preventing Root caries in elderly persons: a Markov simulation study

BackgroundRoot caries are prevalent issues that affect dental health, particularly among elderly individuals with exposed root surfaces. Fluoride therapy has shown effectiveness in preventing root caries, but limited studies have addressed its cost-effectiveness in elderly persons population. This study aimed to evaluate the cost-effectiveness of a fluoride treatment program for preventing root caries in elderly persons within the context of Chinese public healthcare.MethodsA Markov simulation model was adopted for the cost-effectiveness analysis in a hypothetical scenario from a healthcare system perspective. A 60-year-old subject with 23 teeth was simulated for 20 years. A 5% sodium fluoride varnish treatment was compared with no preventive intervention in terms of effectiveness and cost. Tooth years free of root caries were set as the effect. Transition probabilities were estimated from the data of a community-based cohort and published studies, and costs were based on documents published by the government. The incremental cost-effectiveness ratio (ICER) was calculated to evaluate cost-effectiveness. Univariate and probabilistic sensitivity analyses were performed to evaluate the influence of data uncertainty.ResultsFluoride treatment was more effective (with a difference of 10.20 root caries-free tooth years) but also more costly (with a difference of ¥1636.22). The ICER was ¥160.35 per root caries-free tooth year gained. One-way sensitivity analysis showed that the risk ratio of root caries in the fluoride treatment group influenced the result most. In the probabilistic sensitivity analysis, fluoride treatment was cost-effective in 70.5% of the simulated cases.ConclusionsRegular 5% sodium fluoride varnish application was cost-effective for preventing root caries in the elderly persons in most scenarios with the consideration of data uncertainty, but to a limited extent. Improved public dental health awareness may reduce the incremental cost and make the intervention more cost-effective. Overall, the study shed light on the economic viability and impact of such preventive interventions, providing a scientific basis for dental care policies and healthcare resource allocation.

EQ-5D-3L and EQ-5D-5L population norms for Thailand

BackgroundThe previous Thai norm-based scores for the EQ-5D-5L were established with Thai general population samples aged 20–70 years in 2019. Nevertheless, these values need to be updated after the COVID-19 pandemic because of its effects on both physical and mental health. This study therefore aimed to establish population norms of the Thai EQ-5D-3L, EQ-5D-5L and EQ-VAS scores as well as to estimate disutility values associated with self-reported main diseases.MethodsIndividual face-to-face interviews were conducted with 2000 adult (age ≥ 18 years) members of the general Thai population to estimate norm-based scores. Each participant completed the EQ-5D-3L and EQ-5D-5L as well as questions related to their sociodemographic factors and self-reported main diseases. Responses to the two instruments were converted to health utility (HU) scores on the basis of available value sets. Descriptive statistics were used to report the norm-based scores stratified by age and sex categories. Response redistribution determining the response consistency between EQ-5D versions was investigated. The HU score agreement from those two instruments was investigated using intraclass correlation coefficient (ICC). Tobit regression models were employed to investigate the relationships between sociodemographic factors and HU and EQ-VAS scores. Moreover, it was used to estimate the disutility values associated with self-reported main diseases.ResultsThe means (percentage of ceiling effects) of EQ-5D-3L, EQ-5D-5L, and EQ-VAS scores were 0.845 (57.80%), 0.923 (49.05%), and 79.83 (3.20%), respectively. The average percentage of inconsistent response was 1.09%. A good agreement level was found between both EQ-5D versions with the ICCs of 0.789 (95% CI: 0.558–0.878). Female, older, and unemployed participants and those with BMI ≥ 30 reported lower EQ-5D-3L and EQ-5D-5L than their counterparts. Bone/Joint disorder and stroke contributed to the largest disutility value for those two instruments.ConclusionsThe Thai norm-based scores from those two instruments were diminished when advancing age and among female, unemployed, and obese (BMI ≥ 30) participants. It is expected to provide information to policy makers to better allocate health care resources to those with diminished norm-based scores.

Development and comparison of machine-learning models for predicting prolonged postoperative length of stay in lung cancer patients following video-assisted thoracoscopic surgery

ObjectiveThis study aimed to develop models for predicting prolonged postoperative length of stay (PPOLOS) in lung cancer patients undergoing video-assisted thoracoscopic surgery (VATS) by utilizing machine-learning techniques. These models aim to offer valuable insights for clinical decision-making. MethodsThis retrospective cohort study analyzed a dataset of lung cancer patients who underwent VATS, identifying 25 numerical features and 45 textual features. Three classification machine-learning models were developed: XGBoost, random forest, and neural network. The performance of these models was evaluated based on accuracy (ACC) and area under the receiver operating characteristic curve, whereas the importance of variables was assessed using the feature importance parameter from the random forest model. ResultsOf the 6767 lung cancer patients, 1481 patients (21.9%) experienced a postoperative length of stay of > 4 days. The majority were male (4111, 60.8%), married (6246, 92.3%), and diagnosed with adenocarcinoma (4145, 61.3%). The Random Forest classifier exhibited superior prediction performance with an area under the curve (AUC) of 0.792 and ACC of 0.804. The calibration plot revealed that all three classifiers were in close alignment with the ideal calibration line, indicating high calibration reliability. The five most critical features identified were the following: surgical duration (0.116), age (0.066), creatinine (0.062), hemoglobin (0.058), and total protein (0.054). ConclusionsThis study developed and evaluated three machine-learning models for predicting PPOLOS in lung cancer patients undergoing VATS. The findings revealed that the Random Forest model is most accurately predicting the PPOLOS. Findings of this study enable the identification of crucial determinants and the formulation of targeted interventions to shorten the length of stay among lung cancer patients after VATS, which contribute to optimize the allocation of healthcare resources.

Development and validation of machine learning models to predict frailty risk for elderly.

Early identification and intervention of the frailty of the elderly will help lighten the burden of social medical care and improve the quality of life of the elderly. Therefore, we used machine learning (ML) algorithm to develop models to predict frailty risk in the elderly. A prospective cohort study. We collected data on 6997 elderly people from Chinese Longitudinal Healthy Longevity Study wave 6-7 surveys (2011-2012, 2014). After the baseline survey in 1998 (wave 1), the project conducted follow-up surveys (wave 2-8) in 2000-2018. The osteoporotic fractures index was used to assess frailty. Four ML algorithms (random forest [RF], support vector machine, XGBoost and logistic regression [LR]) were used to develop models to identify the risk factors of frailty and predict the risk of frailty. Different ML models were used for the prediction of frailty risk in the elderly and frailty risk was trained on a cohort of 4385 elderly people with frailty (split into a training cohort [75%] and internal validation cohort [25%]). The best-performing model for each study outcome was tested in an external validation cohort of 6997 elderly people with frailty pooled from the surveys (wave 6-7). Model performance was assessed by receiver operating curve and F2-score. Among the four ML models, the F2-score values were similar (0.91 vs. 0.91 vs. 0.88 vs. 0.90), and the area under the curve (AUC) values of RF model was the highest (0.75), followed by LR model (0.74). In the final two models, the AUC values of RF and LR model were similar (0.77 vs. 0.76) and their accuracy was identical (87.4% vs. 87.4%). Our study developed a preliminary prediction model based on two different ML approaches to help predict frailty risk in the elderly. The presented models from this study can be used to inform healthcare providers to predict the frailty probability among older adults and maybe help guide the development of effective frailty risk management interventions. Detecting frailty at an early stage and implementing timely targeted interventions may help to improve the allocation of health care resources and to reduce frailty-related burden. Identifying risk factors for frailty could be beneficial to provide tailored and personalized care intervention for older adults to more accurately prevent or improve their frail conditions so as to improve their quality of life. The study has adhered to STROBE guidelines. No patient or public contribution.