Prediction of the postharvest quality of Boletus wild mushrooms stored with mesoporous silica nanoparticles antibacterial film using Long Short-Term Memory model combined with the Northern Goshawk Optimization (NGO-LSTM).

This study aimed to address the challenge of extending the shelf life of Boletus wild mushrooms, which are prone to environmental and microbial contamination. An antibacterial film composed of polylactic acid (PLA) and mesoporous silica nanoparticles loaded with citral (CMP film) was developed for this purpose. Fifteen quality indices were assessed, and the data were integrated using AHP and TOPSIS to evaluate the film's efficacy. The CMP film effectively maintained the quality of mushroom over time. Additionally, a Nonlinear Global Optimization-Long Short-Term Memory (NGO-LSTM) model was employed to predict storage quality, using seven highly correlated quality indicators. The model achieved a high predictive accuracy, with the R2 exceeding 0.999. This study presents a novel packaging solution and a predictive model that together enhance the storage and quality control of Boletus wild mushrooms.

Machine learning-based prediction model for hypofibrinogenemia after tigecycline therapy.

BACKGROUND: In clinical practice, the incidence of hypofibrinogenemia (HF) after tigecycline (TGC) treatment significantly exceeds the probability claimed by drug manufacturers. OBJECTIVE: We aimed to identify the risk factors for TGC-associated HF and develop prediction and survival models for TGC-associated HF and the timing of TGC-associated HF. METHODS: This single-center retrospective cohort study included 222 patients who were prescribed TGC. First, we used binary logistic regression to screen the independent factors influencing TGC-associated HF, which were used as predictors to train the extreme gradient boosting (XGBoost) model. Receiver operating characteristic curve (ROC), calibration curve, decision curve analysis (DCA), and clinical impact curve analysis (CICA) were used to evaluate the performance of the model in the verification cohort. Subsequently, we conducted survival analysis using the random survival forest (RSF) algorithm. A consistency index (C-index) was used to evaluate the accuracy of the RSF model in the verification cohort. RESULTS: Binary logistic regression identified nine independent factors influencing TGC-associated HF, and the XGBoost model was constructed using these nine predictors. The ROC and calibration curves showed that the model had good discrimination (areas under the ROC curves (AUC) = 0.792 [95% confidence interval (CI), 0.668-0.915]) and calibration ability. In addition, DCA and CICA demonstrated good clinical practicability of this model. Notably, the RSF model showed good accuracy (C-index = 0.746 [95%CI, 0.652-0.820]) in the verification cohort. Stratifying patients treated with TGC based on the RSF model revealed a statistically significant difference in the mean survival time between the low- and high-risk groups. CONCLUSIONS: The XGBoost model effectively predicts the risk of TGC-associated HF, whereas the RSF model has advantages in risk stratification. These two models have significant clinical practical value, with the potential to reduce the risk of TGC therapy.

Integrating whole genome sequencing and machine learning for predicting antimicrobial resistance in critical pathogens: a systematic review of antimicrobial susceptibility tests.

Background: Infections caused by antibiotic-resistant bacteria pose a major challenge to modern healthcare. This systematic review evaluates the efficacy of machine learning (ML) approaches in predicting antimicrobial resistance (AMR) in critical pathogens (CP), considering Whole Genome Sequencing (WGS) and antimicrobial susceptibility testing (AST). Methods: The search covered databases including PubMed/MEDLINE, EMBASE, Web of Science, SCOPUS, and SCIELO, from their inception until June 2024. The review protocol was officially registered on PROSPERO (CRD42024543099). Results: The review included 26 papers, analyzing data from 104,141 microbial samples. Random Forest (RF), XGBoost, and logistic regression (LR) emerged as the top-performing models, with mean Area Under the Receiver Operating Characteristic (AUC) values of 0.89, 0.87, and 0.87, respectively. RF showed superior performance with AUC values ranging from 0.66 to 0.97, while XGBoost and LR showed similar performance with AUC values ranging from 0.83 to 0.91 and 0.76 to 0.96, respectively. Most studies indicate that integrating WGS and AST data into ML models enhances predictive performance, improves antibiotic stewardship, and provides valuable clinical decision support. ML shows significant promise for predicting AMR by integrating WGS and AST data in CP. Standardized guidelines are needed to ensure consistency in future research.

Importance of variables from different time frames for predicting self-harm using health system data.

Objective: Self-harm risk prediction models developed using health system data (electronic health records and insurance claims information) often use patient information from up to several years prior to the index visit when the prediction is made. Measurements from some time periods may not be available for all patients. Using the framework of algorithm-agnostic variable importance, we study the predictive potential of variables corresponding to different time horizons prior to the index visit and demonstrate the application of variable importance techniques in the biomedical informatics setting. Materials and Methods: We use variable importance to quantify the potential of recent (up to three months before the index visit) and distant (more than one year before the index visit) patient mental health information for predicting self-harm risk using data from seven health systems. We quantify importance as the decrease in predictiveness when the variable set of interest is excluded from the prediction task. We define predictiveness using discriminative metrics: area under the receiver operating characteristic curve (AUC), sensitivity, and positive predictive value. Results: Mental health predictors corresponding to the three months prior to the index visit show strong signal of importance; in one setting, excluding these variables decreased AUC from 0.85 to 0.77. Predictors corresponding to more distant information were less important. Discussion: Predictors from the months immediately preceding the index visit are highly important. Implementation of self-harm prediction models may be challenging in settings where recent data are not completely available (e.g., due to lags in insurance claims processing) at the time a prediction is made. Conclusion: Clinically derived variables from different time frames exhibit varying levels of importance for predicting self-harm. Variable importance analyses can inform whether and how to implement risk prediction models into clinical practice given real-world data limitations. These analyses be applied more broadly in biomedical informatics research to provide insight into general clinical risk prediction tasks.

Clinical prediction models for the management of blunt chest trauma in the emergency department: a systematic review.

BACKGROUND: The aim of this systematic review was to investigate how clinical prediction models compare in terms of their methodological development, validation, and predictive capabilities, for patients with blunt chest trauma presenting to the Emergency Department. METHODS: A systematic review was conducted across databases from 1st Jan 2000 until 1st April 2024. Studies were categorised into three types of multivariable prediction research and data extracted regarding methodological issues and the predictive capabilities of each model. Risk of bias and applicability were assessed. RESULTS: 41 studies were included that discussed 22 different models. The most commonly observed study design was a single-centre, retrospective, chart review. The most widely externally validated clinical prediction models with moderate to good discrimination were the Thoracic Trauma Severity Score and the STUMBL Score. DISCUSSION: This review demonstrates that the predictive ability of some of the existing clinical prediction models is acceptable, but high risk of bias and lack of subsequent external validation limits the extensive application of the models. The Thoracic Trauma Severity Score and STUMBL Score demonstrate better predictive accuracy in both development and external validation studies than the other models, but require recalibration and / or update and evaluation of their clinical and cost effectiveness. REVIEW REGISTRATION: PROSPERO database ( https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=351638 ).

From MGUS to multiple myeloma: Unraveling the unknown of precursor states.

In the 1960s, through laboratory-based investigations of peripheral blood partnered with detailed clinical annotations, Dr. Waldenström described a condition he called "benign monoclonal gammopathy". These patients were asymptomatic with a detectable monoclonal protein, and did not meet imaging and laboratory criteria for multiple myeloma. In 1978, through observational retrospective review of medical records, Dr. Kyle observed that not all cases of monoclonal gammopathy were benign. He introduced the term monoclonal gammopathy of undetermined significance (MGUS) to describe a condition that may potentially progress to multiple myeloma (MM), highlighting clinical inability in predicting which patients might progress. In 1980, Drs. Kyle and Greipp described 6 cases which did not fit the definitions of MGUS or MM, and they remained asymptomatic after at least 5 years of follow-up; they were proposed to have smoldering multiple myeloma (SMM). Over time, SMM was defined by arbitrary numerical values (≥10 % plasma cells in the bone marrow and serum M-protein concentration ≥ 3 g/dL). Numerous clinical scores have been developed to define high-risk groups for progression to MM. Current statistical models for progression provide only average risk scores, offering limited clinical utility since the risk of progression at an individual level remains unknown. Physician-scientists are focusing on emerging technologies, such as whole genome sequencing, tumor microenvironment analysis, and single-cell RNA sequencing, to understand precursor states at a molecular level. The overarching goal of these technologies is to better characterize monoclonal gammopathy and other myeloma precursor states. This will enable clinicians to provide more precise, individualized risk assessments and ultimately improve patient outcomes. This review outlines the history of MM precursor states, current definitions, challenges in risk stratification models, and the role of emerging technologies in enhancing predictions and outcomes.

Risk Factors and Predictors of Prolonged Mechanical Ventilation Following Cardiac Surgery: A Narrative Review.

The subset of patients requiring prolonged mechanical ventilation is significantly high worldwide, making it an important topic of continuous and ongoing research. Over the years, various articles have shown that there may be predictors of prolonged ventilation that could be applied in healthcare to make it more patient-centered. The available literature suggests that authors have different definitions of "prolonged" ventilation. However, most critical care units embrace caution if a patient needs mechanical ventilation for more than 48 to 72 hours. The major benefits of mechanical ventilation are an overall decrease in the work of breathing and the facilitation of relatively easier pumping from an ailing heart. An elevated risk of prolonged ventilation after cardiac surgery exists in patients with higher classes of heart failure (as classified by the New York Heart Association (NYHA) or Canadian Cardiovascular Society (CCS)), a pre-existing congenital or acquired cardiac abnormality, and patients with renal failure, to name a few. The impact on quality of life has also been widely studied; as mortality rates increase with factors like age and days dependent on ventilation. Patients undergoing prolonged ventilation constitute an administrative challenge for critical care units, highlighting how multiple patients in this bracket can overwhelm the healthcare system. The use of prediction models in this context can aid healthcare delivery tremendously. Using different predictors, we can craft tailor-made treatment options and achieve the goal of more ventilator-free days per patient.

PREVENT Equation: The Black Sheep among Cardiovascular Risk Scores? A Comparative Agreement Analysis of Nine Prediction Models in High-Risk Lithuanian Women.

Background and Objectives: In the context of female cardiovascular risk categorization, we aimed to assess the inter-model agreement between nine risk prediction models (RPM): the novel Predicting Risk of cardiovascular disease EVENTs (PREVENT) equation, assessing cardiovascular risk using SIGN, the Australian CVD risk score, the Framingham Risk Score for Hard Coronary Heart Disease (FRS-hCHD), the Multi-Ethnic Study of Atherosclerosis risk score, the Pooled Cohort Equation (PCE), the QRISK3 cardiovascular risk calculator, the Reynolds Risk Score, and Systematic Coronary Risk Evaluation-2 (SCORE2). Materials and Methods: A cross-sectional study was conducted on 6527 40-65-year-old women with diagnosed metabolic syndrome from a single tertiary university hospital in Lithuania. Cardiovascular risk was calculated using the nine RPMs, and the results were categorized into high-, intermediate-, and low-risk groups. Inter-model agreement was quantified using Cohen's Kappa coefficients. Results: The study uncovered a significant diversity in risk categorization, with agreement on risk category by all models in only 1.98% of cases. The SCORE2 model primarily classified subjects as high-risk (68.15%), whereas the FRS-hCHD designated the majority as low-risk (94.42%). The range of Cohen's Kappa coefficients (-0.09-0.64) reflects the spectrum of agreement between models. Notably, the PREVENT model demonstrated significant agreement with QRISK3 (κ = 0.55) and PCE (κ = 0.52) but was completely at odds with the SCORE2 (κ = -0.09). Conclusions: Cardiovascular RPM selection plays a pivotal role in influencing clinical decisions and managing patient care. The PREVENT model revealed balanced results, steering clear of the extremes seen in both SCORE2 and FRS-hCHD. The highest concordance was observed between the PREVENT model and both PCE and QRISK3 RPMs. Conversely, the SCORE2 model demonstrated consistently low or negative agreement with other models, highlighting its unique approach to risk categorization. These findings accentuate the need for additional research to assess the predictive accuracy of these models specifically among the Lithuanian female population.

Implementation of a dynamic model updating pipeline provides a systematic process for maintaining performance of prediction models.

OBJECTIVES: We describe the steps for implementing a dynamic updating pipeline for clinical prediction models and illustrate the proposed methods in an application of 5-year survival prediction in cystic fibrosis. STUDY DESIGN AND SETTING: Dynamic model updating refers to the process of repeated updating of a clinical prediction model with new information to counter performance degradation. We describe 2 types of updating pipeline: "proactive updating" where candidate model updates are tested any time new data are available, and "reactive updating" where updates are only made when performance of the current model declines or the model structure changes. Methods for selecting the best candidate updating model are based on measures of predictive performance under the 2 pipelines. The methods are illustrated in our motivating example of a 5-year survival prediction model in cystic fibrosis. Over a dynamic updating period of 10 years, we report the updating decisions made and the performance of the prediction models selected under each pipeline. RESULTS: Both the proactive and reactive updating pipelines produced survival prediction models that overall had better performance in terms of calibration and discrimination than a model that was not updated. Further, use of the dynamic updating pipelines ensured that the prediction model's performance was consistently and frequently reviewed in new data. CONCLUSION: Implementing a dynamic updating pipeline will help guard against model performance degradation while ensuring that the updating process is principled and data-driven.

Research progress on predictive models for malnutrition in cancer patients.

Disease-related malnutrition is a prevalent issue among cancer patients, affecting approximately 40-80% of those undergoing treatment. This condition is associated with numerous adverse outcomes, including extended hospitalization, increased morbidity and mortality, delayed wound healing, compromised muscle function and reduced overall quality of life. Moreover, malnutrition significantly impedes patients' tolerance of various cancer therapies, such as surgery, chemotherapy, and radiotherapy, resulting in increased adverse effects, treatment delays, postoperative complications, and higher referral rates. At present, numerous countries and regions have developed objective assessment models to predict the risk of malnutrition in cancer patients. As advanced technologies like artificial intelligence emerge, new modeling techniques offer potential advantages in accuracy over traditional methods. This article aims to provide an exhaustive overview of recently developed models for predicting malnutrition risk in cancer patients, offering valuable guidance for healthcare professionals during clinical decision-making and serving as a reference for the development of more efficient risk prediction models in the future.

Logistic regression analysis and machine learning for predicting post-stroke gait independence: a retrospective study.

This study investigated whether machine learning (ML) has better predictive accuracy than logistic regression analysis (LR) for gait independence at discharge in subacute stroke patients (n = 843) who could not walk independently at admission. We developed prediction models using LR and five ML algorithms-specifically, the decision tree (DT), support vector machine, artificial neural network, ensemble learning, and k-nearest neighbor methods. Functional Independence Measure sub-items were used to evaluate the ability to walk independently. Model predictive accuracies were evaluated using areas under receiver operating characteristic curves (AUCs) as well as accuracy, precision, recall, F1 score, and specificity. The AUC for DT (0.812) was significantly lower than those for the other algorithms (p < 0.01); however, the AUC for LR (0.895) did not differ significantly from those for the other models (0.893-0.903). Other performance metrics showed no substantial differences between LR and ML algorithms. In conclusion, the DT algorithm had significantly low predictive accuracy, and LR showed no significant difference in predictive accuracy compared with the other ML algorithms. As its predictive accuracy is similar to that of ML, LR can continue to be used for predicting the prognosis of gait independence, with additional advantages of being easily understandable and manually computable.

Correlation between coronary calcification and cardiac structure in non-dialysis patients with chronic kidney disease.

AIMS: We aim to explore the correlation between coronary artery calcification (CAC) score (CACS) and cardiac structure and function in chronic kidney disease (CKD) patients, create a clinical prediction model for severe CAC associated with cardiac ultrasound indexes. METHODS AND RESULTS: The study included 178 non-dialysis CKD patients who underwent CACS testing and collected general information, serological indices, cardiac ultrasound findings and follow-up on renal function, heart failure (HF) manifestations and re-hospitalization. The mean age of participants in the study cohort was 67.4 years; 59% were male, and 66.9% of patients had varying degrees of comorbid CAC. CKD patients with CACS > 100 were older, predominantly male and had a higher proportion of smoking, diabetes and hypertension (P < 0.05) compared with those with CACS = 0 and 0 < CACS ≤ 100, and had higher brain natriuretic peptide, serum magnesium and fibrinogen levels were also higher (P < 0.05). CACS was positively correlated with left atrial inner diameter (LAD), left ventricular end-diastolic inner diameter (LVDd), left ventricular volume at diastole (LVVd), output per beat (SV) and mitral orifice early diastolic blood flow velocity/early mitral annular diastolic myocardial motion velocity (E/e) (P < 0.05). We tested the associations between varying degrees of CAC and HF and heart valve calcification using multivariable-adjusted regression models. The risk of HF in patients with severe CAC was about 1.95 times higher than that in patients without coronary calcification, and the risk of heart valve calcification was 2.46 times higher than that in patients without coronary calcification. Heart valve calcification and HF diagnosis, LAD and LVDd are essential in predicting severe CAC. During a mean follow-up time of 18.26 ± 10.17 months, 65 (36.52%) patients had a composite renal endpoint event, of which 36 (20.22%) were admitted to renal replacement therapy. Patients with severe CAC had a higher risk of progression of renal function, re-admission due to cardiovascular and renal events and more pronounced symptoms of HF (P < 0.05). CONCLUSIONS: There is a correlation between CACS and cardiac structure and function in non-dialysis CKD patients, which may mainly involve abnormalities in left ventricular structure and cardiac diastolic function. CAC may affect renal prognosis and quality of survival in CKD patients. Based on clinical information, HF, valvular calcification status and indicators related to left ventricular hypertrophy can identify people at risk for severe CAC.

Clinician perspectives and recommendations regarding design of clinical prediction models for deteriorating patients in acute care.

BACKGROUND: Successful deployment of clinical prediction models for clinical deterioration relates not only to predictive performance but to integration into the decision making process. Models may demonstrate good discrimination and calibration, but fail to match the needs of practising acute care clinicians who receive, interpret, and act upon model outputs or alerts. We sought to understand how prediction models for clinical deterioration, also known as early warning scores (EWS), influence the decision-making of clinicians who regularly use them and elicit their perspectives on model design to guide future deterioration model development and implementation. METHODS: Nurses and doctors who regularly receive or respond to EWS alerts in two digital metropolitan hospitals were interviewed for up to one hour between February 2022 and March 2023 using semi-structured formats. We grouped interview data into sub-themes and then into general themes using reflexive thematic analysis. Themes were then mapped to a model of clinical decision making using deductive framework mapping to develop a set of practical recommendations for future deterioration model development and deployment. RESULTS: Fifteen nurses (n = 8) and doctors (n = 7) were interviewed for a mean duration of 42 min. Participants emphasised the importance of using predictive tools for supporting rather than supplanting critical thinking, avoiding over-protocolising care, incorporating important contextual information and focusing on how clinicians generate, test, and select diagnostic hypotheses when managing deteriorating patients. These themes were incorporated into a conceptual model which informed recommendations that clinical deterioration prediction models demonstrate transparency and interactivity, generate outputs tailored to the tasks and responsibilities of end-users, avoid priming clinicians with potential diagnoses before patients were physically assessed, and support the process of deciding upon subsequent management. CONCLUSIONS: Prediction models for deteriorating inpatients may be more impactful if they are designed in accordance with the decision-making processes of acute care clinicians. Models should produce actionable outputs that assist with, rather than supplant, critical thinking.

A Clinician's Guide to Understanding Bias in Critical Clinical Prediction Models.

This narrative review focuses on the role of clinical prediction models in supporting informed decision-making in critical care, emphasizing their 2 forms: traditional scores and artificial intelligence (AI)-based models. Acknowledging the potential for both types to embed biases, the authors underscore the importance of critical appraisal to increase our trust in models. The authors outline recommendations and critical care examples to manage risk of bias in AI models. The authors advocate for enhanced interdisciplinary training for clinicians, who are encouraged to explore various resources (books, journals, news Web sites, and social media) and events (Datathons) to deepen their understanding of risk of bias.

A predictive model for stunting among children under the age of three.

Background: In light of the global effort to eradicate stunting in childhood, the objective of this research endeavor was to assess the prevalence of stunting and associated factors, simultaneously construct and validate a risk prediction model for stunting among children under the age of three in Shenzhen, China. Methods: Using the stratified random sampling method, we selected 9,581 children under the age of three for research and analysis. The dataset underwent a random allocation into training and validation sets, adhering to a 8:2 split ratio. Within the training set, a combined approach of LASSO regression analysis and binary logistic regression analysis was implemented to identify and select the predictive variables for the model. Subsequently, model construction was conducted in the training set, encompassing model evaluation, visualization, and internal validation procedures. Finally, to assess the model's generalizability, external validation was performed using the validation set. Results: A total of 684 (7.14%) had phenotypes of stunt. Utilizing a combined approach of LASSO regression and logistic regression, key predictors of stunting among children under three years of age were identified, including sex, age in months, mother's education, father's age, birth order, feeding patterns, delivery mode, average daily parent-child reading time, average time spent in child-parent interactions, and average daily outdoor time. These variables were subsequently employed to develop a comprehensive prediction model for childhood stunting. A nomogram model was constructed based on these factors, demonstrating excellent consistency and accuracy. Calibration curves validated the agreement between the nomogram predictions and actual observations. Furthermore, ROC and DCA analyses indicated the strong predictive performance of the nomograms. Conclusions: The developed model for forecasting stunt risk, which integrates a spectrum of variables. This analytical framework presents actionable intelligence to medical professionals, laying down a foundational framework and a pivot for the conception and execution of preemptive strategies and therapeutic interventions.

Statistical and machine learning models for predicting spalling in CRCP.

Continuously reinforced concrete pavement (CRCP), crucial for the resilience of transportation infrastructure owing to its continuous steel reinforcement, confronts a critical challenge in the form of spalling-a distress phenomenon posing a threat to pavement durability and overall structural integrity. The detachment or breakage of concrete from the surface compromises CRCP's functionality and raises safety concerns and escalating maintenance costs. To address this pressing issue, our study investigates the multifaceted factors influencing spalling, employing a comprehensive approach that integrates statistical and machine learning techniques for predictive modeling. Descriptive statistics meticulously profile the dataset, emphasizing age, thickness, precipitation, temperature, and traffic parameters. Regression analysis unveils key relationships, emphasizing the significance of age, annual temperature, annual precipitation, maximum humidity, and the initial International Roughness Index (IRI) as influential factors. The correlation matrix heatmap guides feature selection, elucidating intricate interdependencies. Simultaneously, feature importance analysis identifies age, Average Annual Daily Traffic (AADT), and total pavement thickness as crucial contributors to spalling. In machine learning, adopting models, including Gaussian Process Regression and ensemble tree models, is grounded in their diverse capabilities and suitability for the complex task at hand. Their varying predictive accuracies underscore the importance of judicious model selection. This research advances pavement engineering practices by offering nuanced insights into factors influencing spalling in CRCP, refining our understanding of spalling influences. Consequently, the study not only opens avenues for developing improved predictive methodologies but also enhances the durability of CRCP infrastructure, addressing broader implications for informed decision-making in transportation infrastructure management. The selection of Gaussian Process Regression and ensemble tree models stems from their adaptability to capture intricate relationships within the dataset, and their comparative performance provides valuable insights into the diverse predictive capabilities of these models in the context of CRCP spalling.

Design and implementation of a portable snapshot multispectral imaging crop-growth sensor.

The timely and accurate acquisition of crop-growth information is a prerequisite for implementing intelligent crop-growth management, and portable multispectral imaging devices offer reliable tools for monitoring field-scale crop growth. To meet the demand for obtaining crop spectra information over a wide band range and to achieve the real-time interpretation of multiple growth characteristics, we developed a novel portable snapshot multispectral imaging crop-growth sensor (PSMICGS) based on the spectral sensing of crop growth. A wide-band co-optical path imaging system utilizing mosaic filter spectroscopy combined with dichroic mirror beam separation is designed to acquire crop spectra information over a wide band range and enhance the device's portability and integration. Additionally, a sensor information and crop growth monitoring model, coupled with a processor system based on an embedded control module, is developed to enable the real-time interpretation of the aboveground biomass (AGB) and leaf area index (LAI) of rice and wheat. Field experiments showed that the prediction models for rice AGB and LAI, constructed using the PSMICGS, had determination coefficients (R²) of 0.7 and root mean square error (RMSE) values of 1.611 t/ha and 1.051, respectively. For wheat, the AGB and LAI prediction models had R² values of 0.72 and 0.76, respectively, and RMSE values of 1.711 t/ha and 0.773, respectively. In summary, this research provides a foundational tool for monitoring field-scale crop growth, which is important for promoting high-quality and high-yield crops.

Understanding how a personalized risk prediction tool (VALUE-PERSARC) supports informed treatment decisions of soft-tissue sarcomas patients in daily clinical practice - A mixed methods study.

INTRODUCTION: Risk prediction models (RPM) can help soft-tissue sarcoma(STS) patients and clinicians make informed treatment decisions by providing them with estimates of (disease-free) survival for different treatment options. However, it is unknown how RPMs are used in the clinical encounter to support decision-making. This study aimed to understand how a PERsonalised SARcoma Care (PERSARC) RPM is used to support treatment decisions and which barriers and facilitators influence its use in daily clinical practice. METHODS: A convergent mixed-methods design is used to understand how PERSARC is integrated in the clinical encounter in three Dutch sarcoma centers. Data were collected using qualitative interviews with STS patients (n = 15) and clinicians (n = 8), quantitative surveys (n = 50) and audiotaped consultations (n = 30). Qualitative data were analyzed using thematic analysis and integrated with quantitative data through merging guided by the SEIPS model. RESULTS: PERSARC was generally used to support clinicians' proposed treatment plan and not to help patients weigh available treatment options. Use of PERSARC in decision-making was hampered by clinician's doubts about whether there were multiple viable treatment options,the accuracy of risk estimates, and time constraints. On the other hand, use of PERSARC facilitated clinicians to estimate and communicate the expected benefit of adjuvant therapy to patients. CONCLUSION: PERSARC was not used to support informed treatment decision-making in STS patients. Integrating RPMs into clinical consultations requires acknowledgement of their benefits in facilitating clinicians' estimation of the expected benefit of adjuvant therapies and information provision to patients, while also considering concerns regarding RPM quality and treatment options' viability.

Interpretable machine learning models for the prediction of all-cause mortality and time to death in hemodialysis patients.

INTRODUCTION: The elevated mortality and hospitalization rates among hemodialysis (HD) patients underscore the necessity for the development of accurate predictive tools. This study developed two models for predicting all-cause mortality and time to death-one using a comprehensive database and another simpler model based on demographic and clinical data without laboratory tests. METHOD: A retrospective cohort study was conducted from January 2017 to June 2023. Two models were created: Model A with 85 variables and Model B with 22 variables. We assessed the models using random forest (RF), support vector machine, and logistic regression, comparing their performance via the AU-ROC. The RF regression model was used to predict time to death. To identify the most relevant factors for prediction, the Shapley value method was used. RESULTS: Among 359 HD patients, the RF model provided the most reliable prediction. The optimized Model A showed an AU-ROC of 0.86 ± 0.07, a sensitivity of 0.86, and a specificity of 0.75 for predicting all-cause mortality. It also had an R2 of 0.59 for predicting time to death. The optimized Model B had an AU-ROC of 0.80 ± 0.06, a sensitivity of 0.81, and a specificity of 0.70 for predicting all-cause mortality. In addition, it had an R2 of 0.81 for predicting time to death. CONCLUSION: Two new interpretable clinical tools have been proposed to predict all-cause mortality and time to death in HD patients using machine learning models. The minimal and readily accessible data on which Model B is based makes it a valuable tool for integrating into clinical decision-making processes.

The use of imputation in clinical decision support systems: a cardiovascular risk management pilot vignette study among clinicians.

Aims: A major challenge of the use of prediction models in clinical care is missing data. Real-time imputation may alleviate this. However, to what extent clinicians accept this solution remains unknown. We aimed to assess acceptance of real-time imputation for missing patient data in a clinical decision support system (CDSS) including 10-year cardiovascular absolute risk for the individual patient. Methods and results: We performed a vignette study extending an existing CDSS with the real-time imputation method joint modelling imputation (JMI). We included 17 clinicians to use the CDSS with three different vignettes, describing potential use cases (missing data, no risk estimate; imputed values, risk estimate based on imputed data; complete information). In each vignette, missing data were introduced to mimic a situation as could occur in clinical practice. Acceptance of end-users was assessed on three different axes: clinical realism, comfortableness, and added clinical value. Overall, the imputed predictor values were found to be clinically reasonable and according to the expectations. However, for binary variables, use of a probability scale to express uncertainty was deemed inconvenient. The perceived comfortableness with imputed risk prediction was low, and confidence intervals were deemed too wide for reliable decision-making. The clinicians acknowledged added value for using JMI in clinical practice when used for educational, research, or informative purposes. Conclusion: Handling missing data in CDSS via JMI is useful, but more accurate imputations are needed to generate comfort in clinicians for use in routine care. Only then can CDSS create clinical value by improving decision-making.