Optimal Clinical Decisions Research Articles

Preoperative atrial fibrillation in association with reduced haemoglobin predicts increased 30-d mortality after cardiac surgery

Objectives Atrial fibrillation is the most common arrhythmia occurring after cardiac surgery. Less attention has been focused on preoperative atrial fibrillation and anaemia as risk factors for mortality after cardiac surgery. The aim of this study was to determine preoperative risk factors for 30-d mortality after open-heart surgery. Design. The study population consisted of 2015 patients (73.4% men; mean age 68 years) undergoing coronary artery bypass grafting (CABG) (52.0%), aortic valve replacement (AVR) (18.6%), AVR and CABG (10.0%), mitral valve plasty or replacement (14.0%), and AVR and aortic root reconstruction (ARR) (5.5%) in Kuopio University Hospital from January 2013 to December 2016. Univariate and multivariate Cox proportional hazards models were used for statistical analyses. Kaplan–Meier survival curves were generated. Results. Total 30-d mortality was 1.8%. By Cox regression analysis, predictors of 30-d mortality (hazard ratio [HR] [95% confidence interval [CI]]) included female gender (1.95 [1.00–3.77]), preoperative atrial fibrillation, (2.38 [1.12–5.03]) reduced haemoglobin level (3.40 [1.47–7.90]), and pulmonary congestion (3.16 [1.52–6.55]). The combination of preoperative reduced haemoglobin and preoperative atrial fibrillation was a strong predictor (12.37 [4.40–34.77], p < .001). Estimated glomerular filtration rate (eGFR) predicted 30-d mortality in univariate models but was not an independent predictor in multivariate models. Conclusions. According to the main findings of our study, the combination of preoperative atrial fibrillation and reduced haemoglobin level substantially increase the risk of 30-d mortality after cardiac surgery. Identification of high-risk patients pre-operatively could help to make optimal clinical decisions for timing of operation and perioperative treatment.

Integrating transcriptomics and bulk time course data into a mathematical framework to describe and predict therapeutic resistance in cancer

A significant challenge in the field of biomedicine is the development of methods to integrate the multitude of dispersed data sets into comprehensive frameworks to be used to generate optimal clinical decisions. Recent technological advances in single cell analysis allow for high-dimensional molecular characterization of cells and populations, but to date, few mathematical models have attempted to integrate measurements from the single cell scale with other types of longitudinal data. Here, we present a framework that actionizes static outputs from a machine learning model and leverages these as measurements of state variables in a dynamic model of treatment response. We apply this framework to breast cancer cells to integrate single cell transcriptomic data with longitudinal bulk cell population (bulk time course) data. We demonstrate that the explicit inclusion of the phenotypic composition estimate, derived from single cell RNA-sequencing data (scRNA-seq), improves accuracy in the prediction of new treatments with a concordance correlation coefficient (CCC) of 0.92 compared to a prediction accuracy of CCC = 0.64 when fitting on longitudinal bulk cell population data alone. To our knowledge, this is the first work that explicitly integrates single cell clonally-resolved transcriptome datasets with bulk time-course data to jointly calibrate a mathematical model of drug resistance dynamics. We anticipate this approach to be a first step that demonstrates the feasibility of incorporating multiple data types into mathematical models to develop optimized treatment regimens from data.

Targeting the Deterministic Evolutionary Trajectories of Clear Cell Renal Cell Carcinoma

Simple SummaryIn contrast to organismal evolution, human cancers are subjected to similar initial conditions and follow a limited range of possible evolutionary trajectories. Therefore, the repetitive nature of cancer evolution may prove to be its greatest weakness. Evolutionary trajectories of clear cell renal cell carcinoma (ccRCC) have been recently described. In this review, we will discuss the relevance of estimating the trajectory of ccRCC evolution as a readout for a response to therapy. Next, we will propose strategies to take advantage of the evolving nature of these tumors for patients’ benefit.The emergence of clinical resistance to currently available systemic therapies forces us to rethink our approach to clear cell renal cell carcinoma (ccRCC). The ability to influence ccRCC evolution by inhibiting processes that propel it or manipulating its course may be an adequate strategy. There are seven deterministic evolutionary trajectories of ccRCC, which correlate with clinical phenotypes. We suspect that each trajectory has its own unique weaknesses that could be exploited. In this review, we have summarized recent advances in the treatment of ccRCC and demonstrated how to improve systemic therapies from the evolutionary perspective. Since there are only a few evolutionary trajectories in ccRCC, it appears feasible to use them as potential biomarkers for guiding intervention and surveillance. We believe that the presented patient stratification could help predict future steps of malignant progression, thereby informing optimal and personalized clinical decisions.

Using machine learning methods to predict in-hospital mortality of sepsis patients in the ICU

BackgroundEarly and accurate identification of sepsis patients with high risk of in-hospital death can help physicians in intensive care units (ICUs) make optimal clinical decisions. This study aimed to develop machine learning-based tools to predict the risk of hospital death of patients with sepsis in ICUs.MethodsThe source database used for model development and validation is the medical information mart for intensive care (MIMIC) III. We identified adult sepsis patients using the new sepsis definition Sepsis-3. A total of 86 predictor variables consisting of demographics, laboratory tests and comorbidities were used. We employed the least absolute shrinkage and selection operator (LASSO), random forest (RF), gradient boosting machine (GBM) and the traditional logistic regression (LR) method to develop prediction models. In addition, the prediction performance of the four developed models was evaluated and compared with that of an existent scoring tool – simplified acute physiology score (SAPS) II – using five different performance measures: the area under the receiver operating characteristic curve (AUROC), Brier score, sensitivity, specificity and calibration plot.ResultsThe records of 16,688 sepsis patients in MIMIC III were used for model training and test. Amongst them, 2949 (17.7%) patients had in-hospital death. The average AUROCs of the LASSO, RF, GBM, LR and SAPS II models were 0.829, 0.829, 0.845, 0.833 and 0.77, respectively. The Brier scores of the LASSO, RF, GBM, LR and SAPS II models were 0.108, 0.109, 0.104, 0.107 and 0.146, respectively. The calibration plots showed that the GBM, LASSO and LR models had good calibration; the RF model underestimated high-risk patients; and SAPS II had the poorest calibration.ConclusionThe machine learning-based models developed in this study had good prediction performance. Amongst them, the GBM model showed the best performance in predicting the risk of in-hospital death. It has the potential to assist physicians in the ICU to perform appropriate clinical interventions for critically ill sepsis patients and thus may help improve the prognoses of sepsis patients in the ICU.

Contemporary Cardiac MRI in Chronic Coronary Artery Disease.

Chronic coronary artery disease remains an unconquered clinical problem, affecting an increasing number of people worldwide. Despite the improved understanding of the disease development, the implementation of the many advances in diagnosis and therapy is lacking. Many clinicians continue to rely on patient’s symptoms and diagnostic methods, which do not enable optimal clinical decisions. For example, echocardiography and invasive coronary catheterisation remain the mainstay investigations for stable angina patients in many places, despite the evidence on their limitations and availability of better diagnostic options. Cardiac MRI is a powerful diagnostic method, supporting robust measurements of crucial markers of cardiac structure and function, myocardial perfusion and scar, as well as providing detailed insight into myocardial tissue. Accurate and informative diagnostic readouts can help with guiding therapy, monitoring disease progress and tailoring the response to treatment. In this article, the authors outline the evidence supporting the state-of-art applications based on cardiovascular magnetic resonance, allowing the clinician optimal use of this insightful diagnostic method in everyday clinical practice.

Artificial Intelligence-Based Clinical Decision Support Systems Using Advanced Medical Imaging and Radiomics

Artificial intelligence (AI) is poised to make a veritable impact in medicine. Clinical decision support (CDS) is an important area where AI can augment the clinician's capability to collect, understand and make inferences on an overwhelming volume of patient data to reach the optimal clinical decision. Advancements in medical image analysis, such as Radiomics, and data computation, such as machine learning, have expanded our understanding of disease processes and their management. In this article, we review the most relevant concepts of AI as applicable to advanced imaging-based clinical decision support systems.

Adverse events related to biologicals used for patients with multiple sclerosis: a comparison between information originating from regulators and information originating from the scientific community.

Background and purposeClinical decision making is facilitated by healthcare professionals’ and patients’ adequate knowledge of the adverse events. This is especially important for biologicals used for treating multiple sclerosis (MS). So far, little is known about whether different information sources report adverse events consistently.MethodsBiologicals authorized by the European Medicines Agency for the treatment of MS were included in this study. Information on adverse events derived from phase 3 clinical trials from European Public Assessment Reports (EPARs) and from scientific publications was compared.ResultsIn the study, eight biologicals used for the treatment of MS were included for which the EPAR and/or scientific publication reported a total of 707 adverse events. Approximately one‐third of the adverse events was reported in both the EPAR and scientific publication, one‐third was only reported in the EPAR and one‐third only in the scientific publication. Serious adverse events and adverse events that regulators classified as ‘important identified risk’ were significantly more often reported in both sources compared to adverse events not classified as such (respectively, 38% vs. 30% and 49% vs. 30%). Adverse events only reported in the EPAR or in the scientific publication were, in general, not described in the benefit–risk section or abstract, which were considered to be the most important sections of the documents.ConclusionsThis study showed that there is substantial discordance in the reporting of adverse events on the same phase 3 trials between EPARs and scientific publications. To support optimal clinical decision making, both documents should be considered.

Guideline for the diagnosis and treatment of gallbladder carcinoma (2019 edition)

In order to improve the overall therapeutic effect of gallbladder cancer in China, Branch of Biliary Surgery, Chinese Surgical Society and Chinese Committee of Biliary Surgeons have formulated the guideline for the diagnosis and treatment of gallbladder carcinoma (2019 edition) . The guideline provided an overview of the evidence on epidemiological risk factors, treatment and follow-up strategies for patients with gallbladder cancer.It also updated the new TNM stage and proposed the clinical classification of gallbladder cancer for the first time. The guideline highlighted the importance of accurate prediction of TNM stage and type of gallbladder cancer based on modern high-quality imaging technology and endoscopic techniques.The idea of comprehensive treatment should be established as the fundamental principle for patients with advanced gallbladder cancer, and a multidisciplinary approach is recommended to make optimal clinical decisions. Standard radical surgical treatment should be delivered by a team of experienced hepato-pancreato-biliary surgeons and pathologists.The combination regimens of chemotherapy, radiotherapy, targeted therapy and immunotherapy for gallbladder cancer have shown promise in improving prognosis. Further research is still needed to confer greater survival benefits to patients with gallbladder cancer.

Comprehensive evaluation of complex polymicrobial specimens using next generation sequencing and standard microbiological culture

Optimal clinical decision-making depends on identification of clinically relevant organisms present in a sample. Standard microbiological culture may fail to identify unusual or fastidious organisms and can misrepresent relative abundance of sample constituents. Culture-independent methods have improved our ability to deconvolute polymicrobial patient samples. We used next-generation 16S rRNA gene sequencing (NGS16S) to determine how often cultivatable organisms in complex polymicrobial samples are not reported by standard culture. Twenty consecutive bronchoalveolar lavage (BAL) samples were plated to standard and additional media; bacteria were identified by NGS16S analysis of DNA extracted directly from samples or from washed culture plates. 96% of organisms identified were cultivable, but only 21% were reported by standard culture, indicating that standard work-up provides an incomplete assessment of microbial constituents. Direct NGS16S correlated well with standard culture, identifying the same predominant organism in 50% of samples. When predominant organisms differed, NGS16S most often detected anaerobes, whose growth is unsupported by standard culture conditions for this specimen. NGS16S identified more organisms per sample and allowed identification of fastidious organisms, while culture was better at capturing organisms when bacterial load was low, and allowed incidental recovery of non-bacterial pathogens. Molecular and culture-based methods together detect more organisms than either method alone.

Levels of evidence supporting European and American community-acquired pneumonia guidelines.

Optimal clinical decisions should be supported by clinical practice guidelines (CPG) based on evidence generated from randomized clinical trials (RCT). We aimed to evaluate the class and level of evidence (LOE) supporting the international community-acquired pneumonia (CAP) guidelines and their variation over time. The 2019 Infectious Diseases Society of America/American Thoracic Society (IDSA/ATS) and the 2011 European Respiratory Society/European Society Clinical Microbiology Infectious Diseases (ERS/ESCMID) CPG and its immediate predecessors (2007 and 2005) were evaluated. The number of recommendations and distribution as LOE A (supported by multiple RCT or a single, large RCT), B (supported by data from a single RCT or observational studies) and C (expert opinion, case studies, or standard of care) was identified. Overall, recommendations for diagnosis, management, and prevention were graded as strong in 51.4%, 62.9%, and 23.5% in spite that they were supported by LOE A in 5.7%, 11.1%, and 52.9%, respectively. In the 2019 ATS/IDSA guidelines (39 recommendations), 7.7% (n= 3) recommendations were classified as LOE A, 30.8% (n= 12) as LOE B, and 61.5% (24%) as LOE C. Across the 2011 ERS/ESCMID guidelines (68 recommendations), 21.2% (n= 14) recommendations were classified as LOE A, 4.6% (n= 3) as LOE B, and 74.2% (n= 49) as LOE C. When comparing with prior versions, the proportion of recommendations that were LOE A did not significantly increase in ERS/ESCMID (21.2% vs 20%) and decreased in ATS/IDSA (7.7% vs 32.0%). In conclusion, large randomized trials or network meta-analysis including comparison of regimens to identify high probability of best cure and mortality is an unmet clinical need on CAP.

Assessment of mortality stratified by meropenem minimum inhibitory concentration in patients with Enterobacteriaceae bacteraemia: A patient-level analysis of published data

In 2010, the Clinical and Laboratory Standards Institute (CLSI) lowered carbapenem breakpoints to reduce the proportion of 'susceptible' organisms that produced carbapenemases. Few studies have evaluated the effect of this change on clinical outcomes. This systematic review aimed to evaluate the effect of carbapenem MICs on 30-day mortality from pooled patient-level data from studies of patients treated with carbapenems across a range of meropenem MICs. PubMed was searched to March 2019 with the terms 'carbapenem', 'meropenem', 'imipenem', 'doripenem', 'ertapenem', 'susceptibility' and 'outcomes'. Studies were included in the analysis if patients had Enterobacteriaceae bacteraemia treated with a carbapenem for ≥48 h and mortality was reported. Studies were excluded if all isolates were either susceptible or resistant to meropenem based on CLSI 2010 breakpoints or if only carbapenemase-producing isolates were included. Authors were contacted for patient-level data. The primary outcome was 30-day mortality, with planned subset analyses of patients treated with meropenem, receiving active combination therapy, treated in the ICU or infected with Klebsiella pneumoniae. Of 157 articles identified, 4 met the inclusion criteria (115 eligible patients). The odds of mortality increased with each increasing meropenem MIC dilution (OR=1.51, 95% CI 1.06-2.15) as a continuous variable. A similar increase in odds was observed in patients treated with meropenem, treated in the ICU, infected with K. pneumoniae or receiving no other active antimicrobials. Increasing meropenem MICs in Enterobacteriaceae were associated with increased mortality; however, more work is needed to define optimal clinical decision rules for infections within the susceptible range.

Advances in the application of artificial intelligence in critical care medicine

Artificial intelligence technology has produced a series of advanced models and algorithms in the field of critical care. Many model applications have been tested by clinical trials to support the physicians′ optimal clinical decision making. In this review, we will introduce application progresses of artificial intelligence in intensive care. This review aims to make clinicians understand how artificial intelligence serve in critical care medicine. The major contents of this review include introducing characteristics of data in intensive care unit (ICU), e.g., time series, image, text and discrete data. Early warning models in the field and research based on medical information mart for intensive care (MIMIC) database will be discussed in detail. Based on the application of artificial intelligence, clinicians will make better clinical decisions in a timely manner so as to improve clinical service ability for caring critical patients. Key words: Artificial intelligence; Big data; Critical care medicine; Intensive care unit

Lack of focus on nutrition and documentation in nursing homes, home care- and home nursing: the self-perceived views of the primary care workforce

BackgroundMalnutrition is a comprehensive challenge for the nursing home, home care- and home nursing sector. Nutritional care and the subsequent documentation are a common and multifaceted healthcare practice that requires that the healthcare professionals possess complex combinations of competencies in order to deliver high-quality care and treatment. The purpose of this study was to investigate how a varied group of healthcare professionals’ perceive their own competencies within nutrition and documentation and how organizational structures influence their daily work and the quality of care provided.MethodsTwo focus groups consisting of 14 healthcare professionals were conducted. The transcribed focus group interviews was analyzed using the qualitative content analysis approach.ResultsSix categories were identified: 1) Lack of uniform and systematic communication affect nutritional care practices 2) Experience-based knowledge among the primary workforce influences daily clinical decisions, 3) Different attitudes towards nutritional care lead to differences in the quality of care 4) Differences in organizational culture affect quality of care, 5) Lack of clear nutritional care responsibilities affect how daily care is performed and 6) Lack of clinical leadership and priorities makes nutritional care invisible.ConclusionsThe six categories revealed two explanatory themes: 1) Absent inter- and intra-professional collaboration and communication obstructs optimal clinical decision-making and 2) quality deterioration due to poorly-established nutritional care structure. Overall, the two themes explain that from the healthcare professionals’ point of view, a visible organization that allocates resources as well as prioritizing and articulating the need for daily nutritional care and documentation is a prerequisite for high-quality care and treatment. Furthermore, optimal clinical decision making among the healthcare professionals are compromised by imprecise and unclear language and terminology in the patients’ healthcare records and also a lack of clinical guidelines and standards for collaboration between different healthcare professionals working in nursing homes, home care or home nursing.The findings of this study are beneficial to support organizations within these settings with strategies focusing on increasing nutritional care and documentation competencies among the healthcare professionals. Furthermore, the results advocate for the daily involvement and support of leaders and managers in articulating and structuring the importance of nutritional care and treatment and the subsequent documentation.

The Philosophy of Evidence-Based Principles and Practice in Nutrition.

The practice of evidence-based nutrition involves using the best available nutrition evidence, together with clinical experience, to conscientiously work with patients’ values and preferences to help them prevent (sometimes), resolve (sometimes), or cope with (often) problems related to their physical, mental, and social health. This article outlines the 3 fundamental principles of evidence-based practice as applied to the field of clinical nutrition. First, optimal clinical decision making requires awareness of the best available evidence, which ideally will come from unbiased systematic summaries of that evidence. Second, evidence-based nutrition provides guidance on how to decide which evidence is more or less trustworthy—that is, how certain can we be of our patients’ prognosis, diagnosis, or of our therapeutic options? Third, evidence alone is never sufficient to make a clinical decision. Decision makers must always trade off the benefits with the risks, burden, and costs associated with alternative management strategies, and, in so doing, consider their patients’ unique predicament, including their values and preferences.

Symptom Clusters and Influencing Factors in Children With Acute Leukemia During Chemotherapy.

Acute leukemia is the most common malignancy in childhood. Identification of symptom clusters and their influencing factors in children with acute leukemia may improve the management of symptoms. The aims of this study were to investigate symptom clusters in children with acute leukemia during chemotherapy and analyze the factors influencing their severity. A cross-sectional survey was administered to 159 Chinese children with acute leukemia during chemotherapy. A demographic questionnaire and the Memorial Symptom Assessment Scale 10-18 were completed by the patients and their parents. Exploratory factor analysis was used to identify symptom clusters. Univariate analyses and multiple linear regression analyses were performed to analyze the factors affecting symptom clusters. Six clusters were identified, including gastrointestinal cluster, emotional cluster, head-related cluster, self-image disorder cluster, skin itching/irritation cluster, and somatic cluster. Factors influencing the severity of symptom clusters included age, gender, stage of chemotherapy, and medical reimbursement. There are multiple symptom clusters in children with acute leukemia during chemotherapy. Medical care staff should manage symptoms from the perspective of symptom cluster and carry out personalized interventions according to factors influencing these clusters. The ability to predict symptom clusters in children with acute leukemia undergoing chemotherapy may assist with optimal clinical decision making in order to alleviate the symptom burden and improve children's quality of life.

What are the indicators of patient-centred care in the literature on integrative medicine and patients with chronic disease?

The practice of evidence-based nutrition involves using the best available nutrition evidence, together with clinical experience, to conscientiously work with patients’ values and preferences to help them prevent (sometimes), resolve (sometimes), or cope with (often) problems related to their physical, mental, and social health. This article outlines the 3 fundamental principles of evidence-based practice as applied to the field of clinical nutrition. First, optimal clinical decision making requires awareness of the best available evidence, which ideally will come from unbiased systematic summaries of that evidence. Second, evidence-based nutrition provides guidance on how to decide which evidence is more or less trustworthy—that is, how certain can we be of our patients’ prognosis, diagnosis, or of our therapeutic options? Third, evidence alone is never sufficient to make a clinical decision. Decision makers must always trade off the benefits with the risks, burden, and costs associated with alternative management strategies, and, in so doing, consider their patients’ unique predicament, including their values and preferences.

The Issue of Rational Use of Antibiotics in the Treatment of Urinary Tract Infection and the Strategy of Antibiotic Resistance Management

The article focuses on the abuse of antibacterial drugs in patients with urinary tract infections, both in the adult population and in children. In today’s era of large-scale antibiotic resistance, such tactics are not only ineffective for the patient, but also detrimental to the population as a whole. The optimal clinical decision is stratification of the patient with urinary tract infections for the appointment of an antibiotic or the use of another alternative with proven efficacy, such as officinal urological vaccine Urivac.

SOP: First-ever epileptic seizure in adult patients

BackgroundAbout 5% of all adults will have at least one epileptic seizure in their life. The incidence of all unprovoked seizures ranges from approximately 50 to 70 /100,000. The very first epileptic seizure in an adult can be a very decisive event and demands a great deal of responsibility on the part of the treating clinician. Optimal clinical work-up and systematic decision-making are necessary to ensure adequate treatment as well as to avoid unnecessary treatment, such as life-long application of anticonvulsants that may not be indicated.AimTo present a pragmatic standard operating procedure (SOP) for approaching the first seizure in adults.MethodBased on current recommendations and personal suggestions, an SOP in the form of a flow chart accompanied with topical explanations and tables was created.ResultsApproaching the first seizure should start with obtaining bystander information on the seizure and its clinical features. Then, differential diagnoses should be considered. The diagnostic work-up hast to contain a neurological and physical examination, emergency blood tests and cerebral imaging. This should allow to differentiate an unprovoked from an acute symptomatic seizure, i.e. triggered by current specific and identifiable structural or metabolic cause that should be eliminated if possible. In the case of an unprovoked seizure, estimation of seizure recurrence is necessary for the decision to start treatment with antiepileptic drugs.ConclusionThe challenge of diagnostic work-up and treatment decisions after a first epileptic seizure in adults may be facilitated by a systematic, SOP-based approach.

Big data in nursing: What should we know?

Big data is a term for data sets that are so large or complex that traditional data processing application software is inadequate, which is described in 4As i.e. Volume, Variety, Velocity, and Veracity. Few examples of big data are Clinical data, Insurance and cost data, Patient behaviour & sentiment data and Research data. The use of big data technologies can help nurses and other healthcare providers improve care quality, optimize outcomes, and reduce the cost of healthcare. The ability for nurses to make optimal clinical decisions in the clinical area is dependent on having access to accurate, real- time information regardless of care setting. Currently, there are no agreed- upon rules for which data standards and nursing terminologies should be used, thus nursing documentation remains inconsistent even within a single hospital that has adopted a single nursing terminology. With inconsistent documentation and lack of agreement on standards, nursing data can’t consistently be used for quality measurement or improvement.

Establishment and external validation of a prognostic model for predicting disease-free survival and risk stratification in breast cancer patients treated with neoadjuvant chemotherapy.

BackgroundThe eighth edition of the American Joint Committee on Cancer (AJCC) tumor-node-metastasis (TNM) staging system for survival prediction and risk stratification in breast cancer (BC) patients after neoadjuvant chemotherapy (NCT) is of limited efficacy. This study aimed to establish a novel prognostic nomogram for predicting disease-free survival (DFS) in BC patients after NCT.Patients and methodsA total of 567 BC patients treated with NCT, from two independent centers, were included in this study. Cox proportional-hazards regression (CPHR) analysis was conducted to identify the independent prognostic factors for DFS, in order to develop a model. Subsequently, the discrimination and calibration ability of the prognostic model were assessed in terms of its concordance index (C-index), risk group stratification, and calibration curve. The performance of the nomogram was compared with that of the eighth edition of the AJCC TNM staging system via C-index.ResultsBased on the CPHR model, eight prognostic predictors were screened and entered into the nomogram. The prognostic model showed better performance (p<0.01) in terms of DFS prediction (C-index: 0.738; 95% CI: 0.698–0.779) than the eighth edition of the AJCC TNM staging system (C-index: 0.644; 95% CI: 0.604–0.684). Stratification into three risk groups highlighted significant differences between the survival curves in the training cohort and those in the validation cohort. The calibration curves for likelihood of 3- and 5-year DFS indicated optimal agreement between nomogram predictions and actual observations.ConclusionWe constructed and externally validated a novel nomogram scoring system for individualized DFS estimation in BC patients treated with NCT. This user-friendly predictive tool may help oncologists to make optimal clinical decisions.