Application of artificial intelligence in a real-world research for predicting the risk of liver metastasis in T1 colorectal cancer

Background Liver is the most common metastatic site of colorectal cancer (CRC) and liver metastasis (LM) determines subsequent treatment as well as prognosis of patients, especially in T1 patients. T1 CRC patients with LM are recommended to adopt surgery and systematic treatments rather than endoscopic therapy alone. Nevertheless, there is still no effective model to predict the risk of LM in T1 CRC patients. Hence, we aim to construct an accurate predictive model and an easy-to-use tool clinically. Methods We integrated two independent CRC cohorts from Surveillance Epidemiology and End Results database (SEER, training dataset) and Xijing hospital (testing dataset). Artificial intelligence (AI) and machine learning (ML) methods were adopted to establish the predictive model. Results A total of 16,785 and 326 T1 CRC patients from SEER database and Xijing hospital were incorporated respectively into the study. Every single ML model demonstrated great predictive capability, with an area under the curve (AUC) close to 0.95 and a stacking bagging model displaying the best performance (AUC = 0.9631). Expectedly, the stacking model exhibited a favorable discriminative ability and precisely screened out all eight LM cases from 326 T1 patients in the outer validation cohort. In the subgroup analysis, the stacking model also demonstrated a splendid predictive ability for patients with tumor size ranging from one to50mm (AUC = 0.956). Conclusion We successfully established an innovative and convenient AI model for predicting LM in T1 CRC patients, which was further verified in the external dataset. Ultimately, we designed a novel and easy-to-use decision tree, which only incorporated four fundamental parameters and could be successfully applied in clinical practice.

Cardiovascular risk prediction in type 2 diabetes: a comparison of 22 risk scores in primary care settings

Aims/hypothesis We aimed to compare the performance of risk prediction scores for CVD (i.e., coronary heart disease and stroke), and a broader definition of CVD including atrial fibrillation and heart failure (CVD+), in individuals with type 2 diabetes. Methods Scores were identified through a literature review and were included irrespective of the type of predicted cardiovascular outcome or the inclusion of individuals with type 2 diabetes. Performance was assessed in a contemporary, representative sample of 168,871 UK-based individuals with type 2 diabetes (age ≥18 years without pre-existing CVD+). Missing observations were addressed using multiple imputation. Results We evaluated 22 scores: 13 derived in the general population and nine in individuals with type 2 diabetes. The Systemic Coronary Risk Evaluation (SCORE) CVD rule derived in the general population performed best for both CVD (C statistic 0.67 [95% CI 0.67, 0.67]) and CVD+ (C statistic 0.69 [95% CI 0.69, 0.70]). The C statistic of the remaining scores ranged from 0.62 to 0.67 for CVD, and from 0.64 to 0.69 for CVD+. Calibration slopes (1 indicates perfect calibration) ranged from 0.38 (95% CI 0.37, 0.39) to 0.74 (95% CI 0.72, 0.76) for CVD, and from 0.41 (95% CI 0.40, 0.42) to 0.88 (95% CI 0.86, 0.90) for CVD+. A simple recalibration process considerably improved the performance of the scores, with calibration slopes now ranging between 0.96 and 1.04 for CVD. Scores with more predictors did not outperform scores with fewer predictors: for CVD+, QRISK3 (19 variables) had a C statistic of 0.68 (95% CI 0.68, 0.69), compared with SCORE CVD (six variables) which had a C statistic of 0.69 (95% CI 0.69, 0.70). Scores specific to individuals with diabetes did not discriminate better than scores derived in the general population: the UK Prospective Diabetes Study (UKPDS) scores performed significantly worse than SCORE CVD (p value <0.001). Conclusions/interpretation CVD risk prediction scores could not accurately identify individuals with type 2 diabetes who experienced a CVD event in the 10 years of follow-up. All 22 evaluated models had a comparable and modest discriminative ability. Graphical abstract

Neutrophil-lymphoycyte-ratio, platelet-lymphocyte-ratio and procalcitonin for early assessment of prognosis in patients undergoing VA-ECMO

The use of veno-arterial extracorporeal membrane oxygenation (VA-ECMO) is increasing, but mortality remains high. Early assessment of prognosis is challenging and valid markers are lacking. This study aimed to investigate Neutrophil–Lymphocyte Ratio (NLR), Platelet-Lymphocyte-Ratio (PLR) and Procalcitonin (PCT) for early assessment of prognosis in patients undergoing VA-ECMO. This retrospective single-center cohort study included 344 consecutive patients ≥ 18 years who underwent VA-ECMO due to cardiogenic shock. Main exposures were NLR, PLR and PCT measured within 24 h after VA-ECMO initiation. The primary endpoint was all-cause in-hospital mortality. In total, 92 patients were included into final analysis (71.7% male, age 57 ± 14 years). In-hospital mortality rate was 48.9%. Receiver operating characteristics (ROC) curve revealed an area under the curve (AUC) of 0.65 [95% confidence interval (CI) 0.53–0.76] for NLR. The AUCs of PLR and PCT were 0.47 [95%CI 0.35–0.59] and 0.54 [95%CI 0.42–0.66], respectively. Binary logistic regression showed an adjusted odds ratio of 3.32 [95%CI 1.13–9.76] for NLR, 1.0 [95%CI 0.998–1.002] for PLR and 1.02 [95%CI 0.99–1.05] for PCT. NLR is independently associated with in-hospital mortality in patients undergoing VA-ECMO. However, discriminative ability is weak. PLR and PCT seem not to be suitable for this purpose.

Predictors of Mortality in Patients with Advanced Cancer—A Systematic Review and Meta-Analysis

To timely initiate advance care planning in patients with advanced cancer, physicians should identify patients with limited life expectancy. We aimed to identify predictors of mortality. To identify the relevant literature, we searched Embase, MEDLINE, Cochrane Central, Web of Science, and PubMed databases between January 2000–April 2020. Identified studies were assessed on risk-of-bias with a modified QUIPS tool. The main outcomes were predictors and prediction models of mortality within a period of 3–24 months. We included predictors that were studied in ≥2 cancer types in a meta-analysis using a fixed or random-effects model and summarized the discriminative ability of models. We included 68 studies (ranging from 42 to 66,112 patients), of which 24 were low risk-of-bias, and 39 were included in the meta-analysis. Using a fixed-effects model, the predictors of mortality were: the surprise question, performance status, cognitive impairment, (sub)cutaneous metastases, body mass index, comorbidity, serum albumin, and hemoglobin. Using a random-effects model, predictors were: disease stage IV (hazard ratio [HR] 7.58; 95% confidence interval [CI] 4.00–14.36), lung cancer (HR 2.51; 95% CI 1.24–5.06), ECOG performance status 1+ (HR 2.03; 95% CI 1.44–2.86) and 2+ (HR 4.06; 95% CI 2.36–6.98), age (HR 1.20; 95% CI 1.05–1.38), male sex (HR 1.24; 95% CI 1.14–1.36), and Charlson comorbidity score 3+ (HR 1.60; 95% CI 1.11–2.32). Thirteen studies reported on prediction models consisting of different sets of predictors with mostly moderate discriminative ability. To conclude, we identified reasonably accurate non-tumor specific predictors of mortality. Those predictors could guide in developing a more accurate prediction model and in selecting patients for advance care planning.

Finely Crafted Features for Traffic Sign Recognition

Traffic sign recognition (TSR) is the basic technology of the Advanced Driving Assistance System (ADAS) and intelligent automobile, whileas high-qualified feature vector plays a key role in TSR. Therefore, the feature extraction of TSR has become an active research in the fields of computer vision and intelligent automobiles. Although deep learning features have made a breakthrough in image classification, it is difficult to apply to TSR because of its large scale of training dataset and high space-time complexity of model training. Considering visual characteristics of traffic signs and external factors such as weather, light, and blur in real scenes, an efficient method to extract high-qualified image features is proposed. As a result, the lower-dimension feature can accurately depict the visual feature of TSR due to powerful descriptive and discriminative ability. In addition, benefiting from a simple feature extraction method and lower time cost, our method is suitable to recognize traffic signs online in real-world applications scenarios. Extensive quantitative experimental results demonstrate the effectiveness and efficiency of our method.

Novel volumetric capnography indices measure ventilation inhomogeneity in cystic fibrosis

BackgroundVolumetric capnography (VCap) is a simpler alternative of multiple-breath washout (MBW) to detect ventilation inhomogeneity (VI) in patients with cystic fibrosis (CF). However, its diagnostic performance is influenced by breathing dynamics. We introduce two novel VCap indices, the Capnographic Inhomogeneity Indices (CIIs) that may overcome this limitation and explore their diagnostic characteristics in a cohort of CF patients.MethodsWe analysed 320 N2-MBW trials from 50 CF patients and 65 controls (age 4-18 years) and calculated classical VCap indices, such as slope III (SIII) and the capnographic index (KPIv). We introduced novel CIIs based on a theoretical lung model, and assessed their diagnostic performance compared to classical VCap indices and the lung clearance index (LCI).ResultsBoth CIIs were significantly higher in CF patients compared with controls (mean±SD CII1 5.9±1.4% versus 5.1±1.0%, p=0.002; CII2 7.7±1.8% versus 6.8±1.4%, p=0.002) and presented strong correlation with LCI (CII1 R2=0.47 and CII2 R2=0.44 in CF patients). Classical VCap indices showed inferior discriminative ability (SIII 2.3±1.0%/L versus 1.9±0.7%/L, P=0.013; KPIv 3.9±1.3% versus 3.5±1.2%, P=0.071), while the correlation with LCI was weak (SIII R2=0.03; KPIv R2=0.08 in CF patients). CIIs showed lower intra-subject inter-trial variability, calculated as coefficient of variation for three and relative difference for two trials, than classical VCap indices, but higher than LCI (CII1 11.1±8.2% and CII2 11.0±8.0% versus SIII 16.3±13.5%; KPIv 15.9±12.8%; LCI 5.9%±4.2%).ConclusionCIIs detect VI better than classical VCap indices and correlate well with LCI. However, further studies on their diagnostic performance and clinical utility are required.

The Impact of Heart Rate Circadian Rhythm on In-hospital Mortality in Stroke and Critically Ill Patients: Insights from the eICU Collaborative Research Database

Background: The dysregulation of the heart rate circadian rhythm has been documented to be an independent risk factor in multiple diseases. However, data showing the impact of dysregulated heart rate circadian rhythm in stroke and critically ill patients are scarce.Methods: Stroke and critically ill patients in the ICU between 2014 and 2015 from the recorded eICU Collaborative Research Database were included in the current analyses. The impact of circadian rhythm of heart rate on in-hospital mortality was analyzed. Three variables, Mesor (rhythm-adjusted mean of heart rate), Amplitude (distance from the highest point of circadian rhythm of heart rate to Mesor), and Peak time (time when the circadian rhythm of heart rate reaches the highest point) were used to evaluate the heart rate circadian rhythm. The incremental value of circadian rhythm variables in addition to Acute Physiology and Chronic Health Evaluation (APACHE) IV score to predict in-hospital mortality was also explored.Results: A total of 6,201 eligible patients were included. The in-hospital mortality was 16.2% (1,002/6,201). The circadian rhythm variables of heart rate, Mesor, Amplitude, and Peak time, were identified to be independent risk factors of in-hospital mortality. After adjustments, Mesor per 10 beats per min (bpm) increase was associated with a 1.17-fold (95%CI: 1.11, 1.24, P<0.001) and Amplitude per 5 bpm was associated with a 1.14-fold (95%CI: 1.06, 1.24, P<0.001) increase in the risk of in-hospital mortality, respectively. The risk of in-hospital mortality was lower in patients who had Peak time reached between 18:00-24:00 or 00:00-06:00; whereas the risk was highest in patients who had Peak time reached between 12:00-18:00 (OR: 1.33, 95%CI: 1.05, 1.68, P=0.017). Compared with APACHE IV score only (c-index=0.757), combining APACHE IV score and circadian rhythm variables of heart rate (c-index=0.766) was associated with increased discriminative ability (P=0.003).Conclusion: Circadian rhythm of heart rate is an independent risk factor of the in-hospital mortality in stroke and critically ill patients. Including circadian rhythm variables regarding heart rate might increase the discriminative ability of the risk score to predict the short-term prognosis of patients.

Radiomics Study for Discriminating Second Primary Lung Cancers From Pulmonary Metastases in Pulmonary Solid Lesions

BackgroundThe objective of this study was to assess the value of quantitative radiomics features in discriminating second primary lung cancers (SPLCs) from pulmonary metastases (PMs).MethodsThis retrospective study enrolled 252 malignant pulmonary nodules with histopathologically confirmed SPLCs or PMs and randomly assigned them to a training or validation cohort. Clinical data were collected from the electronic medical records system. The imaging and radiomics features of each nodule were extracted from CT images.ResultsA rad-score was generated from the training cohort using the least absolute shrinkage and selection operator regression. A clinical and radiographic model was constructed using the clinical and imaging features selected by univariate and multivariate regression. A nomogram composed of clinical-radiographic factors and a rad-score were developed to validate the discriminative ability. The rad-scores differed significantly between the SPLC and PM groups. Sixteen radiomics features and four clinical-radiographic features were selected to build the final model to differentiate between SPLCs and PMs. The comprehensive clinical radiographic–radiomics model demonstrated good discriminative capacity with an area under the curve of the receiver operating characteristic curve of 0.9421 and 0.9041 in the respective training and validation cohorts. The decision curve analysis demonstrated that the comprehensive model showed a higher clinical value than the model without the rad-score.ConclusionThe proposed model based on clinical data, imaging features, and radiomics features could accurately discriminate SPLCs from PMs. The model thus has the potential to support clinicians in improving decision-making in a noninvasive manner.

Development of Clinical Prediction Rules for One-Year Postoperative Functional Outcome in Patients with Intertrochanteric Fractures: The Intertrochanteric Fracture Ambulatory Prediction (IT-AP) Tool

Individualized prediction of postoperative ambulatory status for patients with intertrochanteric fractures is clinically relevant, during both preoperative and intraoperative periods. This study intended to develop clinical prediction rules (CPR) to predict one-year postoperative functional outcomes in patients with intertrochanteric fractures. CPR development was based on a secondary analysis of a retrospective cohort of patients with intertrochanteric fractures aged ≥50 years who underwent a surgical fixation. Good ambulatory status was defined as a New Mobility Score ≥5. Two CPR for preoperative and intraoperative predictions were derived using clinical profiles and surgical-related parameters using logistic regression with the multivariable fractional polynomial procedure. In this study, 221 patients with intertrochanteric fractures were included. Of these, 160 (72.4%) had good functional status at one year. The preoperative model showed an acceptable AuROC of 0.77 (95%CI 0.70 to 0.85). After surgical-related parameters were incorporated into the preoperative model, the model discriminative ability was significantly improved to an AuROC of 0.83 (95%CI 0.77 to 0.88) (p = 0.021). The newly-derived CPR enable physicians to provide patients with intertrochanteric fractures with their individualized predictions of functional outcome one year after surgery, which could be used for risk communication, surgical optimization and tailoring postoperative care that fits patients’ expectations.