Category: Statistics

Epidemiol Psychiatr Sci. 2025 Jan 23;34:e6. doi: 10.1017/S2045796024000842.

ABSTRACT

AIMS: Although individuals with lower socio-economic position (SEP) have a higher prevalence of mental health problems than others, there is no conclusive evidence on whether mental healthcare (MHC) is provided equitably. We investigated inequalities in MHC use among adults in Stockholm County (Sweden), and whether inequalities were moderated by self-reported psychological distress.

METHODS: MHC use was examined in 31,433 individuals aged 18-64 years over a 6-month follow-up period, after responding to the General Health Questionnaire-12 (GHQ-12) in 2014 or the Kessler Six (K6) in 2021. Information on their MHC use and SEP indicators, education, and household income, were sourced from administrative registries. Logistic and negative binomial regression analyses were used to estimate inequalities in gained MHC access and frequency of outpatient visits, with psychological distress as a moderating variable.

RESULTS: Individuals with lower education or income levels were more likely to gain access to MHC than those with high SEP, irrespective of distress levels. Education-related differences in gained MHC access diminished with increasing distress, from a 74% higher likelihood when reporting no distress (odds ratio, OR = 1.74 [95% confidence interval, 95% CI: 1.43-2.12]) to 30% when reporting severe distress (OR = 1.30 [0.98-1.72]). Comparable results were found for secondary care but not primary care i.e., lower education predicted reduced access to primary care in moderate-to-severe distress groups (e.g., OR = 0.63 [0.45-0.90]), and for physical but not digital services. Income-related differences in gained MHC access remained stable or increased with distress, especially for secondary care and physical services.

CONCLUSIONS: Overall, individuals with lower education and income used MHC services more than their counterparts with higher socio-economic status; however, low-educated individuals faced inequities in primary care and underutilized non-physician services such as visits to psychologists.

PMID:39846121 | DOI:10.1017/S2045796024000842

Afr J Prim Health Care Fam Med. 2024 Dec 18;16(1):e1-e8. doi: 10.4102/phcfm.v16i1.4654.

ABSTRACT

BACKGROUND: For continuity and quality of care, accurate record-keeping is crucial. Complete care is facilitated by completing a child’s Road to Health Booklet (RTHB) as well as prompt interpretation and appropriate action. This could result in a decrease in child morbidity and mortality.

AIM: The study was aimed at assessing the completeness of the RTHB of children younger than 5 years.

SETTING: Temba Community Health Centre (CHC), Tshwane District, South Africa.

METHODS: A cross-sectional study was conducted using a data collection sheet adopted from previous studies.

RESULTS: Children less than 1-year-old accounted for 70.2% of the 255 RTHBs. The mean ± s.d. age was 11.5 ±10.76 months. The study finding showed no section was 100% fully completed. Of the 255 records studied, 38 (14.9%) human immunodeficiency virus (HIV)-exposed babies were recorded at birth, 39.5% were negative at 6 weeks and 60.5% were not recorded. Ninety-one (35.7%) children were unexposed. The HIV status of 126 (49.4%) children was not recorded. Sixty-six per cent (66%) of recorded maternal syphilis was negative. Immunisations, weight-for-age, neonatal information, and details of the family and child were fully completed in 80% of the booklets. Developmental screening was 17.2% completed, and oral health was 1.6% partially completed. The overall completeness was 40.3%.

CONCLUSION: The completeness of RTHBs was found to be suboptimal.Contribution: The present study’s findings should serve as a reminder that healthcare practitioners must complete RTHBs in their totality in order to improve continuity and care quality, as the results indicated that RTHB completion was below ideal.

PMID:39846111 | DOI:10.4102/phcfm.v16i1.4654

Afr J Prim Health Care Fam Med. 2024 Dec 19;16(1):e1-e6. doi: 10.4102/phcfm.v16i1.4685.

ABSTRACT

BACKGROUND: Oral pre-exposure prophylaxis (PrEP) uses antiretroviral medication to reduce HIV risk in HIV-negative individuals. Despite its effectiveness, global uptake faces policy and accessibility challenges. In Eswatini, PrEP introduction in 2017 showed promise despite stigma and COVID-19 disruptions.

AIM: This study compared PrEP uptake and retention during and after COVID-19.

SETTING AND METHODS: An analytical cross-sectional study was conducted among clients accessing HIV testing services in selected Eswatini facilities. Data from the HIV testing register, PrEP register, and Client Management Information System (CMIS) were analysed. Uptake, retention, and client outcomes were measured during COVID-19 (March 2020-March 2021) and post-COVID-19 (April 2021-April 2022).

RESULTS: Of 5286 clients, 45% (n = 2380) initiated PrEP during COVID-19, while 55% (n = 2906) initiated post-pandemic. Facility 3 had the highest initiations during COVID-19 (844), while Facility 5 had the lowest (7). Retention was lower among clients aged 15-29 years. Females initially showed higher retention odds (odds ratio [OR]: 1.50), but this was insignificant after adjusting for confounders. Clients initiated post-COVID-19 had higher retention odds (OR: 2.96).

CONCLUSION: COVID-19 impacted PrEP uptake in Eswatini, emphasising the need for flexible healthcare delivery. Targeted campaigns and tailored interventions are crucial for sustaining HIV prevention efforts and addressing demographic shifts.Contribution: This study highlights the importance of responsive healthcare systems and tailored approaches to maintaining HIV prevention during public health crises.

PMID:39846107 | DOI:10.4102/phcfm.v16i1.4685

Q J Exp Psychol (Hove). 2025 Jan 23:17470218251317372. doi: 10.1177/17470218251317372. Online ahead of print.

ABSTRACT

The link between the cognitive effort of word processing and the eye movement patterns elicited by that word is well established in psycholinguistic research using eye tracking. Yet less evidence or consensus exists regarding whether the same link exists between complexity linguistic complexity measures of a sentence or passage, and eye movements registered at the sentence or passage level. This paper focuses on “global” measures of syntactic and lexical complexity, i.e., the measures that characterise the structure of the sentence or passage rather than aggregate lexical properties of individual words. We selected several commonly used global complexity measures and tested their predictive power against sentence- and passage-level eye movements in samples of text reading from 13 languages represented in the Multilingual Eye Movement Corpus (MECO). While some syntactic or lexical complexity measures elicited statistically significant effects, they were negligibly small and not of practical relevance for predicting the processing effort either in individual languages or across languages. These findings suggest that the “eye-mind” link known to be valid at the word level may not scale up to larger linguistic units.

PMID:39846106 | DOI:10.1177/17470218251317372

Eur Heart J Digit Health. 2024 Nov 20;6(1):147-154. doi: 10.1093/ehjdh/ztae083. eCollection 2025 Jan.

ABSTRACT

AIMS: Data availability remains a critical challenge in modern, data-driven medical research. Due to the sensitive nature of patient health records, they are rightfully subject to stringent privacy protection measures. One way to overcome these restrictions is to preserve patient privacy by using anonymization and synthetization strategies. In this work, we investigate the effectiveness of these methods for protecting patient privacy using real-world cardiology health records.

METHODS AND RESULTS: We implemented anonymization and synthetization techniques for a structure data set, which was collected during the HiGHmed Use Case Cardiology study. We employed the data anonymization tool ARX and the data synthetization framework ASyH individually and in combination. We evaluated the utility and shortcomings of the different approaches by statistical analyses and privacy risk assessments. Data utility was assessed by computing two heart failure risk scores on the protected data sets. We observed only minimal deviations to scores from the original data set. Additionally, we performed a re-identification risk analysis and found only minor residual risks for common types of privacy threats.

CONCLUSION: We could demonstrate that anonymization and synthetization methods protect privacy while retaining data utility for heart failure risk assessment. Both approaches and a combination thereof introduce only minimal deviations from the original data set over all features. While data synthesis techniques produce any number of new records, data anonymization techniques offer more formal privacy guarantees. Consequently, data synthesis on anonymized data further enhances privacy protection with little impacting data utility. We share all generated data sets with the scientific community through a use and access agreement.

PMID:39846076 | PMC:PMC11750188 | DOI:10.1093/ehjdh/ztae083

Eur Heart J Digit Health. 2024 Nov 11;6(1):63-72. doi: 10.1093/ehjdh/ztae085. eCollection 2025 Jan.

ABSTRACT

AIMS: Aortic stenosis (AS) is a common and progressive disease, which, if left untreated, results in increased morbidity and mortality. Monitoring and follow-up care can be challenging due to significant variability in disease progression. This study aimed to develop machine learning models to predict the risks of disease progression and mortality in patients with mild AS.

METHODS AND RESULTS: A comprehensive database including 9611 patients with serial transthoracic echocardiograms was collected from a single institution across three clinical sites. The data set included parameters from echocardiograms, electrocardiograms, laboratory values, and diagnosis codes. Data from a single clinical site were preserved as an independent test group. Machine learning models were trained to identify progression to severe stenosis and all-cause mortality and tested in their performance for endpoints at 2 and 5 years. In the independent test group, the AS progression model differentiated those with progression to severe AS within 2 and 5 years with an area under the curve (AUC) of 0.86 for both. The feature of greatest importance was aortic valve mean gradient, followed by other valve haemodynamic measurements including valve area and dimensionless index. The mortality model identified those with mortality within 2 and 5 years with an AUC of 0.84 and 0.87, respectively. Smaller reduced-input validation models had similarly robust findings.

CONCLUSION: Machine learning models can be used in patients with mild AS to identify those at high risk of disease progression and mortality. Implementation of such models may facilitate real-time, patient-specific follow-up recommendations.

PMID:39846070 | PMC:PMC11750192 | DOI:10.1093/ehjdh/ztae085

Eur Heart J Digit Health. 2024 Oct 14;6(1):23-44. doi: 10.1093/ehjdh/ztae074. eCollection 2025 Jan.

ABSTRACT

AIMS: Accurate prediction of clinical outcomes following percutaneous coronary intervention (PCI) is essential for mitigating risk and peri-procedural planning. Traditional risk models have demonstrated a modest predictive value. Machine learning (ML) models offer an alternative risk stratification that may provide improved predictive accuracy.

METHODS AND RESULTS: This study was reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses, Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies and Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis guidelines. PubMed, EMBASE, Web of Science, and Cochrane databases were searched until 1 November 2023 for studies comparing ML models with traditional statistical methods for event prediction after PCI. The primary outcome was comparative discrimination measured by C-statistics with 95% confidence intervals (CIs) between ML models and traditional methods in estimating the risk of all-cause mortality, major bleeding, and the composite outcome major adverse cardiovascular events (MACE). Thirty-four models were included across 13 observational studies (4 105 916 patients). For all-cause mortality, the pooled C-statistic for top-performing ML models was 0.89 (95%CI, 0.84-0.91), compared with 0.86 (95% CI, 0.80-0.93) for traditional methods (P = 0.54). For major bleeding, the pooled C-statistic for ML models was 0.80 (95% CI, 0.77-0.84), compared with 0.78 (95% CI, 0.77-0.79) for traditional methods (P = 0.02). For MACE, the C-statistic for ML models was 0.83 (95% CI, 0.75-0.91), compared with 0.71 (95% CI, 0.69-0.74) for traditional methods (P = 0.007). Out of all included models, only one model was externally validated. Calibration was inconsistently reported across all models. Prediction Model Risk of Bias Assessment Tool demonstrated a high risk of bias across all studies.

CONCLUSION: Machine learning models marginally outperformed traditional risk scores in the discrimination of MACE and major bleeding following PCI. While integration of ML algorithms into electronic healthcare systems has been hypothesized to improve peri-procedural risk stratification, immediate implementation in the clinical setting remains uncertain. Further research is required to overcome methodological and validation limitations.

PMID:39846069 | PMC:PMC11750198 | DOI:10.1093/ehjdh/ztae074

Eur Heart J Digit Health. 2024 Nov 4;6(1):126-136. doi: 10.1093/ehjdh/ztae081. eCollection 2025 Jan.

ABSTRACT

AIMS: Many studies have utilized data sources such as clinical variables, polygenic risk scores, electrocardiogram (ECG), and plasma proteins to predict the risk of atrial fibrillation (AF). However, few studies have integrated all four sources from a single study to comprehensively assess AF prediction.

METHODS AND RESULTS: We included 8374 (Visit 3, 1993-95) and 3730 (Visit 5, 2011-13) participants from the Atherosclerosis Risk in Communities Study to predict incident AF and prevalent (but covert) AF. We constructed a (i) clinical risk score using CHARGE-AF clinical variables, (ii) polygenic risk score using pre-determined weights, (iii) protein risk score using regularized logistic regression, and (iv) ECG risk score from a convolutional neural network. Risk prediction performance was measured using regularized logistic regression. After a median follow-up of 15.1 years, 1910 AF events occurred since Visit 3 and 229 participants had prevalent AF at Visit 5. The area under curve (AUC) improved from 0.660 to 0.752 (95% CI, 0.741-0.763) and from 0.737 to 0.854 (95% CI, 0.828-0.880) after addition of the polygenic risk score to the CHARGE-AF clinical variables for predicting incident and prevalent AF, respectively. Further addition of ECG and protein risk scores improved the AUC to 0.763 (95% CI, 0.753-0.772) and 0.875 (95% CI, 0.851-0.899) for predicting incident and prevalent AF, respectively.

CONCLUSION: A combination of clinical and polygenic risk scores was the most effective and parsimonious approach to predicting AF. Further addition of an ECG risk score or protein risk score provided only modest incremental improvement for predicting AF.

PMID:39846068 | PMC:PMC11750194 | DOI:10.1093/ehjdh/ztae081

Eur Heart J Digit Health. 2024 Nov 21;6(1):96-103. doi: 10.1093/ehjdh/ztae091. eCollection 2025 Jan.

ABSTRACT

AIMS: Atrial fibrillation (AF) leads to impaired exercise capacity, and catheter ablation (CA) for AF improves exercise capacity. However, the precise changes in daily activities after CA for AF remain unclear. The authors aimed to evaluate the changes in daily activities following CA for AF using a wristwatch-type pulse wave monitor (PWM), which tracks steps and exercise time, estimates burnt daily calories, and records sleep duration, in addition to establishing the rhythm diagnosis of AF or non-AF.

METHODS AND RESULTS: One hundred and twenty-three patients with AF (97 paroxysmal, 26 persistent) wore a wristwatch-type PWM for 1 week duration at three time points: before, 1 month after, and 3 months after ablation. Daily activity data were compared. Steps did not change in both groups, and the number of burnt daily calories and total exercise time increased after CA in patients with paroxysmal AF (burnt daily calories: before, 1591 kcal/day; 1 month, 1688 kcal/day; and 3 months, 1624 kcal/day; P < 0.001 and exercise time: before, 45.8 min; 1 month, 51.2 min; and 3 months, 56.3 min; P = 0.023). Sleep hours significantly increased (paroxysmal AF: before, 6.8 h; 1 month, 7.1 h; and 3 months, 7.1 h; P = 0.039 and persistent AF: before, 6.0 h; 1 month, 7.0 h; and 3 months, 7.0 h; P = 0.007).

CONCLUSION: Using a wristwatch-type PWM, we demonstrated changes in daily activities after CA in patients with AF.

TRIAL REGISTRATION NUMBER: jRCT1030210022.

PMID:39846064 | PMC:PMC11750189 | DOI:10.1093/ehjdh/ztae091

Cancer Treat Res Commun. 2025 Jan 17;42:100870. doi: 10.1016/j.ctarc.2025.100870. Online ahead of print.

ABSTRACT

AIM: Breast cancer is the second most common cancer among women and the leading cause of cancer-related mortality in this population. Numerous factors have been identified as either risk factors or protective factors for breast cancer. However, the role of Vitamin D (Vit. D) in breast cancer remains contentious, with conflicting findings in the literature. The present study aimed to compare serum Vit. D levels between women with and without breast cancer.

METHODS: This cross-sectional study included 40 women diagnosed with breast cancer, referred to the Mahdia Hamadan Radiotherapy Center in 2022. These participants were matched with 40 age- and Vit. D serum level-matched women without breast cancer. Serum Vit. D levels were measured using the ELISA method. Statistical analysis was performed using SPSS version 26, with a significance threshold set at a 95% confidence level.

RESULTS: The mean ± standard deviation of serum Vit. D levels in women with and without breast cancer were 31.9 ± 28.27 ng/mL and 37.98 ± 15.89 ng/mL, respectively (P = 0.024). The prevalence of Vit. D insufficiency was 50% in the breast cancer group and 27.5% in the control group, while 50% of the breast cancer group and 72.5% of the control group had sufficient Vit. D levels (P = 0.008). In women with breast cancer, lower Vit. D levels were significantly associated with lower educational (P < 0.001), economic (P < 0.001), and social status (P < 0.001). A weak positive correlation was observed between serum Vit. D levels and patient age (r = 0.162, P = 0.152).

CONCLUSION: The significant difference in serum Vit. D levels between women with and without breast cancer suggests that Vit. D deficiency may be associated with breast cancer risk. These findings support the hypothesis that improving Vit. D status in women could potentially reduce the incidence of breast cancer.

PMID:39842055 | DOI:10.1016/j.ctarc.2025.100870