Clinical Prediction Tool Research Articles

The CTOX-Score, a clinical risk prediction tool for cardiovascular toxicity secondary to cancer therapies

Abstract Introduction Cardiovascular toxicity (cardiotoxicity) is recognized as a major side-effect of cancer therapies. As early diagnosis and management is crucial in clinical practice1,2, knowledge about risk factors and risk scores is scarce3,4. Purpose The aim of this study is to develop a clinical prediction score to identify patients at high/very high risk of cardiotoxicity. Methods The CARDIOTOX registry5,6 included patients receiving cancer therapies related to moderate/high risk for cardiotoxicity (2012-2017). Clinical, laboratory and echo parameters were collected at baseline and at 3 weeks, 3 and 6 months, 1, 1.5 and 2 years after initiation of cancer therapy. Patients were classified according to current cardioncology guidelines2 and divided in two groups: no or mild cardiotoxicity vs moderate or high cardiotoxicity. Difference between groups were tested with t-student or U Mann-Withney for continuous variables and Fisher’s exact test for categorical data. Variables with p<0.05 were included in a multivariate binary logistic regression model to find independent predictors of cardiotoxicity and construct a clinical risk score, CTOX-Score. The calibration was evaluated by Hosmer-Lemeshow goodness-of-fit test and discrimination using ROC curves. Results From the 1324 individuals included in the registry we discarded all those with pre-existing symptomatic heart failure or LVEF<40% at baseline and those with incomplete baseline data. We considered 998 patients, aged 54.62±14.15 years, 176 men (17.6%), of which 53 (5.3%) developed moderate or severe cardiotoxicity. These patients had lower baseline LVEF (59.91±7.50% vs 64.20±5.88%), higher creatinine levels (0.90 (0.76, 1.10) mg/dl vs 0.74 (0.62, 0.90) mg/dl) and higher NT-ProBNP (177 (58, 476) pg/ml vs 66 (38, 133) pg/ml) compared with patients with no or mild cardiotoxicity (p<0.001). We found previous radiotherapy (OR=4.66, CI:1.24-17.52), acute myeloid leukemia (OR=6.85; CI:1.16-40.50), monoclonal antibodies (OR=3.27; CI:1.35-7.89), LVEF (OR=0.96; CI:0.84-0.98) and serum creatinine (OR=5.43; CI:1.63-18.14) as independent predictors of cardiotoxicity (p<0.05). A clinical risk score was developed based in beta coefficient of variables (Table 1). The model has good calibration according to Hosmer-Lemeshow goodness-of-fit (χ2=2.800, p=0.424) and good discrimination power (AUC:0.780, CI:0.69-0.87; p<0.001). The best cut-off value of CTOX-Score is ≥3 points (Sensitivity:70.00%, Specificity:72.25%, NPV:98.11%). Patients were classified in four risk categories: low (0-1 points); moderate (2); high (3-4); very high (≥5) (Figure 1). The model has good accuracy to identify very high-risk patients (Specificity 98.80%). Conclusion The CTOX-Score is a clinical risk prediction model to identify patients at high/very high-risk of cardiotoxicity and could allow for more personalized monitoring of patients. Additional studies are needed to externally validate the model prior to implementation in clinical practice.Multivariate binary logistic regressionCTOX-Score values among population

Differences in Presentation of Ischaemic and Haemorrhagic Stroke: A Systematic Review and Meta-Analysis

Abstract Background Stroke is the 2nd leading cause of death worldwide. Stroke is diagnosed by the combination of clinical symptoms and signs, and neuroimaging. Clinical features may differ between the subtypes of ischaemic and haemorrhagic stroke. We investigated whether there are differences in clinical presentation of acute ischaemic and haemorrhagic stroke. Methods We conducted a systematic review and meta-analysis according to the PRISMA statement. Inclusion criteria were (1) cohort, cross-sectional, case-control, randomised controlled trial, systematic review or meta-analysis; (2) consecutive admissions of adult individuals with an acute ischaemic or haemorrhagic stroke, confirmed by neuroimaging and (3) comparisons possible between stroke subtypes in acute stroke symptom(s). A random-effects model was used for our analyses. Results We included 58 studies (n=12,878,716; ischaemic stroke=10,814,293; haemorrhagic stroke=2,064,423). The mean age of participants was 65.54+13.84 with 44.98% women. In haemorrhagic stroke, altered GCS occurred more frequently than in ischaemic stroke (OR, 3.93 [95% CI, 2.81–5.49]; AIS/ICH=382,110/59,877, 40 studies), as did headache (OR, 3.34 [95% CI, 2.68–4.17]; AIS/ICH=22,413/6,018; 43 studies), seizure (OR, 2.42 [95% CI, 1.62–3.65]; AIS/ICH=10,427,262/2,004,681; 20 studies), vomiting (OR, 3.82 [95% CI, 2.62–5.57]; AIS/ICH=7,736/3,225; 25 studies), neck stiffness (OR, 5.21 [95% CI, 2.22–12.21]; AIS/ICH=511/168; 3 studies), syncope (OR, 2.95 [95% CI, 2.12–4.12]; AIS/ICH=2,427/494; 6 studies) and dizziness (OR, 1.33 [95% CI, 1.05–1.68]; AIS/ICH=4,730/1,213; 11 studies). Hemiplegia occurred more frequently in ischaemic stroke (OR, 0.67 [95% CI, 0.49–0.91]; AIS/ICH=15,857/4,338; 31 studies) than haemorrhagic stroke, as did ataxia (OR, 0.73 [95% CI, 0.61–0.86]; AIS/ICH=7,741/2,244; 8 studies) and morning onset (OR, 0.41 [95% CI, 0.32– 0.54]; AIS/ICH=2,721/495; 4 studies). Conclusion This review focused on synthesizing existing evidence on differences in clinical presentation between ischaemic and haemorrhagic stroke. It suggests there are substantive differences in stroke symptoms between these subtypes. These results may provide insights into future directions for clinical prediction tool development.

A Pre-Hospital Prediction Tool for Stroke Type Utilising Machine Learning Techniques

Abstract Background Stroke is a leading cause of death worldwide and leaves most survivors with permanent disability. 12.2 million people suffer strokes annually, of which 70% occur in low- and middle-income countries (LMIC). Stroke presents diagnostic challenges which limits access to effective, but time-sensitive, reperfusion therapies. Currently, stroke is diagnosed by the combination of clinical symptoms and signs and brain imaging. The aim of this study was to develop clinical prediction tools, for differentiating acute ischemic stroke (AIS) and intracerebral haemorrhage (ICH) in the pre-hospital setting without neuroimaging, utilising machine learning (ML). Methods We included 5349 patients with confirmed acute stroke who presented within 6 hours of symptom onset, from the INTERSTROKE case-control study. We compared predictions using six commonly used ML algorithms for classification i.e. multivariate logistic regression (MLR), k-nearest neighbour (KNN), support vector machine (SVM), neural networks (NN), random forests (RF), XGBoost. Algorithm inputs included medical history, symptoms and signs, and point-of-care blood tests, with an output of final diagnosis. Results The training cohort included 4280 patients with 3084 ischemic stroke and 1196 ICH cases, and the test cohort included 1069 patients with 771 ischemic stroke and 298 ICH cases. From 174 potential variables, we used univariate analyses to select 52 candidate variables for inclusion in the ML algorithms. These were selected based on their ability to predict (p < 0.20) stroke subtype. The AUCs in the test cohort for each of the ML classification models were: MLR 0.819, KNN 0.795, SVM 0.802, NN 0.814, RF 0.814, and XGBoost 0.807. Conclusion ML models showed great potential to predict stroke type at the prehospital stage and have comparable predictive abilities to previously developed ML prediction tools. This may facilitate point-of-care decisions and management of stroke in the pre-hospital setting in the future.

Identifying metabolic dysfunction-associated steatotic liver disease in patients with type 2 diabetes mellitus using clinic-based prediction tools.

Metabolic dysfunction-associated steatotic liver disease (MASLD), formerly known as non-alcoholic fatty liver disease (NAFLD), is a global cause of chronic liver disease. The prevalence of MASLD is high in patients with type 2 diabetes mellitus (T2DM). Various non-invasive tools such as the fibrosis-4 index (FIB-4) and NAFLD fibrosis score (NFS), liver ultrasound, and FibroScan can aid in the detection of liver fibrosis in MASLD, while the Hamaguchi ultrasound-based liver grading system has demonstrated high sensitivity and specificity comparable to liver biopsy. We assessed the frequency of MASLD in patients with T2DM using the liver ultrasound Hamaguchi score and the accuracy of NFS and Fib-4 in identifying MASLD. We retrospectively collected data and reviewed the charts of all patients with T2DM who underwent liver ultrasound and laboratory tests during the past 5 years. A total of 6,214 medical records were screened, and only 153 patients (68.6% women; mean age, 59 ± 12.2 years) fulfilled the selection criteria. MASLD was diagnosed using the Hamaguchi grading criteria in 45.1% of patients. A high/intermediate NFS had a higher sensitivity (79.7%) for diagnosing MASLD with a specificity of 10.7%, while a high/intermediate Fib-4 score showed only 30.4% sensitivity but a higher specificity of 54.8%. Our study indicates that MASLD is frequent in patients with T2DM, and clinical prediction tools such as NFS and Fib-4 can be applied in clinic/primary care settings with variable results.

Tuberculosis-Associated Respiratory Disability in Children, Adolescents, and Adults: Protocol for a Systematic Review and Individual Participant Data Meta-Analysis.

Approximately 2% of the global population has survived tuberculosis (TB). Increasing evidence indicates that a significant proportion of pulmonary TB survivors develop TB-associated respiratory disability, commonly referred to as post-TB lung disease (PLTD) and marked by impaired respiratory function, persistent symptoms, and activity limitations. However, the prevalence, risk factors, and progression of TB-associated respiratory disability throughout the life course are not well understood. To address these gaps, we will undertake a systematic review and individual participant-level data meta-analysis (IPD-MA) focusing on TB-associated respiratory disability in children, adolescents, and adults successfully treated for pulmonary TB. We will systematically search MEDLINE, Embase, CENTRAL, Global Index Medicus, and medRxiv for original studies investigating TB-associated respiratory disability in people of all ages who have completed treatment for microbiologically confirmed or clinically diagnosed pulmonary TB. Authors of eligible studies will be invited to contribute de-identified data and form a collaborative group. Primary outcomes will be (1) abnormal lung function based on spirometry parameters and (2) chronic respiratory symptoms. We will estimate the overall and subgroup-specific prevalence of each outcome through IPD meta-analysis. Next, we will develop clinical prediction tools assessing the risk of future TB-associated respiratory disability at (i) the start of TB treatment and (ii) end of TB treatment for those without existing signs of disability. Finally, we will use stepwise hierarchical modelling to identify epidemiological determinants of respiratory disability. This study has been approved by the ethics review boards at the Rhode Island Hospital (2138217-2) and the Research Institute of the McGill University Health Centre (2024-10345). Individual study authors will be required to obtain institutional approval prior to sharing data. Results will be disseminated through open-access, peer-reviewed publications and conference presentations. CRD42024529906.

Early identification of postoperative remission for thyrotropin-secreting adenomas.

Thyrotropin-secreting adenoma (TSHoma) is a rare type of pituitary adenoma, occurring in one per million people. Little is known about TSHoma. We summarized the demographic, clinical and hormonal characteristics of TSHoma based on a single-centre experience. Moreover, we explored the predictive value of postoperative thyroid function for long-term remission. We retrospectively analysed 63 patients who were diagnosed as TSHoma and surgically treated at our hospital from January 2015 to June 2021. The preoperative clinical characteristics were analysed and compared between remission and nonremission groups. Thyroid function was measured at 1 day, 1 month, 3 months, 6 months, 12 months and over 12 months after surgery to determine whether they could predict long-term remission. The male to female ratio for TSHoma was 1.25. The mean age at diagnosis was 45 ± 12 years. Clinical presentation was varied, presenting with hyperthyroidism (68.25%), space-occupying effect (15.87%), amenorrhea (7.14% of female patients) and nonsymptoms (22.22%). 88.14% of patients achieved postoperative endocrinological remission. Larger tumour size and tumour invasion into cavernous sinus and suprasellar with chiasmal compression were strong predictors of lower rates of endocrinological remission. Postoperative thyroid function at 3 months was a viable diagnostic predictor for postoperative remission, especially for FT4 level with a 20.65 pmol/L cutoff. Tumour size and extent are major prognostic factors for remission. Postoperative thyroid function at 3 months could be used as a clinical prediction tool for long-term endocrinological remission.

Clinical screening tool for early detection of congenital heart disease in children living at high altitude

Background: Congenital heart diseases (CHD) have a high morbidity and mortality and its early detection is critical. The aim of the study is to develop a clinical screening tool for early detection of children with congenital heart disease at high altitude. Methods: This was a hospital based cross sectional study. All children between age 0 to 1 year visiting the OPD and admitted in indoor services of pediatrics with suspected heart disease based on pre-defined clinical criteria were evaluated for development of clinical screening tool for prediction of presence of CHD using parameters; heart rate (HR), respiratory rate (RR), ratio of HR/RR, pulse oximetry, presence of precordial pulsations and murmurs. Then diagnostic performance of these tools was calculated by using ECHO as a gold standard test. Results: A total of 102 study participants were included in our study. Among the total, 79 (77.5%) had underlying CHD. Result was considered positive if any of them was pres ent. In children age less than one year living at high altitude suspected to have high risk for presence of CHD and/or arterial oxygen saturation of less than 87.2%, this screening tool has sensitivity of 78.79% and specificity of 66.67%. Conclusions: This study concluded that combination of screening tools along with pulse oximetry in the community settings of developing countries are better in early detection and timely management of CHD than using these tests/ parameters alone.

Validating and Updating GRASP: An Evidence-Based Framework for Grading and Assessment of Clinical Predictive Tools

BackgroundWhen selecting clinical predictive tools, clinicians are challenged with an overwhelming and ever-growing number, most of which have never been implemented or evaluated for effectiveness. The authors developed an evidence-based framework for grading and assessment of predictive tools (GRASP). The objective of this study is to refine, validate GRASP, and assess its reliability for consistent application. MethodsA mixed-methods study was conducted, involving an initial web-based survey for feedback from a wide group of international experts in clinical prediction to refine the GRASP framework, followed by reliability testing with two independent researchers assessing eight predictive tools. The survey involved 81 experts who rated agreement with the framework's criteria on a five-point Likert scale and provided qualitative feedback. The reliability of the GRASP framework was evaluated through interrater reliability testing using Spearman's rank correlation coefficient. ResultsThe survey yielded strong agreement of the experts with the framework's evaluation criteria, overall average score: 4.35/5, highlighting the importance of predictive performance, usability, potential effect, and post-implementation impact in grading clinical predictive tools. Qualitative feedback led to significant refinements, including detailed categorisation of evidence levels and clearer representation of evaluation criteria. Interrater reliability testing showed high agreement between researchers and authors (0.994) and among researchers (0.988), indicating strong consistency in tool grading. ConclusionThe GRASP framework provides a high-level, evidence-based, and comprehensive, yet simple and feasible, approach to evaluate, compare, and select the best clinical predictive tools, with strong expert agreement and high interrater reliability. It assists clinicians in selecting effective tools by grading them on the level of validation of predictive performance before implementation, usability and potential effect during planning for implementation, and post-implementation impact on healthcare processes and clinical outcomes. Future studies should focus on the framework's application in clinical settings and its impact on decision-making and guideline development.

Development and validation of a nomogram for major adverse cardiovascular events after chronic total occlusion percutaneous coronary intervention for ischemic heart failure.

Chronic total occlusion percutaneous coronary intervention (CTO-PCI) is an available means of revascularization in patients with ischemic heart failure (IHF). However, the prognosis of IHF patients undergoing CTO-PCI remains unclear due to the lack of reliable clinical predictive tools. This study aimed to establish a nomogram for major adverse cardiovascular events (MACE) after CTO-PCI in IHF patients. Sixty-seven potential predictive variables for MACE in 560 IHF patients undergoing CTO-PCI were screened using least absolute shrinkage and selection operator regression. A nomogram was constructed based on multivariable Cox regression to visualize the risk of MACE, and then evaluation was carried out using the concordance index (C-index), time-independent receiver operating characteristic (timeROC) curves, calibration curves, and decision curve analysis (DCA). During a median follow-up of 32.0 months, there were 208 MACE occurrences. Seven variables were selected for nomogram construction: age, left ventricular ejection fraction, left ventricular end-diastolic diameter, N-terminal precursor B-type diuretic peptide, bending, and use of intravascular ultrasound and beta-blockers. The C-index was 0.715 (0.680-0.750) and the internal validation result was 0.715 (0.676-0.748). The timeROC area under the curve at 6 months, 1 year, and 2 years was 0.750 (0.653-0.846), 0.747 (0.690-0.804), and 0.753 (0.708-0.798), respectively. The calibration curves and DCA showed the nomogram had acceptable calibration and clinical applicability. We developed a simple and efficient nomogram for MACE after CTO-PCI in IHF patients, which helps in early risk stratification and postoperative management optimization.

Role of artificial intelligence applied to ultrasound in gynecology oncology: A systematic review.

The aim of this paper was to explore the role of artificial intelligence (AI) applied to ultrasound imaging in gynecology oncology. Web of Science, PubMed, and Scopus databases were searched. All studies were imported to RAYYAN QCRI software. The overall quality of the included studies was assessed using QUADAS-AI tool. Fifty studies were included, of these 37/50 (74.0%) on ovarian masses or ovarian cancer, 5/50 (10.0%) on endometrial cancer, 5/50 (10.0%) on cervical cancer, and 3/50 (6.0%) on other malignancies. Most studies were at high risk of bias for subject selection (i.e., sample size, source, or scanner model were not specified; data were not derived from open-source datasets; imaging preprocessing was not performed) and index test (AI models was not externally validated) and at low risk of bias for reference standard (i.e., the reference standard correctly classified the target condition) and workflow (i.e., the time between index test and reference standard was reasonable). Most studies presented machine learning models (33/50, 66.0%) for the diagnosis and histopathological correlation of ovarian masses, while others focused on automatic segmentation, reproducibility of radiomics features, improvement of image quality, prediction of therapy resistance, progression-free survival, and genetic mutation. The current evidence supports the role of AI as a complementary clinical and research tool in diagnosis, patient stratification, and prediction of histopathological correlation in gynecological malignancies. For example, the high performance of AI models to discriminate between benign and malignant ovarian masses or to predict their specific histology can improve the diagnostic accuracy of imaging methods.

Using social risks to predict unplanned hospital readmission and emergency care among hospitalized Veterans.

(1) To estimate the association of social risk factors with unplanned readmission and emergency care after a hospital stay. (2) To create a social risk scoring index. We analyzed administrative data from the Department of Veterans Affairs (VA) Corporate Data Warehouse. Settings were VA medical centers that participated in a national social work staffing program. We grouped socially relevant diagnoses, screenings, assessments, and procedure codes into nine social risk domains. We used logistic regression to examine the extent to which domains predicted unplanned hospital readmission and emergency department (ED) use in 30 days after hospital discharge. Covariates were age, sex, and medical readmission risk score. We used model estimates to create a percentile score signaling Veterans' health-related social risk. We included 156,690 Veterans' admissions to a VA hospital with discharged to home from 1 October, 2016 to 30 September, 2022. The 30-day rate of unplanned readmission was 0.074 and of ED use was 0.240. After adjustment, the social risks with greatest probability of readmission were food insecurity (adjusted probability = 0.091 [95% confidence interval: 0.082, 0.101]), legal need (0.090 [0.079, 0.102]), and neighborhood deprivation (0.081 [0.081, 0.108]); versus no social risk (0.052). The greatest adjusted probabilities of ED use were among those who had experienced food insecurity (adjusted probability 0.28 [0.26, 0.30]), legal problems (0.28 [0.26, 0.30]), and violence (0.27 [0.25, 0.29]), versus no social risk (0.21). Veterans with social risk scores in the 95th percentile had greater rates of unplanned care than those with 95th percentile Care Assessment Needs score, a clinical prediction tool used in the VA. Veterans with social risks may need specialized interventions and targeted resources after a hospital stay. We propose a scoring method to rate social risk for use in clinical practice and future research.

A clinical predictive model identifies pediatric patients at risk for eosinophilic esophagitis

BackgroundIdentifying children needing endoscopic evaluation for suspected eosinophilic esophagitis (EoE) is crucial for prompt diagnosis and management. AimsWe aimed to develop a clinical prediction tool to distinguish children with EoE from children without the disease before endoscopy. MethodsWe conducted a retrospective case-control study of children undergoing upper endoscopy at a tertiary care center. Clinical characteristics before endoscopy were extracted from 380 EoE cases and 380 controls without EoE. We built a predictive model for case-control status and performed age-stratified analyses. ResultsAfter multivariable analysis, history of adaptive eating behaviors, food allergy, food impaction, male sex, and regurgitation were independently associated with EoE, and abdominal pain and failure to thrive with control status (AUC 0.81). Food allergy and male sex were predictors of EoE across all ages. Regurgitation and adaptive eating behaviors were specific to EoE in early (0–5 years) (AUC 0.74) and middle childhood (6–11 years) (AUC 0.82), while dysphagia and food impaction were specific to EoE in the adolescence (12–17 years) (AUC 0.87). ConclusionWe determined age-specific clinical features that predict EoE with good discrimination in a pediatric population before endoscopy. Validation of this model in an independent population can confirm the utility of this tool.

Development and validation of a clinical breast cancer tool for accurate prediction of recurrence

Given high costs of Oncotype DX (ODX) testing, widely used in recurrence risk assessment for early-stage breast cancer, studies have predicted ODX using quantitative clinicopathologic variables. However, such models have incorporated only small cohorts. Using a cohort of patients from the National Cancer Database (NCDB, n = 53,346), we trained machine learning models to predict low-risk (0-25) or high-risk (26-100) ODX using quantitative estrogen receptor (ER)/progesterone receptor (PR)/Ki-67 status, quantitative ER/PR status alone, and no quantitative features. Models were externally validated on a diverse cohort of 970 patients (median follow-up 55 months) for accuracy in ODX prediction and recurrence. Comparing the area under the receiver operating characteristic curve (AUROC) in a held-out set from NCDB, models incorporating quantitative ER/PR (AUROC 0.78, 95% CI 0.77–0.80) and ER/PR/Ki-67 (AUROC 0.81, 95% CI 0.80–0.83) outperformed the non-quantitative model (AUROC 0.70, 95% CI 0.68–0.72). These results were preserved in the validation cohort, where the ER/PR/Ki-67 model (AUROC 0.87, 95% CI 0.81–0.93, p = 0.009) and the ER/PR model (AUROC 0.86, 95% CI 0.80–0.92, p = 0.031) significantly outperformed the non-quantitative model (AUROC 0.80, 95% CI 0.73–0.87). Using a high-sensitivity rule-out threshold, the non-quantitative, quantitative ER/PR and ER/PR/Ki-67 models identified 35%, 30% and 43% of patients as low-risk in the validation cohort. Of these low-risk patients, fewer than 3% had a recurrence at 5 years. These models may help identify patients who can forgo genomic testing and initiate endocrine therapy alone. An online calculator is provided for further study.

Development and application of a risk nomogram for the prediction of risk of carbapenem-resistant Acinetobacter baumannii infections in neuro-intensive care unit: a mixed method study

ObjectiveThis study aimed to develop and apply a nomogram with good accuracy to predict the risk of CRAB infections in neuro-critically ill patients. In addition, the difficulties and expectations of application such a tool in clinical practice was investigated.MethodsA mixed methods sequential explanatory study design was utilized. We first conducted a retrospective study to identify the risk factors for the development of CRAB infections in neuro-critically ill patients; and further develop and validate a nomogram predictive model. Then, based on the developed predictive tool, medical staff in the neuro-ICU were received an in-depth interview to investigate their opinions and barriers in using the prediction tool during clinical practice. The model development and validation is carried out by R. The transcripts of the interviews were analyzed by Maxqda.ResultsIn our cohort, the occurrence of CRAB infections was 8.63% (47/544). Multivariate regression analysis showed that the length of neuro-ICU stay, male, diabetes, low red blood cell (RBC) count, high levels of procalcitonin (PCT), and number of antibiotics ≥ 2 were independent risk factors for CRAB infections in neuro-ICU patients. Our nomogram model demonstrated a good calibration and discrimination in both training and validation sets, with AUC values of 0.816 and 0.875. Additionally, the model demonstrated good clinical utility. The significant barriers identified in the interview include “skepticism about the accuracy of the model”, “delay in early prediction by the indicator of length of neuro-ICU stay”, and “lack of a proper protocol for clinical application”.ConclusionsWe established and validated a nomogram incorporating six easily accessed indicators during clinical practice (the length of neuro-ICU stay, male, diabetes, RBC, PCT level, and the number of antibiotics used) to predict the risk of CRAB infections in neuro-ICU patients. Medical staff are generally interested in using the tool to predict the risk of CRAB, however delivering clinical prediction tools in routine clinical practice remains challenging.

Comprehensive proteomic profiling of lung adenocarcinoma: development and validation of an innovative prognostic model.

Lung adenocarcinoma (LUAD), a global leading cause of cancer deaths, remains inadequately addressed by current protein biomarkers. Our study focuses on developing a protein-based risk signature for improved prognosis of LUAD. We employed the least absolute shrinkage and selection operator (LASSO)-COX algorithm on The Cancer Genome Atlas database to construct a prognostic model incorporating six proteins (CD49B, UQCRC2, SMAD1, FOXM1, CD38, and KAP1). The model's performance was assessed using principal component, Kaplan-Meier (KM), and receiver operating characteristic (ROC) analysis, indicating strong predictive capability. The model stratifies LUAD patients into distinct risk groups, with further analysis revealing its potential as an independent prognostic factor. Additionally, we developed a predictive nomogram integrating clinicopathologic factors, aimed at assisting clinicians in survival prediction. Gene set enrichment analysis (GSEA) and examination of the tumor immune microenvironment were conducted, highlighting metabolic pathways in high-risk genes and immune-related pathways in low-risk genes, indicating varied immunotherapy sensitivity. Validation through immunohistochemistry from the Human Protein Atlas (HPA) database and immunofluorescence staining of clinical samples was performed, particularly focusing on CD38 expression. Our six-protein model (CD49B, UQCRC2, SMAD1, FOXM1, CD38, KAP1) effectively categorized LUAD patients into high and low-risk groups, confirmed by principal component, KM, and ROC analyses. The model showed high predictive accuracy, with distinct survival differences between risk groups. Notably, CD38, traditionally seen as protective, was paradoxically associated with poor prognosis in LUAD, a finding supported by immunohistochemistry and immunofluorescence data. GSEA revealed that high-risk genes are enriched in metabolic pathways, while low-risk genes align with immune-related pathways, suggesting better immunotherapy response in the latter group. This study presented a novel prognostic protein model for LUAD, highlighting the CD38 expression paradox and enhancing our understanding of protein roles in lung cancer progression. It offered new clinical tools for prognosis prediction and provided assistance for future lung cancer pathogenesis research.

Integrating clinical variables with magnetic resonance imaging and electroanatomic mapping parameters to predict response to first-time and repeat atrial fibrillation ablation procedures

Abstract Background The heterogeneity in patient response to atrial fibrillation ablation mandates the development of methods to predict clinical outcomes. Several clinical risk scores exist to prognosticate patients post ablation. Magnetic resonance imaging can quantify anatomical and functional atrial properties, whilst electroanatomic mapping data provides unparalleled atrial substrate characterisation. These data could be leveraged to predict ablation outcomes more accurately. Purpose To incorporate magnetic resonance imaging and electroanatomic mapping parameters with clinical variables to predict response to 1) first-time and 2) repeat atrial fibrillation ablation. Methods A retrospective analysis of 123 consecutive patients undergoing first-time atrial fibrillation ablation including pre-procedural atrial magnetic resonance imaging was performed. Data were split into training (n=68) and test (n=55) cohorts depending on data availability for clinical risk score calculation. The APPLE, DR-FLASH, FLAME, HATCH, HATCH+OSA, CHA2Ds2VASc and CAAP-AF scores were calculated for patients in the training cohort. Univariate logistic regression was used to identify variables associated with arrhythmia recurrence which were then combined into a multivariate logistic regression model. Area under the curve receiver operating characteristic (AUC-ROC) analysis was used to compare the ability of clinical risk scores and the combined model to predict arrhythmia recurrence risk after one procedure. The model's ability to predict repeat ablation response was tested in 38 patients who underwent redo procedures. The ROC optimal cut-off score was used to divide patients into two groups (high and low arrhythmia recurrence risk) for time-to-event analysis. Results In univariate analysis, weight, age, hypertension, left atrial ejection fraction and mean left atrial bipolar voltage were associated with arrhythmia recurrence after one procedure. The multivariate logistic regression model achieved an AUC of 0.7491 (95% confidence interval (CI) 0.6269-0.8712) in the training cohort and 0.7457 (95% CI 0.6137-0.8778) in the test cohort for predicting arrhythmia recurrence at 12 months (Figure 1A). Amongst clinical risk prediction tools, CAAP-AF had the highest predictive value (AUC 0.6529, 95% CI 0.5265-0.7793) (Figure 1B). In patients undergoing repeat ablations, the combined model had an AUC of 0.7585 (95% CI 0.5989-0.9182) for predicting arrhythmia recurrence (Figure 2A). The Kaplan-Meier curves showed a higher risk of arrhythmia recurrence in the ‘high recurrence risk’ group at 12 months (log-rank p=0.029) (Figure 2B). Conclusion A logistic regression model integrating clinical, anatomical, functional, and electrophysiological parameters improved the accuracy of atrial fibrillation ablation outcome prediction compared to existing clinical risk scores. The model may be used to predict response to repeat procedures offering the potential to improve the patient selection process.

Immunotherapy Applications for Thymine Dimers and WT1 Antigen in Renal Cancers: A Comparative Statistical Analysis.

Renal cell carcinoma (RCC) remains incurable in advanced stages. Biomarkers have proven to be quite useful in cancer therapeutics. Herein, we provide a comparative/integrative statistical analysis of seminal immunohistochemistry (IHC) findings for Wilms' Tumor 1 antigen (WT1) and thymine dimers (TDs), emerging as atypical, yet promising, potential biomarkers for RCCs. We assessed WT1/TD reactivity in adult RCC tumor cells, tumor microenvironment (TME), and tumor-adjacent healthy renal tissue (HRT). WT1 positivity was scarce and strictly nuclear in tumor cells, whereas TD-reactive tumor tissues were prevalent. We report statistically significant positive correlations between the density of reactive RCC cellularity and the intensity of nuclear staining for both biomarkers (WT1 - rho = 0.341, p-value = 0.036; TDs - rho = 0.379, p-value = 0.002). RCC stromal TME TD-positivity was much more frequent than WT1 reactivity, apparently proportional to that of the proper RCC cellularity and facilitated by extensive RCC inflammatory infiltration. TDs exhibited nuclear reactivity for most TME cell lines, while RCC TME WT1 expression was rare and inconsistent. In HRTs, TDs were entirely restricted to renal tubular cells, the likely cellular progenitor of most conventional RCC subtypes. In lieu of proper validation, these early findings have significant implications regarding the origins/biology of RCCs and may inform RCC therapeutics, both accounting for the high frequency of immunotherapy-permissive frameshift indels in RCCs, but also hinting at novel predictive clinical tools for WT1-targeted immunotherapy. Overall, the current study represents a meek yet hopefully significant step towards understanding the molecular biology and potential therapeutic targets of RCCs.

Predicting bladder cancer survival with high accuracy: insights from MAPK pathway-related genes

The mitogen-activated protein kinase (MAPK) pathway plays a critical role in tumor development and immunotherapy. Nevertheless, additional research is necessary to comprehend the relationship between the MAPK pathway and the prognosis of bladder cancer (BLCA), as well as its influence on the tumor immune microenvironment. To create prognostic models, we screened ten genes associated with the MAPK pathway using COX and least absolute shrinkage and selection operator (LASSO) regression analysis. These models were validated in the Genomic Data Commons (GEO) cohort and further examined for immune infiltration, somatic mutation, and drug sensitivity characteristics. Finally, the findings were validated using The Human Protein Atlas (HPA) database and through Quantitative Real-time PCR (qRT-PCR). Patients were classified into high-risk and low-risk groups based on the prognosis-related genes of the MAPK pathway. The high-risk group had poorer overall survival than the low-risk group and showed increased immune infiltration compared to the low-risk group. Additionally, the nomograms built using the risk scores and clinical factors exhibited high accuracy in predicting the survival of BLCA patients. The prognostic profiling of MAPK pathway-associated genes represents a potent clinical prediction tool, serving as the foundation for precise clinical treatment of BLCA.

Retrospective validation of a rapid Lyme fluorescent immunoassay in differentiating Lyme arthritis from other musculoskeletal presentations in children in a Lyme-endemic region.

Lyme arthritis is a common manifestation of Lyme disease in children, with clinical features overlapping with other causes of acute and chronic joint pain/swelling in children. We have demonstrated that the Sofia IgG is a reliable test to rule in and rule out the diagnosis of Lyme arthritis in children with musculoskeletal presentations in a Lyme-endemic region. When used in conjunction with clinical and laboratory variables routinely considered when differentiating Lyme arthritis from other diagnoses, the Sofia IgG has the potential to fill an important gap in care, especially when acute decision-making is necessary. The Sofia IgG should be included in prospective research studies examining clinical prediction tools to identify children at low risk of septic arthritis.

Precision Medicine-Are We There Yet? A Narrative Review of Precision Medicine's Applicability in Primary Care.

Precision medicine (PM), also termed stratified, individualised, targeted, or personalised medicine, embraces a rapidly expanding area of research, knowledge, and practice. It brings together two emerging health technologies to deliver better individualised care: the many "-omics" arising from increased capacity to understand the human genome and "big data" and data analytics, including artificial intelligence (AI). PM has the potential to transform an individual's health, moving from population-based disease prevention to more personalised management. There is however a tension between the two, with a real risk that this will exacerbate health inequalities and divert funds and attention from basic healthcare requirements leading to worse health outcomes for many. All areas of medicine should consider how this will affect their practice, with PM now strongly encouraged and supported by government initiatives and research funding. In this review, we discuss examples of PM in current practice and its emerging applications in primary care, such as clinical prediction tools that incorporate genomic markers and pharmacogenomic testing. We look towards potential future applications and consider some key questions for PM, including evidence of its real-world impact, its affordability, the risk of exacerbating health inequalities, and the computational and storage challenges of applying PM technologies at scale.