BMC Medical Research Methodology最新文献

Background: Focus groups (FGs) are an established method in health research to capture a full range of different perspectives on a particular research question. The extent to which they are effective depends, not least, on the composition of the participants. This study aimed to investigate how published FG studies plan and conduct the recruitment of study participants. We looked at what kind of information is reported about recruitment practices and what this reveals about the comprehensiveness of the actual recruitment plans and practices.

Methods: We conducted a systematic search of FG studies in PubMed and Web of Science published between 2018 and 2024, and included n = 80 eligible publications in the analysis. We used a text extraction sheet to collect all relevant recruitment information from each study. We then coded the extracted text passages and summarised the findings descriptively.

Results: Nearly half (n = 38/80) of the studies were from the USA and Canada, many addressing issues related to diabetes, cancer, mental health and chronic diseases. For recruitment planning, 20% reported a specific sampling target, while 6% used existing studies or literature for organisational and content planning. A further 10% reported previous recruitment experience of the researchers. The studies varied in terms of number of participants (range = 7-202) and group size (range = 7-20). Recruitment occurred often in healthcare settings, rarely through digital channels and everyday places. FG participants were most commonly recruited by the research team (21%) or by health professionals (16%), with less collaboration with public organisations (10%) and little indication of the number of people involved (13%). A financial incentive for participants was used in 43% of cases, and 19% reported participatory approaches to plan and carry out recruitment. 65 studies (81%) reported a total of 58 limitations related to recruitment.

Conclusions: The reporting of recruitment often seems to be incomplete, and its performance lacking. Hence, guidelines and recruitment recommendations designed to assist researchers are not yet adequately serving their purpose. Researchers may benefit from more practical support, such as early training on key principles and options for effective recruitment strategies provided by institutions in their immediate professional environment, e.g. universities, faculties or scientific associations.

Time-to-event data are very common in medical applications. Regression models have been developed on such data especially in the field of survival analysis. Kernels are used to handle even more complicated and enormous quantities of medical data by injecting non-linearity into linear models. In this study, a Multiple Kernel Learning (MKL) method has been proposed to optimize survival outcomes under the Accelerated Failure Time (AFT) model, a useful alternative to the Proportional Hazards (PH) frailty model. In other words, a survival parametric regression framework has been presented for clinical data to effectively integrate kernel learning with AFT model using a gradient descent optimization strategy. This methodology involves applying four different parametric models, evaluated using 19 distinct kernels to extract the best fitting scenario. This culminated in a sophisticated strategy that combined these kernels through MKL. We conducted a comparison between the Frailty model and MKL due to their shared fundamental properties. The models were assessed using the Concordance index (C-index) and Brier score (B-score). Each model was tested on both a case study and a replicated/independent dataset. The outcomes showed that kernelization enhances the performance of the model, especially by combining selected kernels for MKL.

Background: Peripartum depression is a common but potentially debilitating pregnancy complication. Mobile applications can be used to collect data throughout the pregnancy and postpartum period to improve understanding of early risk indicators.

Aim: This study aimed to improve understanding of why women drop out of a peripartum depression mHealth study, and how we can improve the app design.

Method: Participants who dropped out of the Mom2B study (n = 134) answered closed and open questions on their motives for dropping out of the study, suggestions for improvement, and preferred timeframe of the study. A mix of quantitative and qualitative strategies was used to analyze the responses.

Results: The most common reasons for discontinuation were lack of time, problems with or loss of the pregnancy, the use of other pregnancy applications, surveys being too lengthy, the app draining too much battery, and participants incorrectly believing that their answers were irrelevant for the study. Participants suggested fewer survey moments, more reminders, and a need for more unique content compared to commercially available apps.

Conclusions: Researcher who want to use mHealth designs in peripartum studies need to ensure that their study designs are as time-efficient as possible, remind participants about the study, manage expectations about the study and what is expected of participants throughout the study, design their apps to be attractive in a competitive market, and follow-up with participants who are excluded from the study due to pregnancy complications.

Background: We aimed to develop and validate an algorithm for identifying women with polycystic ovary syndrome (PCOS) in the French national health data system.

Methods: Using data from the French national health data system, we applied the International Classification of Diseases (ICD-10) related diagnoses E28.2 for PCOS among women aged 18 to 43 years in 2021. Then, we developed an algorithm to identify PCOS using combinations of clinical criteria related to specific drugs claims, biological exams, international classification of Diseases (ICD-10) related diagnoses during hospitalization, and/or registration for long-term conditions. The sensitivity, specificity and positive predictive value (PPV) of different combinations of algorithm criteria were estimated by reviewing the medical records of the Department of Reproductive Medicine at a university hospital for the year 2022, comparing potential women identified as experiencing PCOS by the algorithms with a list of clinically registered women with or without PCOS.

Results: We identified 2,807 (0.01%) women aged 18 to 43 who received PCOS-related care in 2021 using the ICD-10 code for PCOS in the French National health database. By applying the PCOS algorithm to 349 women, the positive and negative predictive values were 0.90 (95%CI (83-95) and 0.93 (95%CI 0.90-0.96) respectively. The sensitivity of the PCOS algorithm was estimated at 0.85 (95%CI 0.77-0.91) and the specificity at 0.96 (95%CI 0.92-0.98).

Conclusion: The validity of the PCOS diagnostic algorithm in women undergoing reproductive health care was acceptable. Our findings may be useful for future studies on PCOS using administrative data on a national scale, or even on an international scale given the similarity of coding in this field.

Objective: To assess whether the outcome generation true model could be identified from other candidate models for clinical practice with current conventional model performance measures considering various simulation scenarios and a CVD risk prediction as exemplar.

Study design and setting: Thousands of scenarios of true models were used to simulate clinical data, various candidate models and true models were trained on training datasets and then compared on testing datasets with 25 conventional use model performance measures. This consists of univariate simulation (179.2k simulated datasets and over 1.792 million models), multivariate simulation (728k simulated datasets and over 8.736 million models) and a CVD risk prediction case analysis.

Results: True models had overall C statistic and 95% range of 0.67 (0.51, 0.96) across all scenarios in univariate simulation, 0.81 (0.54, 0.98) in multivariate simulation, 0.85 (0.82, 0.88) in univariate case analysis and 0.85 (0.82, 0.88) in multivariate case analysis. Measures showed very clear differences between the true model and flip-coin model, little or none differences between the true model and candidate models with extra noises, relatively small differences between the true model and proxy models missing causal predictors.

Conclusion: The study found the true model is not always identified as the "outperformed" model by current conventional measures for binary outcome, even though such true model is presented in the clinical data. New statistical approaches or measures should be established to identify the casual true model from proxy models, especially for those in proxy models with extra noises and/or missing causal predictors.

Background: The majority of phase 3 clinical trials are implemented in multiple sites or centres, which inevitably leads to a correlation between observations from the same site or centre. This correlation must be carefully considered in both the design and the statistical analysis to ensure an accurate interpretation of the results and reduce the risk of biased results. This scoping review aims to provide a detailed statistical method used to analyze data collected from multicentre HIV randomized controlled trials in the African region.

Methods: This review followed the methodological framework proposed by Arksey and O'Malley. We searched four databases (PubMed, EBSCOhost, Scopus, and Web of Science) and retrieved 977 articles, 34 of which were included in the review.

Results: Data charting revealed that the most used statistical methods for analysing HIV endpoints in multicentre randomized controlled trials in Africa were standard survival analysis techniques (24 articles [71%]). Approximately 47% of the articles used stratified analysis methods to account for variations across different sites. Out of 34 articles reviewed, only 6 explicitly considered intra-site correlation in the analysis.

Conclusions: Our scoping review provides insights into the statistical methods used to analyse HIV data in multicentre randomized controlled trials in Africa and highlights the need for standardized reporting of statistical methods.

Background: Spinal pain affects up to 30% of school-age children and can interfere with various aspects of daily life, such as school attendance, physical function, and social life. Current assessment tools often rely on parental reporting which limits our understanding of how each child is affected by their pain. This study aimed to address this gap by developing MySpineData-Kids ("MiRD-Kids"), a tailored patient-reported questionnaire focusing on children with spinal pain in secondary care (Danish hospital setting).

Methods: The process and development of MiRD-Kids followed a structured, multi-phase approach targeted children in outpatient care. The first phase involved evidence-synthesis, expert consultations, and item formulation, resulting in the first version. The second phase involved pilot testing among pediatric spinal pain patients, leading to modifications for improved clarity and relevance. The third phase involved implementation at the Pediatric outpatient track at The Spine Centre of Southern Denmark, University Hospital of Southern Denmark.

Results: MiRD-Kids was based on selected items from seven questionnaires, encompassing 20 items across six domains. Pilot testing with 13 pediatric patients facilitated modifications and finalized the questionnaire. The questionnaire includes sections for parents/legal guardians and six domains for children covering pain, sleep, activities, trauma, concerns, and treatment, following the International Classification of Functioning, Disability, and Health (ICF). Implementation challenges were overcome within a 2-month period, resulting in the clinical questionnaire MiRD-Kids a comprehensive tool for assessing pediatric spinal pain in hospital outpatient settings.

Conclusion: MiRD-Kids is the first comprehensive questionnaire for children with spinal pain seen in outpatient caresetting and follows the ICF approach. It can support age-specific high-quality research and comprehensive clinical assessment of children aged 12 to 17 years, potentially, contributing to efforts aimed at mitigating the long-term consequences of spinal pain.

Background: In this work, we implement a data-driven approach using an aggregation of several analytical methods to study the characteristics of COVID-19 daily infection and death time series and identify correlations and characteristic trends that can be corroborated to the time evolution of this disease. The datasets cover twelve distinct countries across six continents, from January 22, 2020 till March 1, 2022. This time span is partitioned into three windows: (1) pre-vaccine, (2) post-vaccine and pre-omicron (BA.1 variant), and (3) post-vaccine including post-omicron variant. This study enables deriving insights into intriguing questions related to the science of system dynamics pertaining to COVID-19 evolution.

Methods: We implement a set of several distinct analytical methods for: (a) statistical studies to estimate the skewness and kurtosis of the data distributions; (b) analyzing the stationarity properties of these time series using the Augmented Dickey-Fuller (ADF) tests; (c) examining co-integration properties for the non-stationary time series using the Phillips-Ouliaris (PO) tests; (d) calculating the Hurst exponent using the rescaled-range (R/S) analysis, along with the Detrended Fluctuation Analysis (DFA), for self-affinity studies of the evolving dynamical datasets.

Results: We notably observe a significant asymmetry of distributions shows from skewness and the presence of heavy tails is noted from kurtosis. The daily infection and death data are, by and large, nonstationary, while their corresponding log return values render stationarity. The self-affinity studies through the Hurst exponents and DFA exhibit intriguing local changes over time. These changes can be attributed to the underlying dynamics of state transitions, especially from a random state to either mean-reversion or long-range memory/persistence states.

Conclusions: We conduct systematic studies covering a widely diverse time series datasets of the daily infections and deaths during the evolution of the COVID-19 pandemic. We demonstrate the merit of a multiple analytics frameworks through systematically laying down a methodological structure for analyses and quantitatively examining the evolution of the daily COVID-19 infection and death cases. This methodology builds a capability for tracking dynamically evolving states pertaining to critical problems.

Background: Health services research often relies on secondary data, necessitating quality checks for completeness, validity, and potential errors before use. Various methods address implausible data, including data elimination, statistical estimation, or value substitution from the same or another dataset. This study presents an internal validation process of a secondary dataset used to investigate hospital compliance with minimum caseload requirements (MCR) in Germany. The secondary data source validated is the German Hospital Quality Reports (GHQR), an official dataset containing structured self-reported data from all hospitals in Germany.

Methods: This study conducted an internal cross-field validation of MCR-related data in GHQR from 2016 to 2021. The validation process checked the validity of reported MCR caseloads, including data availability and consistency, by comparing the stated MCR caseload with further variables in the GHQR. Subsequently, implausible MCR caseload values were corrected using the most plausible values given in the same GHQR. The study also analysed the error sources and used reimbursement-related Diagnosis Related Groups Statistic data to assess the validation outcomes.

Results: The analysis focused on four MCR procedures. 11.8-27.7% of the total MCR caseload values in the GHQR appeared ambiguous, and 7.9-23.7% were corrected. The correction added 0.7-3.7% of cases not previously stated as MCR caseloads and added 1.5-26.1% of hospital sites as MCR performing hospitals not previously stated in the GHQR. The main error source was this non-reporting of MCR caseloads, especially by hospitals with low case numbers. The basic plausibility control implemented by the Federal Joint Committee since 2018 has improved the MCR-related data quality over time.

Conclusions: This study employed a comprehensive approach to dataset internal validation that encompassed: (1) hospital association level data, (2) hospital site level data and (3) medical department level data, (4) report data spanning six years, and (5) logical plausibility checks. To ensure data completeness, we selected the most plausible values without eliminating incomplete or implausible data. For future practice, we recommend a validation process when using GHQR as a data source for MCR-related research. Additionally, an adapted plausibility control could help to improve the quality of MCR documentation.

Background: The prediction of coronavirus disease in 2019 (COVID-19) in broader regions has been widely researched, but for specific areas such as urban areas the predictive models were rarely studied. It may be inaccurate to apply predictive models from a broad region directly to a small area. This paper builds a prediction approach for small size COVID-19 time series in a city.

Methods: Numbers of COVID-19 daily confirmed cases were collected from November 1, 2022 to November 16, 2023 in Xuzhou city of China. Classical deep learning models including recurrent neural network (RNN), long and short-term memory (LSTM), gated recurrent unit (GRU) and temporal convolutional network (TCN) are initially trained, then RNN, LSTM and GRU are integrated with a new attention mechanism and transfer learning to improve the performance. Ten times ablation experiments are conducted to show the robustness of the performance in prediction. The performances among the models are compared by the mean absolute error, root mean square error and coefficient of determination.

Results: LSTM outperforms than others, and TCN has the worst generalization ability. Thus, LSTM is integrated with the new attention mechanism to construct an LSTMATT model, which improves the performance. LSTMATT is trained on the smoothed time series curve through frequency domain convolution augmentation, then transfer learning is adopted to transfer the learned features back to the original time series resulting in a TLLA model that further improves the performance. RNN and GRU are also integrated with the attention mechanism and transfer learning and their performances are also improved, but TLLA still performs best.

Conclusions: The TLLA model has the best prediction performance for the time series of COVID-19 daily confirmed cases, and the new attention mechanism and transfer learning contribute to improve the prediction performance in the flatten part and the jagged part, respectively.