Source Component Shift Adaptation via Offline Decomposition and Online Mixing Approach

A fundamental part of medical research is the development and validation of diagnostic and prognostic prediction models [1,2]. These prediction models aim to predict the absolute probability that a certain disease or condition is currently present (diagnostic models) or that an outcome will occur within a specific follow-up period (prognostic models) for an individual subject. Prediction models typically rely on multiple predictors, which can include demographic characteristics, medical history and physical examination items, or more complex measurements from, for example, medical imaging, electrophysiology, pathology, and biomarkers. Also for diagnostic models, estimates of probabilities are rarely based on a single test, and doctors naturally integrate several patient characteristics and symptoms [3]. A broad range of prediction modeling techniques exist, like regression approaches, neural network models, decision tree models, genetic programming models, and support vector machine learning models, although prediction models developed by a multivariable regression approach are by far prevailing. It is widely recommended that a developed prediction model should not be used in practice before being externally validated—at least once—in other individuals than those used for model development [4–7]. Unfortunately, most prediction models are poorly or not at all validated, rendering interpretation of their generalizability difficult. In addition, many systematic reviews showed that for the same outcome or same target population, numerous competing models exist [8–10]. Generally speaking, researchers often ignore existing prediction models and develop yet another prediction model from their own data [2]. This practice sustains a cycle of underpowered prediction model development studies and poor knowledge about the generalizability and applicability of developed prediction models. Evidence synthesis and meta-analysis of individual participant data (IPD) from multiple studies seems to be a unique opportunity to address these problems, as it allows researchers to develop and directly validate models on large datasets and across a wide range of populations and settings, to directly test a model’s generalizability (Fig 1) [11–13]. Fig 1 Trends in publications of IPD-MA studies focusing on the development and/or validation of diagnostic or prognostic prediction models. There is currently little guidance on how to conduct an IPD meta-analysis (IPD-MA) for developing and/or validating diagnostic or prognostic prediction models [15]. To date, most IPD-MA articles focus on estimating relative quantities, like a risk ratio, hazard ratio, or odds ratio for a specific treatment or a specific etiologic factor. In contrast, prediction modeling research is focused on developing and validating multivariable models aimed at calculating an absolute risk estimate of the combined variables, rather than estimating the relative effect of a specific treatment or etiologic factor. Furthermore, prediction modeling studies focus entirely on the role and joint contribution of multiple covariates, whereas intervention studies in principle rely on randomization to reduce the role of covariates (Table 1). Hence, IPD-MAs of randomized intervention and etiological studies, which are beyond the scope of this paper and are instead addressed in the accompanying paper [16], differ from IPD-MAs of multivariable prediction models, which are the focus of this paper. Table 1 The main differences between IPD-MA of treatment intervention studies and of multivariable prediction modeling studies. We provide an overview of the advantages and limitations of IPD-MAs aiming to develop a novel prediction model or to validate one or more existing models across multiple datasets. This overview is based on published guidelines and existing recommendations for the conduct of prediction modeling studies and of IPD-MA research. We illustrate this overview with examples of recently published IPD-MAs of prediction models across various medical domains. Our aim is to help researchers, readers, reviewers, and editors to identify and understand the key issues involved with such IPD-MA projects.

Analytics and Prediction Modeling During the COVID-19 Pandemic

BackgroundEmergency department boarding and hospital exit block are primary causes of emergency department crowding and have been conclusively associated with poor patient outcomes and major threats to patient safety. Boarding occurs when a patient is delayed or blocked from transitioning out of the emergency department because of dysfunctional transition or bed assignment processes. Predictive models for estimating the probability of an occurrence of this type could be useful in reducing or preventing emergency department boarding and hospital exit block, to reduce emergency department crowding.ObjectiveThe aim of this study was to identify and appraise the predictive performance, predictor utility, model application, and model utility of hospital admission prediction models that utilized prehospital, adult patient data and aimed to address emergency department crowding.MethodsWe searched multiple databases for studies, from inception to September 30, 2019, that evaluated models predicting adult patients’ imminent hospital admission, with prehospital patient data and regression analysis. We used PROBAST (Prediction Model Risk of Bias Assessment Tool) and CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) to critically assess studies.ResultsPotential biases were found in most studies, which suggested that each model’s predictive performance required further investigation. We found that select prehospital patient data contribute to the identification of patients requiring hospital admission. Biomarker predictors may add superior value and advantages to models. It is, however, important to note that no models had been integrated with an information system or workflow, operated independently as electronic devices, or operated in real time within the care environment. Several models could be used at the site-of-care in real time without digital devices, which would make them suitable for low-technology or no-electricity environments.ConclusionsThere is incredible potential for prehospital admission prediction models to improve patient care and hospital operations. Patient data can be utilized to act as predictors and as data-driven, actionable tools to identify patients likely to require imminent hospital admission and reduce patient boarding and crowding in emergency departments. Prediction models can be used to justify earlier patient admission and care, to lower morbidity and mortality, and models that utilize biomarker predictors offer additional advantages.

IntroductionPrediction models for gestational hypertension and preeclampsia have been developed with data and assumptions from developed countries. Their suitability and application for low resource settings have not been tested. This review aimed to identify and assess the methodological quality of prediction models for gestational hypertension and pre-eclampsia with reference to their application in low resource settings.MethodsUsing combinations of keywords for gestational hypertension, preeclampsia and prediction models seven databases were searched to identify prediction models developed with maternal data obtained before 20 weeks of pregnancy and including at least three predictors (Prospero registration CRD 42017078786). Prediction model characteristics and performance measures were extracted using the CHARMS, STROBE and TRIPOD checklists. The National Institute of Health quality assessment tools for observational cohort and cross-sectional studies were used for study quality appraisal.ResultsWe retrieved 8,309 articles out of which 40 articles were eligible for review. Seventy-seven percent of all the prediction models combined biomarkers with maternal clinical characteristics. Biomarkers used as predictors in most models were pregnancy associated plasma protein-A (PAPP-A) and placental growth factor (PlGF). Only five studies were conducted in a low-and middle income country.ConclusionsMost of the studies evaluated did not completely follow the CHARMS, TRIPOD and STROBE guidelines in prediction model development and reporting. Adherence to these guidelines will improve prediction modelling studies and subsequent application of prediction models in clinical practice. Prediction models using maternal characteristics, with good discrimination and calibration, should be externally validated for use in low and middle income countries where biomarker assays are not routinely available.

One effective iterative method for estimating parameters in latent variable probabilistic models is the Expectation-Maximization (EM) algorithm, which finds extensive use in classification issues. A versatile probabilistic framework for modeling data from multiple Gaussian distributions, Gaussian Mixture Models (GMMs) employ EM for parameter estimation, which is explored in this article. Problems with class membership estimation (including means, covariances, and mixing coefficients) are the primary focus of this study. Starting with initial parameter estimations, estimating posterior probabilities in the E-step, and repeatedly updating model parameters in the M-step until convergence, the technique entails applying the EM algorithm on both synthetic and real-world datasets. In order to measure performance, we compare it to K-means and other baseline classifiers using measures like classification accuracy, Adjusted Rand Index (ARI), and log-likelihood progression. When data is distributed according to a multimodal Gaussian distribution, the findings show that EM-GMM provides better parameter estimation and better classification accuracy. Initialization procedures have a substantial effect on performance, as convergence study further shows. In addition to reiterating the EM algorithm's usefulness for probabilistic classification, this paper also describes its advantages and disadvantages and offers suggestions for improving its performance in settings with high-dimensional data and noise.

Predictive models play a critical role in enhancing medication safety in clinical practice. While multiple models for adverse drug reactions (ADRs) in adults have demonstrated potential clinical utility, pediatric-specific predictive models remain understudied, with limited comprehensive evaluation of their methodological quality and reporting standards. To map the landscape of existing risk prediction models for ADRs specifically developed or validated for pediatric patients, and to describe their characteristics, methodological quality, and reporting completeness. A systematic search was conducted in Embase, PubMed, CNKI, Wanfang, VIP, and SinoMed for studies on pediatric ADR prediction models. The information from included studies was evaluated using the Systematic Reviews of Prediction Modelling Studies (CHARMS) checklist, the risk of bias was assessed with the Prediction Model Risk of Bias Assessment Tool (PROBAST), and adherence to Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines was reviewed. Predictive ability of the included model, including the area under the receiver operating characteristic curve (AuROC), sensitivity, and specificity, was also reported. Out of 12,667 screened studies, 7 articles (describing 10 models) met the inclusion criteria. Study designs included case-control, nested case-control, prospective cohort, and cross-sectional studies. Logistic regression was the primary modeling method, with one study using machine learning. Common methodological limitations included unreported handling of missing data and univariable predictor screening. Model discrimination (AuROC) ranged from 0.63-0.97, with sensitivity and specificity between 52.02-98.50% and 33.33-98.79%, respectively. TRIPOD adherence varied (62.16-86.49%), with notable reporting deficiencies in blinding, sample size justification, intervention details, model usage instructions, and supplementary materials. No models underwent external validation. Existing pediatric ADR prediction models are limited by methodological and reporting shortcomings. Future research should focus on rigorous model development and external validation to ensure generalizability across diverse clinical settings.

Random effects regression models are routinely used for clustered data in etiological and intervention research. However, in prediction models, the random effects are either neglected or conventionally substituted with zero for new clusters after model development. In this study, we applied a Bayesian prediction modelling method to the subclinical ketosis data previously collected by Van der Drift et al. (2012). Using a dataset of 118 randomly selected Dutch dairy farms participating in a regular milk recording system, the authors proposed a prediction model with milk measures as well as available test-day information as predictors for the diagnosis of subclinical ketosis in dairy cows. While their original model included random effects to correct for the clustering, the random effect term was removed for their final prediction model. With the Bayesian prediction modelling approach, we first used non-informative priors for the random effects for model development as well as for prediction. This approach was evaluated by comparing it to the original frequentist model. In addition, herd level expert opinion was elicited from a bovine health specialist using three different scales of precision and incorporated in the prediction as informative priors for the random effects, resulting in three more Bayesian prediction models. Results showed that the Bayesian approach could naturally take the clustering structure of clusters into account by keeping the random effects in the prediction model. Expert opinion could be explicitly combined with individual level data for prediction. However in this dataset, when elicited expert opinion was incorporated, little improvement was seen at the individual level as well as at the herd level. When the prediction models were applied to the 118 herds, at the individual cow level, with the original frequentist approach we obtained a sensitivity of 82.4% and a specificity of 83.8% at the optimal cutoff, while with the three Bayesian models with elicited expert opinion, we obtained sensitivities ranged from 78.7% to 84.6% and specificities ranged from 75.0% to 83.6%. At the herd level, 30 out of 118 within herd prevalences were correctly predicted by the original frequentist approach, and 31 to 44 herds were correctly predicted by the three Bayesian models with elicited expert opinion. Further investigation in expert opinion and distributional assumption for the random effects was carried out and discussed.

Existing expert systems have not improved the diagnostic accuracy of ventilator-associated pneumonia (VAP). The aim of this systematic literature review was to review and summarize state-of-the-art prediction models detecting or predicting VAP from exhaled breath, patient reports and demographic and clinical characteristics. Both diagnostic and prognostic prediction models were searched from a representative list of multidisciplinary databases. An extensive list of validated search terms was added to the search to cover papers failing to mention predictive research in their title or abstract. Two authors independently selected studies, while three authors extracted data using predefined criteria and data extraction forms. The Prediction Model Risk of Bias Assessment Tool was used to assess both the risk of bias and the applicability of the prediction modelling studies. Technology readiness was also assessed. Out of 2052 identified studies, 20 were included. Fourteen (70%) studies reported the predictive performance of diagnostic models to detect VAP from exhaled human breath with a high degree of sensitivity and a moderate specificity. In addition, the majority of them were validated on a realistic dataset. The rest of the studies reported the predictive performance of diagnostic and prognostic prediction models to detect VAP from unstructured narratives [2 (10%)] as well as baseline demographics and clinical characteristics [4 (20%)]. All studies, however, had either a high or unclear risk of bias without significant improvements in applicability. The development and deployment of prediction modelling studies are limited in VAP and related outcomes. More computational, translational, and clinical research is needed to bring these tools from the bench to the bedside. PROSPERO CRD42020180218, registered on 05-07-2020.

Developing and Evaluating Prediction Models in Rehabilitation Populations

Clinical prediction modeling plays a pivotal part in modern clinical care, particularly in predicting the risk of in-hospital mortality. Recent modeling efforts have focused on leveraging intraoperative data sources to improve model performance. However, the individual and collective benefit of pre- and intraoperative data for clinical decision-making remains unknown. We hypothesized that pre- and intraoperative predictors contribute equally to the net benefit in a decision curve analysis (DCA) of in-hospital mortality prediction models that include pre- and intraoperative predictors. Data from the VitalDB database featuring a subcohort of 6043 patients were used. A total of 141 predictors for in-hospital mortality were grouped into preoperative (demographics, intervention characteristics, and laboratory measurements) and intraoperative (laboratory and monitor data, drugs, and fluids) data. Prediction models using either preoperative, intraoperative, or all data were developed with multiple methods (logistic regression, neural network, random forest, gradient boosting machine, and a stacked learner). Predictive performance was evaluated by the area under the receiver-operating characteristic curve (AUROC) and under the precision-recall curve (AUPRC). Clinical utility was examined with a DCA in the predefined risk preference range (denoted by so-called treatment threshold probabilities) between 0% and 20%. AUROC performance of the prediction models ranged from 0.53 to 0.78. AUPRC values ranged from 0.02 to 0.25 (compared to the incidence of 0.09 in our dataset) and high AUPRC values resulted from prediction models based on preoperative laboratory values. A DCA of pre- and intraoperative prediction models highlighted that preoperative data provide the largest overall benefit for decision-making, whereas intraoperative values provide only limited benefit for decision-making compared to preoperative data. While preoperative demographics, comorbidities, and surgery-related data provide the largest benefit for low treatment thresholds up to 5% to 10%, preoperative laboratory measurements become the dominant source for decision support for higher thresholds. When it comes to predicting in-hospital mortality and subsequent decision-making, preoperative demographics, comorbidities, and surgery-related data provide the largest benefit for clinicians with risk-averse preferences, whereas preoperative laboratory values provide the largest benefit for decision-makers with more moderate risk preferences. Our decision-analytic investigation of different predictor categories moves beyond the question of whether certain predictors provide a benefit in traditional performance metrics (eg, AUROC). It offers a nuanced perspective on for whom these predictors might be beneficial in clinical decision-making. Follow-up studies requiring larger datasets and dedicated deep-learning models to handle continuous intraoperative data are essential to examine the robustness of our results.

Significance: Postoperative Pressure Injuries (PIs) present unique risks, requiring dedicated research for accurate assessment. Despite the increasing number of Intraoperative Acquired Pressure Injury (IAPI) prediction models, their risk of bias and clinical applicability remains unclear. Recent Advances: Adhered to the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement requirements, IAPI prediction models of adult inpatients (≥18 years) were systematically retrieved from eight databases. Bias risk and applicability were evaluated using the Prediction model Risk Of Bias Assessment Tool (PROBAST), followed by narrative synthesis. Critical Issues: From 837 studies, 25 were included, covering 32 prediction models. Most studies (88%) were single-center and conducted in China, Korea, the United States, or Singapore, spanning various surgical specialties. Among 26,142 participants, IAPI incidence ranged from 4.1% to 41.75%. Common predictors included surgery duration, age, and diabetes. Areas Under the Curve (AUC) values varied from 0.702 to 0.984, but calibration was underreported. All studies had high bias risk, with 22 models exhibiting applicability concerns. Future Directions: The development of IAPI models requires a clear definition of the timing and personnel responsible for assessing PIs, with a preference for prospective data collection and thorough internal and external validation. Adherence to the critical appraisal and data extraction for systematic reviews of prediction modeling studies checklist and PROBAST guidelines can improve reporting quality. Models should be user-friendly, clinically applicable, and rigorously validated. Precisely defining and rigorously selecting predictors is critical to reducing variability. Future research should adopt more stringent designs to develop high-quality models capable of effectively guiding clinical practice. PROSPERO registration number: CRD42024502726.

To summarize the implementation approaches and updating methods of clinically implemented models and consecutively advise researchers on the implementation and updating. We included studies describing the implementation of prognostic binary prediction models in a clinical setting. We retrieved articles from Embase, Medline, and Web of Science from January 1, 2010, to January 1, 2024. We performed data extraction, based on Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis and Prediction Model Risk of Bias Assessment guidelines, and summarized. The search yielded 1872 articles. Following screening, 37 articles, describing 56 prediction models, were eligible for inclusion. The overall risk of bias was high in 86% of publications. In model development and internal validation, 32% of the models was assessed for calibration. External validation was performed for 27% of the models. Most models were implemented into the hospital information system (63%), followed by a web application (32%) and a patient decision aid tool (5%). Moreover, 13% of models have been updated following implementation. Impact assessments generally showed successful model implementation and the ability to improve patient care, despite not fully adhering to prediction modeling best practice. Both impact assessment and updating could play a key role in identifying and lowering bias in models.

This dissertation contributes with novel predictive modelling approaches to data-driven computational psychiatry and offers alternative analyses frameworks to the standard statistical analyses in psychiatric research. In particular, this document advances research in medical data mining, especially psychiatry, via two phases. In the first phase, this document promotes research by proposing synergistic machine learning and statistical approaches for detecting patterns and developing predictive models in clinical psychiatry data to classify diseases, predict treatment outcomes or improve treatment selections. In particular, these data-driven approaches are built upon several machine learning techniques whose predictive models have been pre-processed, trained, optimised, post-processed and tested in novel computationally intensive frameworks. In the second phase, this document advances research in medical data mining by proposing several novel extensions in the area of data classification by offering a novel decision tree algorithm, which we call PIDT, based on parameterised impurities and statistical pruning approaches toward building more accurate decision trees classifiers and developing new ensemblebased classification methods. In particular, the experimental results show that by building predictive models with the novel PIDT algorithm, these models primarily led to better performance regarding accuracy and tree size than those built with traditional decision trees. The contributions of the proposed dissertation can be summarised as follow. Firstly, several statistical and machine learning algorithms, plus techniques to improve these algorithms, are explored. Secondly, prediction modelling and pattern detection approaches for the first-episode psychosis associated with cannabis use are developed. Thirdly, a new computationally intensive machine learning framework for understanding the link between cannabis use and first-episode psychosis was introduced. Then, complementary and equally sophisticated prediction models for the first-episode psychosis associated with cannabis use were developed using artificial neural networks and deep learning within the proposed novel computationally intensive framework. Lastly, an efficient novel decision tree algorithm (PIDT) based on novel parameterised impurities and statistical pruning approaches is proposed and tested with several medical datasets. These contributions can be used to guide future theory, experiment, and treatment development in medical data mining, especially psychiatry.

Risk prediction models for postoperative delirium in elderly patients with fragility hip fracture: A systematic review and critical appraisal

BackgroundAsthma is a chronic disease that exacerbates due to various risk factors, including the patient’s biosignals and environmental conditions. It is affecting on average 7% of the world population. Preventing an asthma attack is the main challenge for asthma patients, which requires keeping track of any risk factor that can cause a seizure. Many researchers developed asthma attacks prediction models that used various asthma biosignals and environmental factors. These predictive models can help asthmatic patients predict asthma attacks in advance, and thus preventive measures can be taken. This paper introduces a review of these models to evaluate the used methods, model’s performance, and determine the need to improve research in this field.MethodA systematic review was conducted for the research articles introducing asthma attack prediction models for children and adults. We searched the PubMed, ScienceDirect, Springer, and IEEE databases from January 2000 to December 2020. The search includes the prediction models that used biosignal, environmental, and both risk factors. The research article’s quality was assessed and scored based on two checklists, the Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) and the Critical Appraisal Skills Programme clinical prediction rule checklist (CASP). The highest scored articles were selected to review.ResultFrom 1068 research articles we reviewed, we found that most of the studies used asthma biosignal factors only for prediction, few of the studies used environmental factors, and limited studies used both of these factors. Fifteen different asthma attack predictive models were selected for this review. we found that most of the studies used traditional prediction methods, like Support Vector Machine and regression. We have identified the pros and cons of the reviewed asthma attack prediction models and propose solutions to advance the studies in this field.ConclusionAsthma attack predictive models become more significant when using both patient’s biosignal and environmental factors. There is a lack of utilizing advanced machine learning methods, like deep learning techniques. Besides, there is a need to build smart healthcare systems that provide patients with decision-making systems to identify risk and visualize high-risk regions.