Standard Risk Research Articles

Prediction of prostate cancer recurrence after radiotherapy using a fused machine learning approach: utilizing radiomics from pretreatment T2W MRI images with clinical and pathological information

The risk of biochemical recurrence (BCR) after radiotherapy for localized prostate cancer (PCa) varies widely within standard risk groups. There is a need for low-cost tools to more robustly predict recurrence and personalize therapy. Radiomic features from pretreatment MRI show potential as noninvasive biomarkers for BCR prediction. However, previous research has not fully combined radiomics with clinical and pathological data to predict BCR in PCa patients following radiotherapy.
Purpose: This study aims to predict 5-year BCR using radiomics from pretreatment T2W MRI and clinical-pathological data in PCa patients treated with radiation therapy, and to develop a unified model compatible with both 1.5T and 3T MRI scanners.
Methods: A total of 150 T2W scans and clinical parameters were preprocessed. Of these, 120 cases were used for training and validation, and 30 for testing. Four distinct machine learning models were developed: Model 1 used radiomics, Model 2 used clinical and pathological data, and Model 3 combined these using late fusion. Model 4 integrated radiomic and clinical-pathological data using early fusion.
Results: Model 1 achieved an AUC of 0.73, while Model 2 had an AUC of 0.64 for predicting outcomes in 30 new test cases. Model 3, using late fusion, had an AUC of 0.69. Early fusion models showed strong potential, with Model 4 reaching an AUC of 0.84, highlighting the effectiveness of the early fusion model.
Conclusions: This study is the first to use a fusion technique for predicting BCR in PCa patients following radiotherapy, utilizing pre-treatment T2W MRI images and clinical-pathological data. The methodology improves predictive accuracy by fusing radiomics with clinical-pathological information, even with a relatively small dataset, and introduces the first unified model for both 1.5T and 3T MRI images.

Machine learning approaches in non-contact autofluorescence spectrum classification.

Manual surgical resection of soft tissue sarcoma tissue can involve many challenges, including the critical need for precise determination of tumor boundary with normal tissue and limitations of current surgical instrumentation, in addition to standard risks of infection or tissue healing difficulty. Substantial research has been conducted in the biomedical sensing landscape for development of non-human contact sensing devices. One such point-of-care platform, previously devised by our group, utilizes autofluorescence-based spectroscopic signatures to highlight important physiological differences in tumorous and healthy tissue. The following study builds on this work, implementing classification algorithms, including Artificial Neural Network, Support Vector Machine, Logistic Regression, and K-Nearest Neighbors, to diagnose freshly resected murine tissue as sarcoma or healthy. Classification accuracies of over 93% are achieved with Logistic Regression, and Area Under the Curve scores over 94% are achieved with Support Vector Machines, delineating a clear way to automate photonic diagnosis of ambiguous tissue in assistance of surgeons. These interpretable algorithms can also be linked to important physiological diagnostic indicators, unlike the black-box ANN architecture. This is the first known study to use machine learning to interpret data from a non-contact autofluorescence sensing device on sarcoma tissue, and has direct applications in rapid intraoperative sensing.

Improved uptake and adherence to risk reducing medication with use of low dose Tamoxifen in patients at high risk for breast cancer.

Women at increased risk for breast cancer (BC) may benefit from taking risk reducing medication (RRM) with tamoxifen (tam). Historical uptake to tam for women who qualify has been low. Recent studies have shown low dose tam to have similar efficacy to standard dosing lower risk for adverse events. Herein, we aimed to evaluate uptake, adherence, and tolerability of low dose tam in women at increased risk for BC and those with DCIS. In this two-site prospective study, women who qualified for BC RRM were offered participation and received consultation with a breast specialist for discussion of RRM rationale, benefits, side effects, and risks. Patients received baseline and 1 year follow-up surveys. 41 patients consented for participation and 31 completed 1-year follow-up. After initial consultation, 90% (n=37) reported good/complete understanding of BC risk. Of patients included in 1 year follow-up, 5 had DCIS, 13 had high-risk intraepithelial lesion, and 13 qualified based on BCRAT/IBIS calculation. 74% (n= 23) of patients reported they took low dose tam after consultation with 78.2% (n=18) of those still taking medication at 1 year. Patients who continued medication had higher estimated BC risk compared to those who discontinued (IBIS 10-yr risk 12.7% vs 7.6%, p = 0.027). All patients with DCIS initiated low dose tam and only 1 patient with DCIS had discontinued at 1 year. Uptake to low dose tam after informed discussion is high. Adherence and tolerability at 1 year follow-up is improved compared with traditional dosing of tam.

Added prognostic value of fat attenuation index and CT-derived fractional flow reserve over plaque burden in suspected CAD patients without standard modifiable risk factors

Background: In this study, we aimed to investigate the added prognostic value of fat attenuation index (FAI) and CT-derivedfractional flow (CT-FFR) over plaque burden in suspected coronary artery disease (CAD) patients without standard modifiablerisk factors (SMuRFs). Methodology: A total of 260 consecutive suspected CAD subjects without SMuRFs who underwent first coronary computed tomography angiography (CCTA) were retrospectively collected. We calculated FAI, CT-FFR, and segment involvement score (SIS) from CCTA images. Cox regression models were used to assess the incremental prognostic value of FAI and CT-FFR. Results: During a median follow-up of 25.00 months, major adverse cardiovascular events (MACE) were observed in 40 (15.4%) patients. FAI ≥ −70.1, CT-FFR ≤ 0.80, and SIS ≥ 4.5 were associated with the increased rate of MACE (P < 0.0001). FAI did not provide incremental prognostic value over SIS (P = 0.169). Likewise, CT-FFR did not enhance risk prediction (P = 0.159). Combining FAI and CT-FFR added incremental prediction value and improved risk discrimination (P = 0.032; Absolute integrate discrimination improvement (IDI) = 0.070, P < 0.001). Conclusion: In suspected CAD patients without SMuRFs, neither FAI nor CT-FFR independently added incremental prognostic value over plaque burden. Combining FAI and CT-FFR had added prognostic value and improved cardiovascular risk stratification. Keywords: Coronary artery disease; CT-derived fractional flow reserve; fat attenuation index; plaque burden; standard cardiovascularrisk factor; prognosis.

Older Adult Fall Risk Prediction with Deep Learning and Timed Up and Go (TUG) Test Data.

Falls are a major health hazard for older adults; therefore, in the context of an aging population, predicting the risk of a patient suffering falls in the near future is of great impact for health care systems. Currently, the standard prospective fall risk assessment instrument relies on a set of clinical and functional mobility assessment tools, one of them being the Timed Up and Go (TUG) test. Recently, wearable inertial measurement units (IMUs) have been proposed to capture motion data that would allow for the building of estimates of fall risk. The hypothesis of this study is that the data gathered from IMU readings while the patient is performing the TUG test can be used to build a predictive model that would provide an estimate of the probability of suffering a fall in the near future, i.e., assessing prospective fall risk. This study applies deep learning convolutional neural networks (CNN) and recurrent neural networks (RNN) to build such predictive models based on features extracted from IMU data acquired during TUG test realizations. Data were obtained from a cohort of 106 older adults wearing wireless IMU sensors with sampling frequencies of 100 Hz while performing the TUG test. The dependent variable is a binary variable that is true if the patient suffered a fall in the six-month follow-up period. This variable was used as the output variable for the supervised training and validations of the deep learning architectures and competing machine learning approaches. A hold-out validation process using 75 subjects for training and 31 subjects for testing was repeated one hundred times to obtain robust estimations of model performances At each repetition, 5-fold cross-validation was carried out to select the best model over the training subset. Best results were achieved by a bidirectional long short-term memory (BLSTM), obtaining an accuracy of 0.83 and AUC of 0.73 with good sensitivity and specificity values.

EVALUATING PERINATAL OUTCOMES IN HIGH-RISK PREGNANCIES USING THE MODIFIED COOPLAND’S SCORING SYSTEM AT A TERTIARY HOSPITAL

This study aims to thoroughly assess perinatal mortality rates, Apgar scores, birth weights, and neonatal complications within the first-week post-birth among high-risk pregnancies. Methods: During a prospective cohort study at Jinnah Postgraduate Medical Centre, Karachi, from October 2023 to May 2024, we evaluated outcomes in 664 high-risk pregnant women using systematic random sampling. Participants, with singleton pregnancies of 24 weeks or more gestation, were stratified by risk level. Data included demographic details, socioeconomic status, BMI, and pregnancy history. Maternal outcomes, such as mode of delivery and postpartum haemorrhage requiring transfusion, and perinatal outcomes, including birth weight and APGAR scores, were assessed. Statistical analysis emphasized odds ratios, with p < 0.05 considered significant. Ethical approval was obtained, and all participants provided informed consent. Results: This prospective cohort study at Jinnah Postgraduate Medical Centre from October 2023 to May 2024 involved 664 high-risk pregnant women categorized by standard risk scoring. Participants were predominantly low-risk (65.77%), followed by moderate-risk (19.88%) and high-risk (14.35%). Key findings included increased rates of cesarean sections, postpartum haemorrhage, premature births, low birth weight, adverse APGAR scores, NICU admissions, and perinatal mortality with escalating risk levels. Statistical analyses revealed significant associations and elevated odds ratios for adverse outcomes among higher-risk groups, underscoring the importance of risk assessment in managing maternal and perinatal health outcomes. Conclusion: Our study highlights the urgent importance of identifying and effectively managing high-risk pregnancies. We discovered that these pregnancies are associated with significantly elevated risks of complications such as Cesarean deliveries, postpartum haemorrhage, preterm births, low birth weights, low 5-minute APGAR scores, NICU admissions, and perinatal mortality. Implementing a straightforward, non-invasive risk-scoring system can facilitate early detection of high-risk cases, enabling timely and tailored interventions that can greatly improve outcomes for both mothers and infants.

T(11;14) with multiple myeloma: Standard risk survival but slow and poor response.

We described 790 patients with newly diagnosed multiple myeloma, including 224 (28.4%) standard risk (SR) patients without t(11;14), 99 (12.5%) patients with t(11;14)alone, 58 (7.3%) with t(11;14) + HR, and 409 (51.8%) in the high-risk cytogenetic abnormality (HRCA) group including t(4;14), t(14;16), t(14;20), C1A1 and/or del(17p) but without t(11;14), to evaluate the impact of t(11;14) in NDMM patients on response rate, response kinetics and survival. Our study showed that NDMM patients in the t(11;14)alone group had similar PFS (49.3 vs. 50.7months; P = 0.392) and OS (112.4 vs. NR months; P = 0.982) as those in the SR group. However, the t(11;14)alone group exhibited a significantly poorer depth of response compared to the SR group, particularly with a lower MRD negativity rate (60.0% vs. 76.0%, P = 0.009). In the t(11;14)alone group, MRD status did not significantly impact PFS or OS, which was in contrast to the other groups. Response kinetics analyses showed that the t(11;14)alone group had a slower response rate than the other subgroups (t(11;14)alone vs. SR vs. HRCA: median time to MRD negativity = 9.19 vs. 4.25 vs. 4.27 months; P < 0.001). Our study showed that t(11;14)alone was characterized by survival comparable to standard risk cytogenetics despite exhibiting the slowest timing of response onset and lowest plateau of remission, which suggested a relatively indolent clinical course.

Access and adherence to cancer care through the Veteran Affairs Close to Me cancer care service.

111 Background: Diagnosing and treating more than 56,000 Veterans annually, the Veterans Affairs (VA) National Oncology Program (NOP) is one of the nation’s largest integrated providers of oncology services. Within VA, oncology care and parenteral therapies are primarily offered at VA Medical Centers (VAMCs) in urban areas, often inaccessible to rural patients. Issues with travel distance, parking, time, and caregiver support can prevent patients from adhering to treatment appointments as evidenced by historical annual No-Show rates for VAMC infusion clinics that range from 1.1-6.7%. To mitigate potential barriers to access, NOP launched the Close to Me (CTM) cancer care service. The service deploys Registered Nurses (RNs) to local VA Community Based Outpatient Clinics (CBOCs) to administer cancer treatments. VA has opened 23 CTM clinics across 5 geographical regions since October 2021. Methods: The CTM service was implemented at VAMCs with NOP providing direct project management, safety assessment and resources such as a comprehensive implementation toolkit, standard operating procedures, care coordination tools, a tiered risk drug matrix and a standardized Healthcare Failure Mode and Effect Analysis risk evaluation. RNs followed a standardized workflow to assess patient eligibility and verify treatment clearances. Access to care was reported by numbers of unique patients and treatment visits. Patient appointment adherence was monitored by no-show rates documented in the electronic health record. Infusion reactions and medical emergencies were reported by RNs. Travel miles saved was calculated by subtracting the difference in miles round trip from the patient’s home to main VAMC and from home to CBOC, then multiplied by number of treatment visits to CBOC. Results: From October 2021 through April 2024, 23 new CTM clinics opened across 5 regions. 515 unique patients were enrolled for a total of 1,916 patient visits. Treatment appointment no-show rate was 1% across all CTM clinics. The most commonly administered medication classes include gonadotropin-releasing hormone agonist (30%), immune globulin (14.5%), immune checkpoint inhibitors (9.3%) and bisphosphonates (8.3%). Zero infusion reactions or medical emergencies were recorded across 1,430 treatments administered. A total of 204,000 travel miles were saved by patients enrolled in this program. Conclusions: The CTM cancer care service safely optimizes current VA CBOC infrastructure to increase access points to oncology treatment for patients across various geographical regions. CTM reduced travel burden for patients and increased ability to adhere to treatment appointments as evidenced by the service’s low no-show rate. These consistent results across CTM services at VAMCs nationwide have cemented CTM as a safe and effective treatment delivery model to expand access. CTM will be scaled to an additional 30 regions by end of 2025.

TCT-14 Prevalence and Impact of Standard Modifiable Risk Factors Among Patients Undergoing Percutaneous Coronary Intervention

TCT-14 Prevalence and Impact of Standard Modifiable Risk Factors Among Patients Undergoing Percutaneous Coronary Intervention

Sex differences in transradial access failure in ST segment elevation myocardial infarction.

Transradial access (TRA) is now the default access site for PPCI, but technically is a more challenging approach mostly due to anatomic challenges connected to the RA. To assess the differences according to sex in radial artery (RA) access site characteristics during primary percutaneous coronary intervention (PPCI) for ST segment elevation myocardial infarction (STEMI). All 5092 consecutive STEMI patients from our center in the period from March 2011 until December 2017 were examined. The right proximal radial was the "intention-to-treat" access in all patients. Preprocedural RA angiography was performed in all patients. Clinical and procedure characteristics, type of radial anatomy variants, need to use another arterial access sites (the primary endpoint for this study), and procedure time were analyzed by sex. Using logistic regression, we selected predictors of radial crossover. Access site bleeding complications and vascular complications were also recorded. The STEMI population in this period included 1326 females and 3766 male patients. Females were older (65 ± 11 years) than males (59 ± 11 years, p < 0.0001). Among standard risk factors, hypertension and diabetes mellitus were more common in women and smoking less common. RA anomalies were more frequent in the females (8.8% vs. 6.5%, p < 0.0001), with complex RA loop and tortuous RA twice as frequent in women. Failure of TRA access as the initially chosen site occurred in 4.6% (61) of females versus 2.5% (97) of male STEMI patients (p = 0.0003). The most common subsequent access site was right ulnar access in both groups (57 and 61% respectively). Access site bleeding complications were more common in women 4.4% versus 3.2%, mirrored in hematomas with EASY score III to V. Clinical RA spasm (RAS) was significantly more frequent in females (5.7% vs. 2.2%, p < 0.0001). Multiple regression analysis identified 5 independent predictors for TRA access crossover: previous TRA, anomalous RA, RAS, along with female sex and diabetes. Female sex is a significant predictor of more complex TRA in STEMI. Understanding sex differences and predictors for TRA crossover will strengthen the use of different procedural modalities that can help in preserving a successful wrist access in female STEMI patients.

NON-STANDARD RISK MODEL FOR APPLICATIONS IN RAILWAY TRANSPORT

In risk management in railway transport, standard risk models are usually used based on its typical definition and discrete quantification. This approach allows for easy justification of the adopted model, most often by referring to appropriate norms or standards (such as IRIS). The scientific approach does not disqualify the practical use of standard risk models, but its disadvantages (especially typical risk matrices, including their subjectivity) are increasingly being pointed out. In risk management procedures, most frequently one model is used to assess the risk of all identified hazards. This may turn out to be a mistake, considering the specific characteristics of the hazards. A risk model applied to one hazard may not be adequate to assess the risk of another. Therefore, it should be individually adapted both in terms of variables and the ranges of their measurement values. For some hazards, it will even be necessary to develop or adopt non-standard models. The aim of the article is to present non-standard risk models that provide a base for their easy implementation in safety management procedures used by railway entities.

Survival of Children with Acute Lymphoblastic Leukemia with Risk Group-Based Protocol Changes: A Single Center Experience with 460 Patients over a 20-Year Period.

Recent treatments for pediatric acute lymphoblastic leukemia (ALL) are founded on risk stratification. We examined the survival rates and prognostic factors of patients over a 20-year period at a single institution. This study analyzed patients diagnosed with ALL and treated at the Pediatric Department of Samsung Medical Center (SMC). Patients were categorized into standard-risk (SR), high-risk (HR), and very high-risk (VHR) groups. The SMC protocol for the HR group underwent two changes during the study period: A modified Children's Cancer Group (CCG)-1882 protocol was used from 2000 to 2005, the Korean multicenter HR ALL-0601 protocol from 2006 to 2014, and the Korean multicenter HR ALL-1501 protocol from 2015 to 2019. Of the 460 patients, complete remission was achieved in 436 patients (94.8%). The 10-year overall survival rate (OS) was 83.8±1.9% for all patients. OS according to the SMC risk group was as follows: 95.9±1.4% in the SR group, 83.8±3.6% in the HR group, and 66.2±6.9% in the VHR group. The 5-year OS within the HR group varied according to the treatment protocol: 73.9±7.5%, in the modified CCG-1882 protocol, 83.0±3.9%, in the 0601 protocol, and 96.2±2.6%, in the 1501 protocol. For those aged 15 years and older, the OS was only 56.5±13.1%. Relapse occurred in 71 patients (15.4%), and the OS after relapse was 37.7±6.0%. The treatment outcomes of patients with ALL improved markedly. However, there is a need to further characterize adolescents and young adult patients, as well as those who have experienced relapses.

Relationship between phthalate exposure and kidney function in Taiwanese adults as determined through covariate-adjusted standardization and cumulative risk assessment

Few studies have investigated the associations between phthalate exposure and kidney function indicators in adults by simultaneously performing covariate-adjusted creatinine standardization, cumulative risk assessment, and mixture analysis. Thus, we applied these methods simultaneously to investigate the aforementioned associations in an adult population. This cross-sectional study analyzed data (N = 839) from a community-based arm of the Taiwan Biobank. The levels of 10 urinary phthalate metabolites were measured and calculated as the sum of the molar concentrations of the dibutyl phthalate metabolite (ΣDBPm) and di(2-ethylhexyl) phthalate (DEHP) metabolite (ΣDEHPm). The hazard index (HI) and daily intake (DI) were estimated by measuring the urinary levels of the phthalate metabolite. Kidney function biomarkers were assessed by measuring the following: blood urea nitrogen (BUN), uric acid, the albumin-to-creatinine ratio (ACR), and the estimated glomerular filtration rate (eGFR). Generalized linear models were implemented to examine the associations between exposure to individual phthalates, HI scores, and kidney function biomarkers. We also employed Bayesian kernel machine regression (BKMR) to analyze the relationships between exposure to various combinations of phthalates and kidney function. ΣDEHPm levels were significantly and positively associated with BUN and ACR levels, and ΣDBPm levels were positively associated with ACR levels. In addition, eGFR was negatively associated with ΣDBPm and ΣDEHPm levels. In the BKMR model, a mixture of 10 phthalate metabolites was significantly associated with BUN, uric acid, ACR, and eGFR results. Higher DIDEHP and higher DIDnBP values were significantly associated with lower eGFRs and higher ACRs, respectively. Higher DIDiBP and DIDEP values were significantly associated with higher uric acid levels. A higher HI was significantly associated with lower eGFRs and higher ACRs. Our results suggest that exposure to environmental phthalates is associated with impaired kidney function in Taiwanese adults.

Modulating the unfolded protein response with ISRIB mitigates cisplatin ototoxicity

Cisplatin is a commonly used chemotherapy agent with a nearly universal side effect of sensorineural hearing loss. The cellular mechanisms underlying cisplatin ototoxicity are poorly understood. Efforts in drug development to prevent or reverse cisplatin ototoxicity have largely focused on pathways of oxidative stress and apoptosis. An effective treatment for cisplatin ototoxicity, sodium thiosulfate (STS), while beneficial when used in standard risk hepatoblastoma, is associated with reduced survival in disseminated pediatric malignancy, highlighting the need for more specific drugs without potential tumor protective effects. The unfolded protein response (UPR) and endoplasmic reticulum (ER) stress pathways have been shown to be involved in the pathogenesis of noise-induced hearing loss and cochlear synaptopathy in vivo, and these pathways have been implicated broadly in cisplatin cytotoxicity. This study sought to determine whether the UPR can be targeted to prevent cisplatin ototoxicity. Neonatal cochlear cultures and HEK cells were exposed to cisplatin, and UPR marker gene expression and cell death measured. Treatment with ISRIB (Integrated Stress Response InhIBitor), a drug that activates eif2B and downregulates the pro-apoptotic PERK/CHOP pathway of the UPR, was tested for its ability to reduce apoptosis in HEK cells, hair-cell death in cochlear cultures, and hearing loss using an in vivo mouse model of cisplatin ototoxicity. Finally, to evaluate whether ISRIB might interfere with cisplatin chemoeffectiveness, we tested it in head and neck squamous cell carcinoma (HNSCC) cell-based assays of cisplatin cytotoxicity. Cisplatin exhibited a biphasic, non-linear dose–response of cell death and apoptosis that correlated with different patterns of UPR marker gene expression in HEK cells and cochlear cultures. ISRIB treatment protected against cisplatin-induced hearing loss and hair-cell death, but did not impact cisplatin’s cytotoxic effects on HNSCC cell viability, unlike STS. These findings demonstrate that targeting the pro-apoptotic PERK/CHOP pathway with ISRIB can mitigate cisplatin ototoxicity without reducing anti-cancer cell effects, suggesting that this may be a viable strategy for drug development.

Evaluating the Factors Affecting the Involvement of Shariah Committees in Risk Management Practices in Islamic Banks: Qualitative Research in the Kingdom of Saudi Arabia

Purpose: This study aims to add to the existing literature on Islamic finance by explaining the ways in which Shariah committees can improve and strengthen their influence over Islamic banks’ risk management practises. This research attempts to break down the complexities of Saudi Arabia’s risk management and identify the crucial role that Shariah committees play in ensuring compliance with Shariah law. Design of study: A qualitative research method was adopted conducting semi-structured interviews. Purposive sampling was used to choose 34 individuals. The data were analyzed using thematic analysis, with the use of NVivo software, which made it easier to identify patterns in the Arabic answers. Following the ethical norms established by RMIT University, obtaining participants’ explicit consent, and guaranteeing anonymity are all of the top priority. Findings: Several factors determine Saudi Islamic Bank Shariah Committee risk management. An effective regulatory framework, Shariah committee-bank leadership communication, and learning of Islamic financial ideas can aid in Shariah compliance. However, interpreting complex financial services within Shariah, inconsistencies between Islamic principles and standard risk management methodologies, and a shortage of competent Shariah scholars with banking and risk management knowledge may slow development. Research is needed to understand Saudi procedures. Originality: The current research comprehensively documented potential factors that facilitate or resist the involvement of Shariah Committees in practices of risk management in Saudi Arabia’s Islamic banks.

Harnessing AI for Early Detection of Cardiovascular Diseases: Insights from Predictive Models Using Patient Data

Cardiovascular diseases (CVDs) continue to be the leading cause of death in the world, taking millions of lives every year. Early detection and treatment of these diseases are critical in preventing deaths and illnesses. Currently, traditional diagnostic methods like routine clinical examinations and other standard risk assessment tools fail to detect CVDs in early on set stages, posing numerous limitations for preventable interventions. This work explores incorporating artificial intelligence (AI) to catalyze early CVD diagnosis using AI models for patient data including electrocardiogram (ECG), wearable-generated metrics, and medical history. The research showcased the ability of AI to predict with high accuracy when CVD would start using machine learning methods such as Random Forest, Support Vector Machines (SVM) and Neural Networks. The powerful AI models were carefully constructed by training and testing them on an extensive dataset that contained measurements of diverse patient characteristics including many other readouts related to cardiovascular risk. Compared to traditional methods, the models outperformed, and Neural Networks had an accuracy of 92% in identifying high-risk patients. A hallmark of this work is that AI identifies subtle patterns and relationships within patient data ones that conventional approaches might not find. These AI-based predictive models might soon become part of the routine clinical evaluation for cardiovascular disease, providing a personalized and early health intervention to empower your cardiovascular care. Timely identification of these high-risk patients could allow for targeted interventions, leading to improved health and reductions in healthcare spending. Despite the promising potential that AI holds in healthcare, it also has brought up issues of data privacy, ethical use and the need for extensive clinical validation. This paper suggests a predictive strategy could be implemented using AI algorithms to lead early detection and management of CVD, which opens an opportunity for individualized care accompanied by big data era. Future studies should focus on improving such models with more diverse and larger datasets as well as overcoming logistical difficulties encountered in integrating AI into clinical workflows.

The pulmonary nodule: from incidental finding to pathological confirmation

As the number of CT examinations of the lungs increases, so does the prevalence of incidentally discovered pulmonary nodules. While most lung nodules are benign, the risk of malignancy significantly rises with the presence of risk factors and specific imaging features. Upon encountering an incidental nodule, efforts should focus on achieving an accurate pathological diagnosis, particularly to ascertain malignancy while minimizing the risks associated with unnecessary diagnostic procedures. A comprehensive understanding of the typical characteristics and behavior of malignant lung nodules, along with a detailed patient history and standardized clinical and imaging risk assessment, is crucial for determining the optimal diagnostic approach. Additionally, the decision regarding histologic confirmation should consider the patient's comorbidities, preferences, and the examiner's expertise. Emerging sampling technologies provide methods for addressing peripheral lung nodules with minimal risk of complications.

Lactate/Pyruvate Ratio as an Early Predictor of Mortality in Patients with Sepsis: A Cohort Study.

Background: The lactate/pyruvate (LP) ratio has been studied as an alternative to serum lactate to determine clinical prognosis. Despite its clinical utility, there is a paucity of evidence evaluating the role of the L/P ratio in patients with sepsis. Methods: We assessed the clinical utility of the L/P ratio in patients with sepsis. The L/P ratio was measured at baseline, 4 and 8 h after admission. Our primary outcome was to determine the prognostic utility of the L/P ratio on the 15-day mortality risk. Our secondary outcomes were to compare the L/P ratio across time and its prognostic utility against standard risk calculators such as APACHE-II and SOFA scores. Results: We had a total of 80 patients, with 18 (22.5%) survivors and 62 (77.5%) non-survivors. While we found that patients having higher L/P ratios at 8 h had an increased 30-mortality risk (OR 1.08, 95% CI 1.02-1.18), the model's performance showed no difference when compared to other measurements of the L/P ratio that showed no association with mortality (p-value: 0.45). For our secondary outcome, we found that the APACHE-II and SOFA scores have better performance and predictability than the L/P ratio (AUC 0.83 and AUC 0.80, respectively), but showed no association with mortality (OR 1.07, 95% CI 1.01-1.17 and OR 1.08, 95% CI 1.02-1.18). Conclusions: Based on our findings, the L/P ratio appears to function more effectively as an early predictor of mortality when used as an adjuvant biomarker with other clinical parameters.

In-Hospital Mortality and Treatment in Patients With Acute Coronary Syndrome With and Without Standard Modifiable Cardiovascular Risk Factors: Findings From the CCC-ACS Project.

Patients with acute coronary syndrome without standard modifiable cardiovascular risk factors (SMuRFs; hypertension, smoking, dyslipidemia, diabetes) have not been well studied, with little known about their characteristics, quality of care, or outcomes. We sought to systematically analyze patients with ACS without SMuRFs, especially to evaluate the effectiveness of guideline-directed medical therapy for these patients. In the CCC-ACS (Improving Care for Cardiovascular Disease in China-Acute Coronary Syndrome) project (2014-2019), we examined the presence and absence of SMuRFs and features among 89 462 patients with initial acute coronary syndrome. The main outcome was in-hospital all-cause mortality. Among eligible patients, 11.0% had none of the SMuRFs (SMuRF-less). SMuRF-less patients had higher in-hospital mortality (unadjusted hazard ratio [HR], 1.49 [95% CI, 1.19-1.87]). After adjustment for clinical characteristics and treatments, the associations between SMuRF status and in-hospital mortality persisted (adjusted HR, 1.35 [95% CI, 1.07-1.70]). Guideline-directed optimal medical therapy (receiving angiotensin-converting enzyme inhibitors/angiotensin receptor blockers, β-blockers, and statins) was not associated with lower mortality (adjusted HR, 0.98 [95% CI, 0.58-1.67]) in SMuRF-less patients, unlike the association in patients with SMuRFs (adjusted HR, 0.80 [95% CI, 0.66-0.98]). Sensitivity analyses were consistent with these results. SMuRF-less patients were associated with an increased risk of in-hospital mortality. Guideline-directed medical therapy was less effective in SMuRF-less patients than in patients with SMuRFs. Dedicated studies are needed to confirm the optimal therapy for SMuRF-less patients. URL: https://www.clinicaltrials.gov; Unique identifier: NCT02306616.

Clinical and Molecular Risk Factors in Extracranial Malignant Rhabdoid Tumors: Toward an Integrated Model of High-Risk Tumors.

Extracranial malignant rhabdoid tumors (eMRT) are a challenging entity. Despite the use of multimodal treatment approaches, therapy failure occurs in 55% to 67% of these. Molecular markers for identification of patients at increased risk for relapse or refractory (R/R) disease are not available. Clinical characteristics may only insufficiently predict the individual course of disease. Using the EU-RHAB database, we analyzed a cohort of 121 patients with eMRT clinically. For 81 patients, molecular and clinical data were available, which were further complemented with publicly available DNA molecular data from 92 eMRTs. We aimed to delineate molecular risk factors by dissecting the DNA methylome of these tumors. Moreover, we establish clinical characteristics and treatment details of R/R disease in a subcohort of 80 patients. Using consensus hierarchical clustering, we identified three distinct subgroups, one of which (eMRT standard risk) was associated with significantly improved survival, irrespective of germline status and/or localization. At the transcriptome level, this subgroup was characterized by an overexpression of genes involved in muscle development. A relevant proportion of patients developed distant relapses or progressions; the median time to the event was 4 months, underlining the need for early identification and risk stratification of R/R disease. The overall survival was significantly decreased in patients with progressive disease when compared with relapse cases, and reaching complete remission during salvage therapy provided a survival benefit. Our analysis of eMRT in this comprehensive cohort provides novel insights into the patterns of relapse and integrates molecular and clinical risk factors to guide clinical decision-making.