Development of a machine learning-based predictive model for transitional cell carcinoma of the renal pelvis in White Americans: a SEER-based study DOI Open Access
Z G Liu, Hang Ma, Yingchun Guo

et al.

Translational Andrology and Urology, Journal Year: 2024, Volume and Issue: 13(12), P. 2681 - 2693

Published: Dec. 1, 2024

Transitional cell carcinoma (TCC) of the renal pelvis is a rare cancer within urinary system. However, prognosis not entirely satisfactory. This study aims to develop clinical model for predicting cancer-specific survival (CSS) at 1-, 3-, and 5-year White Americans with pelvic TCC. Data all American patients diagnosed TCC from 2010 2015 were extracted analyzed Surveillance, Epidemiology, End Results (SEER) database in this retrospective study. Subsequently, after excluding metastatic group, subgroup analysis was performed on data 1,715 non-metastatic Patients included randomly divided into training validation sets ratio 7:3. In addition, features set by Boruta algorithm. The importance these visualized using eXtreme Gradient Boosting (XGBoost)-based SHapley Additive exPlanation (SHAP) tool. To improve predictive accuracy, nomogram identified independent prognostic variables developed. A total 1,887 set, area under curve (AUC) CSS nomograms 0.813 [95% confidence interval (CI): 0.774-0.852], 0.738 (95% CI: 0.702-0.774), 0.733 0.698-0.768), respectively. Correspondingly, AUCs above time points 0.781 0.732-0.830), 0.785 0.741-0.829), 0.775 0.729-0.820) results revealed that 0.788, 0.725, 0.726 respectively, while 0.831, 0.786, 0.754 study, predicts efficiently constructed. application may enhance patient care assist clinicians choosing optimal treatment strategies.

Language: Английский

Artificial intelligence for optimizing benefits and minimizing risks of pharmacological therapies: challenges and opportunities DOI Creative Commons
Salvatore Crisafulli, Francesco Ciccimarra, Chiara Bellitto

et al.

Frontiers in Drug Safety and Regulation, Journal Year: 2024, Volume and Issue: 4

Published: March 18, 2024

In recent years, there has been an exponential increase in the generation and accessibility of electronic healthcare data, often referred to as “real-world data”. The landscape data sources significantly expanded encompass traditional databases newer such social media, wearables, mobile devices. Advances information technology, along with growth computational power evolution analytical methods relying on bioinformatic tools and/or artificial intelligence techniques, have enhanced potential for utilizing this generate real-world evidence improve clinical practice. Indeed, these innovative approaches enable screening analysis large amounts rapidly evidence. As numerous practical uses medicine successfully investigated image processing, disease diagnosis prediction, well management pharmacological treatments, thus highlighting need educate health professionals emerging approaches. This narrative review provides overview foremost opportunities challenges presented by pharmacology, specifically concerning drug post-marketing safety evaluation.

Language: Английский

Citations

4
Comparative Performance of 4 Penicillin-Allergy Prediction Strategies in a Large Cohort DOI
Ileana‐Maria Ghiordanescu, Iuliana Ciocănea‐Teodorescu, Nicolas Molinari

et al.

The Journal of Allergy and Clinical Immunology In Practice, Journal Year: 2024, Volume and Issue: 12(11), P. 2985 - 2993

Published: July 20, 2024

Language: Английский

Citations

4
Penicillin allergy management strategies relevant for clinical practice - a narrative review DOI Creative Commons
Ileana‐Maria Ghiordanescu,

Nicolas Molinari,

Ana-Maria Forsea

et al.

Romanian Journal of Internal Medicine, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Abstract Penicillin allergy is the most commonly reported drug allergy, with prevalence rates ranging from 6% to 31% across various populations and geographic areas. The penicillin label linked higher mortality morbidity rates, extended hospital stays, increased readmission a greater reliance on second-line antibiotics. Research indicates that nearly 99% of those labeled as penicillin-allergic can tolerate drug. However, alternative antibiotics are often prescribed without confirming largely due legal concerns regarding re-exposure. Even when negative challenge test conducted, non-allergist providers may remain hesitant reintroduce penicillin. To address considerable gap between actual allergies, well ensure prompt use penicillins by non-allergists, management strategies have emerged in recent years. Although several comprehensive reviews examined these strategies, selecting applying suitable for routine practice difficult. This narrative review focuses relevant data efficiency key risk assessment tools, particularly clinical significance, discusses their readiness implementation settings.

Language: Английский

Citations

0
Multifaceted implementation strategy to improve the evaluation of penicillin allergies in perioperative patients: a pre-post feasibility implementation study DOI Creative Commons
Eileen Carter,

Katherine Zavez,

Carol Schramm

et al.

Infection Control and Hospital Epidemiology, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 7

Published: Oct. 30, 2024

Abstract Objective: The U.S. Centers for Disease Control and Prevention encourages nurses to evaluate penicillin allergies as part of hospital-based antibiotic stewardship programs. We evaluated the feasibility an implementation strategy improve nurses’ comprehensive documentation allergies. defined uptake acceptability procedures. Design: Six-month pre-post study. Setting: Outpatient surgical areas academic medical center located in Intervention: was guided by Capability, Opportunity, Motivation Model Behavior Change included, building interdisciplinary coalition iteratively effort, educational meetings with prescribers perioperative nurses, development distribution pocket cards, structured communication messages electronic record. Results: A total 426 patients 487 allergy records (216 pre-implementation period, 271 post-implementation period) were analyzed. Penicillin contained following information pre- versus period: symptoms reaction (87% vs 87%), timing/years since (8% 26%), onset relation taking (0% 21%), how resolved re-exposure (3% 21%). Focus groups revealed perceived procedures highly acceptable. Major drivers included effectiveness a detailed history self-efficacy conducting history. Conclusions: Nurses intervention acceptable, improved theory-informed strategy. offer components facilitate engagement evaluation.

Language: Английский

Citations

0
Development of a machine learning-based predictive model for transitional cell carcinoma of the renal pelvis in White Americans: a SEER-based study DOI Open Access
Z G Liu, Hang Ma, Yingchun Guo

et al.

Translational Andrology and Urology, Journal Year: 2024, Volume and Issue: 13(12), P. 2681 - 2693

Published: Dec. 1, 2024

Transitional cell carcinoma (TCC) of the renal pelvis is a rare cancer within urinary system. However, prognosis not entirely satisfactory. This study aims to develop clinical model for predicting cancer-specific survival (CSS) at 1-, 3-, and 5-year White Americans with pelvic TCC. Data all American patients diagnosed TCC from 2010 2015 were extracted analyzed Surveillance, Epidemiology, End Results (SEER) database in this retrospective study. Subsequently, after excluding metastatic group, subgroup analysis was performed on data 1,715 non-metastatic Patients included randomly divided into training validation sets ratio 7:3. In addition, features set by Boruta algorithm. The importance these visualized using eXtreme Gradient Boosting (XGBoost)-based SHapley Additive exPlanation (SHAP) tool. To improve predictive accuracy, nomogram identified independent prognostic variables developed. A total 1,887 set, area under curve (AUC) CSS nomograms 0.813 [95% confidence interval (CI): 0.774-0.852], 0.738 (95% CI: 0.702-0.774), 0.733 0.698-0.768), respectively. Correspondingly, AUCs above time points 0.781 0.732-0.830), 0.785 0.741-0.829), 0.775 0.729-0.820) results revealed that 0.788, 0.725, 0.726 respectively, while 0.831, 0.786, 0.754 study, predicts efficiently constructed. application may enhance patient care assist clinicians choosing optimal treatment strategies.

Language: Английский

Citations

0