Radiomics and machine learning applications in rectal cancer: Current update and future perspectives

The high incidence of rectal cancer in both sexes makes it one of the most common tumors, with significant morbidity and mortality rates. To define the best treatment option and optimize patient outcome, several rectal cancer biological variables must be evaluated. Currently, medical imaging plays a crucial role in the characterization of this disease, and it often requires a multimodal approach. Magnetic resonance imaging is the first-choice imaging modality for local staging and restaging and can be used to detect high-risk prognostic factors. Computed tomography is widely adopted for the detection of distant metastases. However, conventional imaging has recognized limitations, and many rectal cancer characteristics remain assessable only after surgery and histopathology evaluation. There is a growing interest in artificial intelligence applications in medicine, and imaging is by no means an exception. The introduction of radiomics, which allows the extraction of quantitative features that reflect tumor heterogeneity, allows the mining of data in medical images and paved the way for the identification of potential new imaging biomarkers. To manage such a huge amount of data, the use of machine learning algorithms has been proposed. Indeed, without prior explicit programming, they can be employed to build prediction models to support clinical decision making. In this review, current applications and future perspectives of artificial intelligence in medical imaging of rectal cancer are presented, with an imaging modality-based approach and a keen eye on unsolved issues. The results are promising, but the road ahead for translation in clinical practice is rather long.     

Automation,machine learning,and artificial intelligence in echocardiography: A brave new world

Automation, machine learning, and artificial intelligence (AI) are changing the landscape of echocardiography providing complimentary tools to physicians to enhance patient care. Multiple vendor software programs have incorporated automation to improve accuracy and efficiency of manual tracings. Automation with longitudinal strain and 3D echocardiography has shown great accuracy and reproducibility allowing the incorporation of these techniques into daily workflow. This will give further experience to nonexpert readers and allow the integration of these essential tools into more echocardiography laboratories. The potential for machine learning in cardiovascular imaging is still being discovered as algorithms are being created, with training on large data sets beyond what traditional statistical reasoning can handle. Deep learning when applied to large image repositories will recognize complex relationships and patterns integrating all properties of the image, which will unlock further connections about the natural history and prognosis of cardiac disease states. The purpose of this review article was to describe the role and current use of automation, machine learning, and AI in echocardiography and discuss potential limitations and challenges of in the future.     

Deep learning in hepatocellular carcinoma: Current status and future perspectives

Hepatocellular carcinoma (HCC) is among the leading causes of cancer incidence and death. Despite decades of research and development of new treatment options, the overall outcomes of patients with HCC continue to remain poor. There are areas of unmet need in risk prediction, early diagnosis, accurate prognostication, and individualized treatments for patients with HCC. Recent years have seen an explosive growth in the application of artificial intelligence (AI) technology in medical research, with the field of HCC being no exception. Among the various AI-based machine learning algorithms, deep learning algorithms are considered state-of-the-art techniques for handling and processing complex multimodal data ranging from routine clinical variables to high-resolution medical images. This article will provide a comprehensive review of the recently published studies that have applied deep learning for risk prediction, diagnosis, prognostication, and treatment planning for patients with HCC.     

Statistical and machine learning methodology for abdominal aortic aneurysm prediction from ultrasound screenings

A method of analysis of a database of patients (n = 10 329) screened for an abdominal aortic aneurysm (AAA) is presented. Self‐reported height, weight, age, gender, ethnicity, and parameters “Heart Problems,” “Hypertension,” “High Cholesterol,” “Diabetes Mellitus,” “Smoker Past 2 Years,” “Ever Smoked?,” “Family History AAA,” and “Family History Brain Aneurysm” were provided. Incidence of a AAA (defined as 3 cm diameter) was calculated as a function of age and body mass index (BMI) of greater than or less than a BMI 25 for various patient groups. Age was grouped into one of three categories in 15‐year intervals (35‐50 years, 50‐65 years, and 65 to 80 years). Most patients were Caucasian (n = 8575) and the largest group of patients with a AAA was the Caucasian male (198 of 279 total detected AAAs). A machine learning algorithm was written, with learning inputs from the acquired patient database. Of all groups, Caucasian males were found to have the highest incidence of AAA, with males in general higher than females. Smoking within the past two years was highly associated with AAA incidence, and a past history of smoking to a lesser extent. The incidence of AAA increased with age. When dividing groups into two cohorts by a BMI of 25, generally middle‐aged patients with a BMI > 25 had a higher incidence of a AAA. However, in general, the older age group with a BMI < 25 had a higher incidence of AAA. The addition of machine learning allows one to note the effect of an input keeping other input parameters constant. This helps identify a parameter that may be an independent predictor of a particular outcome. When using BMI as the single changing input, an increasing BMI was associated with an increased probability of a AAA, most significantly in middle‐aged patients, and then narrowing to similar probabilities in older age. This AAA screening program is ongoing. As data continues to be collected with particularly those patient groups presently underrepresented, questions as to an association of AAA with BMI as a function of age, and also an improvement in machine learning algorithm accuracy for various patient populations will continue.     

Predicting inpatient mortality in patients with inflammatory bowel disease: A machine learning approach

Background and Aim

Data are lacking on predicting inpatient mortality (IM) in patients admitted for inflammatory bowel disease (IBD). IM is a critical outcome; however, difficulty in its prediction exists due to infrequent occurrence. We assessed IM predictors and developed a predictive model for IM using machine-learning (ML).

Methods

Using the National Inpatient Sample (NIS) database (2005–2017), we extracted adults admitted for IBD. After ML-guided predictor selection, we trained and internally validated multiple algorithms, targeting minimum sensitivity and positive likelihood ratio (+LR) ≥ 80% and ≥ 3, respectively. Diagnostic odds ratio (DOR) compared algorithm performance. The best performing algorithm was additionally trained and validated for an IBD-related surgery sub-cohort. External validation was done using NIS 2018.

Results

In 398 426 adult IBD admissions, IM was 0.32% overall, and 0.87% among the surgical cohort (n = 40 784). Increasing age, ulcerative colitis, IBD-related surgery, pneumonia, chronic lung disease, acute kidney injury, malnutrition, frailty, heart failure, blood transfusion, sepsis/septic shock and thromboembolism were associated with increased IM. The QLattice algorithm, provided the highest performance model (+LR: 3.2, 95% CI 3.0–3.3; area-under-curve [AUC]:0.87, 85% sensitivity, 73% specificity), distinguishing IM patients by 15.6-fold when comparing high to low-risk patients. The surgical cohort model (+LR: 8.5, AUC: 0.94, 85% sensitivity, 90% specificity), distinguished IM patients by 49-fold. Both models performed excellently in external validation. An online calculator ( https://clinicalc.ai/im-ibd/ ) was developed allowing bedside model predictions.

Conclusions

An online prediction-model calculator captured > 80% IM cases during IBD-related admissions, with high discriminatory effectiveness. This allows for risk stratification and provides a basis for assessing interventions to reduce mortality in high-risk patients.     

Clinicopathological models for predicting lymph node metastasis in patients with early-stage lung adenocarcinoma: the application of machine learning algorithms

BackgroundLymph node metastasis (LNM) status can be a critical decisive factor for clinical management of lung cancer. Accurately evaluating the risk of LNM during or after the surgery can be helpful for making clinical decisions. This study aims to incorporate clinicopathological characteristics to develop reliable machine learning (ML)-based models for predicting LNM in patients with early-stage lung adenocarcinoma.MethodsA total of 709 lung adenocarcinoma patients with tumor size ≤2 cm were enrolled for analysis and modeling by multiple ML algorithms. The receiver operating characteristic (ROC) curve and decision curve were used for evaluating model’s predictive performance and clinical usefulness. Feature selection based on potential models was performed to identify most-contributed predictive factors.ResultsLNM occurred in 11.3% (80/709) of patients with lung adenocarcinoma. Most models reached high areas under the ROC curve (AUCs) >0.9. In the decision curve, all models performed better than the treat-all and treat-none lines. The random forest classifier (RFC) model, with a minimal number of five variables introduced (including carcinoembryonic antigen, solid component, micropapillary component, lymphovascular invasion and pleural invasion), was identified as the optimal model for predicting LNM, because of its excellent performance in both ROC and decision curves.ConclusionsThe cost-efficient application of RFC model could precisely predict LNM during or after the operation of early-stage adenocarcinomas (sensitivity: 87.5%; specificity: 82.2%). Incorporating clinicopathological characteristics, it is feasible to predict LNM intraoperatively or postoperatively by ML algorithms.     

Application of machine learning approaches to predict the 5-year survival status of patients with esophageal cancer

BackgroundAccurate prognostic estimation for esophageal cancer (EC) patients plays an important role in the process of clinical decision-making. The objective of this study was to develop an effective model to predict the 5-year survival status of EC patients using machine learning (ML) algorithms.MethodsWe retrieved the information of patients diagnosed with EC between 2010 and 2015 from the Surveillance, Epidemiology, and End Results (SEER) Program, including 24 features. A total of 8 ML models were applied to the selected dataset to classify the EC patients in terms of 5-year survival status, including 3 newly developed gradient boosting models (GBM), XGBoost, CatBoost, and LightGBM, 2 commonly used tree-based models, gradient boosting decision trees (GBDT) and random forest (RF), and 3 other ML models, artificial neural networks (ANN), naive Bayes (NB), and support vector machines (SVM). A 5-fold cross-validation was used in model performance measurement.ResultsAfter excluding records with missing data, the final study population comprised 10,588 patients. Feature selection was conducted based on the χ² test, however, the experiment results showed that the complete dataset provided better prediction of outcomes than the dataset with removal of non-significant features. Among the 8 models, XGBoost had the best performance [area under the receiver operating characteristic (ROC) curve (AUC): 0.852 for XGBoost, 0.849 for CatBoost, 0.850 for LightGBM, 0.846 for GBDT, 0.838 for RF, 0.844 for ANN, 0.833 for NB, and 0.789 for SVM]. The accuracy and logistic loss of XGBoost were 0.875 and 0.301, respectively, which were also the best performances. In the XGBoost model, the SHapley Additive exPlanations (SHAP) value was calculated and the result indicated that the four features: reason no cancer-directed surgery, Surg Prim Site, age, and stage group had the greatest impact on predicting the outcomes.ConclusionsThe XGBoost model and the complete dataset can be used to construct an accurate prognostic model for patients diagnosed with EC which may be applicable in clinical practice in the future.     

Machine learning methods for perioperative anesthetic management in cardiac surgery patients: a scoping review

BackgroundMachine learning (ML) is developing fast with promising prospects within medicine and already has several applications in perioperative care. We conducted a scoping review to examine the extent and potential limitations of ML implementation in perioperative anesthetic care, specifically in cardiac surgery patients.MethodsWe mapped the current literature by searching three databases: MEDLINE (Ovid), EMBASE (Ovid), and Cochrane Library. Articles were eligible if they reported on perioperative ML use in the field of cardiac surgery with relevance to anesthetic practices. Data on the applicability of ML and comparability to conventional statistical methods were extracted.ResultsForty-six articles on ML relevant to the work of the anesthesiologist in cardiac surgery were identified. Three main categories emerged: (I) event and risk prediction, (II) hemodynamic monitoring, and (III) automation of echocardiography. Prediction models based on ML tend to behave similarly to conventional statistical methods. Using dynamic hemodynamic or ultrasound data in ML models, however, shifts the potential to promising results.ConclusionsML in cardiac surgery is increasingly used in perioperative anesthetic management. The majority is used for prediction purposes similar to conventional clinical scores. Remarkable ML model performances are achieved when using real-time dynamic parameters. However, beneficial clinical outcomes of ML integration have yet to be determined. Nonetheless, the first steps introducing ML in perioperative anesthetic care for cardiac surgery have been taken.     

Treatment strategies for nodal and gastrointestinal follicular lymphoma: current status and future development

In recent years,therapies for follicular lymphoma (FL) have steadily improved.A series of phase Ⅲ trials comparing the effect of rituximab with chemotherapy vs chemotherapy alone in treating FL have indicated significant improvements in progression-free survival (PFS) and overall survival.Recent studies have found that prolonged response durations and PFS were obtained with maintenance therapy using rituximab or interferon after completion of first line therapy.For patients with relapsed or refractory FL,ph...     

Prediction of age and sex from paranasal sinus images using a deep learning network

This study was conducted to develop a convolutional neural network (CNN)-based model to predict the sex and age of patients by identifying unique unknown features from paranasal sinus (PNS) X-ray images.We employed a retrospective study design and used anonymized patient imaging data. Two CNN models, adopting ResNet-152 and DenseNet-169 architectures, were trained to predict sex and age groups (20–39, 40–59, 60+ years). The area under the curve (AUC), algorithm accuracy, sensitivity, and specificity were assessed. Class-activation map (CAM) was used to detect deterministic areas. A total of 4160 PNS X-ray images were collected from 4160 patients. The PNS X-ray images of patients aged ≥20 years were retrieved from the picture archiving and communication database system of our institution. The classification performances in predicting the sex (male vs female) and 3 age groups (20–39, 40–59, 60+ years) for each established CNN model were evaluated.For sex prediction, ResNet-152 performed slightly better (accuracy = 98.0%, sensitivity = 96.9%, specificity = 98.7%, and AUC = 0.939) than DenseNet-169. CAM indicated that maxillary sinuses (males) and ethmoid sinuses (females) were major factors in identifying sex. Meanwhile, for age prediction, the DenseNet-169 model was slightly more accurate in predicting age groups (77.6 ± 1.5% vs 76.3 ± 1.1%). CAM suggested that the maxillary sinus and the periodontal area were primary factors in identifying age groups.Our deep learning model could predict sex and age based on PNS X-ray images. Therefore, it can assist in reducing the risk of patient misidentification in clinics.     

Application of artificial intelligence in screening for adverse perinatal outcomes: A protocol for systematic review

The article presents a systematic review protocol. The aim of the study is an assessment of current studies regarding the application of artificial intelligence and neural networks in the screening for adverse perinatal outcomes. We intend to compare the reported efficacy of these methods to improve pregnancy care and outcomes. There are more and more studies that describe the role of machine learning in facilitating the diagnosis of adverse perinatal outcomes, like gestational diabetes or pregnancy hypertension. A systematic review of available literature seems to be crucial to compare the known efficacy and application. Publication of a systematic review in this category would improve the value of future studies. The studies reporting on artificial intelligence application will have a major impact on future prenatal practice.     

Artificial intelligence in small bowel capsule endoscopy ‐ current status,challenges and future promise

Neural network‐based solutions are under development to alleviate physicians from the tedious task of small‐bowel capsule endoscopy reviewing. Computer‐assisted detection is a critical step, aiming to reduce reading times while maintaining accuracy. Weakly supervised solutions have shown promising results; however, video‐level evaluations are scarce, and no prospective studies have been conducted yet. Automated characterization (in terms of diagnosis and pertinence) by supervised machine learning solutions is the next step. It relies on large, thoroughly labeled databases, for which preliminary “ground truth” definitions by experts are of tremendous importance. Other developments are under ways, to assist physicians in localizing anatomical landmarks and findings in the small bowel, in measuring lesions, and in rating bowel cleanliness. It is still questioned whether artificial intelligence will enter the market with proprietary, built‐in or plug‐in software, or with a universal cloud‐based service, and how it will be accepted by physicians and patients.     

Artificial Intelligence Aided Design of Tissue Engineering Scaffolds Employing Virtual Tomography and 3D Convolutional Neural Networks

Design requirements for different mechanical metamaterials, porous constructions and lattice structures, employed as tissue engineering scaffolds, lead to multi-objective optimizations, due to the complex mechanical features of the biological tissues and structures they should mimic. In some cases, the use of conventional design and simulation methods for designing such tissue engineering scaffolds cannot be applied because of geometrical complexity, manufacturing defects or large aspect ratios leading to numerical mismatches. Artificial intelligence (AI) in general, and machine learning (ML) methods in particular, are already finding applications in tissue engineering and they can prove transformative resources for supporting designers in the field of regenerative medicine. In this study, the use of 3D convolutional neural networks (3D CNNs), trained using digital tomographies obtained from the CAD models, is validated as a powerful resource for predicting the mechanical properties of innovative scaffolds. The presented AI-aided or ML-aided design strategy is believed as an innovative approach in area of tissue engineering scaffolds, and of mechanical metamaterials in general. This strategy may lead to several applications beyond the tissue engineering field, as we analyze in the discussion and future proposals sections of the research study.     

Mapping of ventricular tachycardia in patients with ischemic cardiomyopathy: Current approaches and future perspectives

Despite the technical improvements made in recent years, the overall long‐term success rate of ventricular tachycardia (VT) ablation in patients with ischemic cardiomyopathy remains disappointing. This unsatisfactory situation has persisted even though several approaches to VT substrate ablation allow mapping and ablation of noninducible/nontolerated arrhythmias. The current substrate mapping methods present some shortcomings regarding the accurate definition of the true scar, the modality of detection in sinus rhythm of abnormal electrograms that identify sites of critical channels during VT and the possibility to determine the boundaries of functional re‐entrant circuits during sinus or paced rhythms. In this review, we focus on current and proposed ablation strategies for VT to provide an overview of the potential/real application (and results) of several ablation approaches and future perspectives.     

Understanding short bowel syndrome: Current status and future perspectives

Short bowel syndrome (SBS) is a rare malabsorptive disorder as a result of the loss of bowel mass mostly secondary to surgical resection of the small intestine. Other causes are vascular diseases, neoplasms or inflammatory bowel disease. The spectrum of the disease is widely variable from single micronutrient malabsorption to complete intestinal failure, depending on the remaining length of the small intestine, the anatomical portion of intestine and the function of the remnant bowel. Over the last years, the management of affected patients has remarkably improved with the increase in patients’ quality of life and survival, mainly thanks to advances in home-based parenteral nutrition (PN). In the last ten years new treatment strategies have become available together with increasing experience and the encouraging results with new drugs, such as teduglutide, have added a new dimension to the management of SBS.This review aims to summarize the knowledge available in the current literature on SBS epidemiology, pathophysiology, and its surgical (including intestinal lengthening procedures and intestinal transplantation) and medical management with emphasis on the recent advances.Moreover, this review attempts to provide the new understanding and recent approaches to SBS complications such as sepsis, catheter thrombosis, and intestinal failure-associated liver disease.     

Prediction model based on machine learning for short- and long-term adverse events in left atrial appendage closure

BackgroundAt present, the prediction of adverse events (AE) had practical significance in clinic and the accuracy of AE prediction model after left atrial appendage closure (LAAC) needed to be improved. To identify a good prediction model based on machine learning for short- and long-term AE after LAAC.MethodsIn this study, 869 patients were included from the Department of Cardiovascular Medicine of Shanghai University of Medicine and Health Sciences Affiliated Zhoupu Hospital during 2017 and 2021. Univariate and multivariate analyses were conducted for short-term AE after LAAC to determine possible risk factors related with AE. We compared 8 machine learning algorithms for prediction short-term AE, and XGBoost was found to have the best performance. In addition, Cox-regression was used for long-term AE to find out the risk factors and establish a prediction model.ResultsIn univariate and multivariate analysis, body mass index (BMI) [odds ratio (OR) =0.91], congestive heart failure, hypertension, age ≥75 years, diabetes, stroke₂ attack (CHADS₂) score (OR =0.49) and bleeding history or predisposition, labile international normalized ratio (INR), elderly, drug/alcohol usage (BLED) score (OR =1.71) were shown to be significant risk factors for short-term AE. The XGbosst algorithm was used to predict short-term AE based on 15 possible risk factors. For long-term AE, Cox regression was used for the prediction. The CHADS₂ score [hazard ratio (HR) =1.43], hypertension (HR =2.18), age more than 75 (HR =0.49), diabetes (HR =0.57), BLED score (HR=0.28), stroke (HR =19.8), hepatopathy (HR =3.97), nephropathy (HR =2.93), INR instability (HR =4.18), drinking (HR =2.67), and drugs (HR =2.36) were significant risk factors for long-term AE. The XGBoost had a good receiver operating characteristic (ROC) curve and area under the curve (AUC) was 0.85. The accuracy of the XGBoost model stayed at nearly 0.95.ConclusionsIn short- and long-term AE, CHADS₂ score and BLED score were the most obvious risk factors. Several other risk factors also played roles in AE of LAAC. The incidence of long-term AE is under 15% and LAAC is effective and safe. The XGBoost model had good prediction accuracy and ROC curve.     

Machine learning applications in the diagnosis of leukemia: Current trends and future directions

Machine learning (ML) offers opportunities to advance pathological diagnosis, especially with increasing trends in digitalizing microscopic images. Diagnosing leukemia is time‐consuming and challenging in many areas globally and there is a growing trend in utilizing ML techniques for its diagnosis. In this review, we aimed to describe the literature of ML utilization in the diagnosis of the four common types of leukemia: acute lymphocytic leukemia (ALL), chronic lymphocytic leukemia (CLL), acute myeloid leukemia (AML), and chronic myelogenous leukemia (CML). Using a strict selection criterion, utilizing MeSH terminology and Boolean logic, an electronic search of MEDLINE and IEEE Xplore Digital Library was performed. The electronic search was complemented by handsearching of references of related studies and the top results of Google Scholar. The full texts of 58 articles were reviewed, out of which, 22 studies were included. The number of studies discussing ALL, AML, CLL, and CML was 12, 8, 3, and 1, respectively. No studies were prospectively applying algorithms in real‐world scenarios. Majority of studies had small and homogenous samples and used supervised learning for classification tasks. 91% of the studies were performed after 2010, and 74% of the included studies applied ML algorithms to microscopic diagnosis of leukemia. The included studies illustrated the need to develop the field of ML research, including the transformation from solely designing algorithms to practically applying them clinically.     

Identification of hub genes and their correlation with immune infiltration in coronary artery disease through bioinformatics and machine learning methods

BackgroundCoronary artery disease (CAD) is a multifactorial disease and its pathogenesis remains unclear. We aimed to explore the optimal feature genes (OFGs) for CAD and to investigate the function of immune cell infiltration of CAD. It will be helpful for better understanding of the pathogenesis and the development of genetic prediction of CAD.MethodsDatasets related to CAD were obtained from the Gene Expression Omnibus (GEO) database. Cases from the datasets met diagnostic criteria including clinical symptoms, electrocardiographic (ECG) and angiographic evidence. We identified differentially expressed genes (DEGs) and conducted functional enrichment analysis. OFGs were obtained from the least absolute shrinkage and selection operator (LASSO) algorithm, support vector machine recursive feature elimination (SVM-RFE) algorithm, and random forest (RF) algorithm. CIBERSORT was used to compare immune infiltration between CAD patients and normal controls, and the correlation between OFGs and immune cells was analyzed.ResultsDEGs were involved in the interleukin (IL)-17 signaling pathway, nuclear factor (NF)-kappa B signaling pathway, and tumor necrosis factor (TNF) signaling pathway. Gene Ontology (GO) analysis revealed DEGs were enriched in lipopolysaccharide (LPS), tertiary granule, and pattern recognition receptor activity. Disease Ontology (DO) analysis suggested DEGs were enriched in lung disease, arteriosclerotic cardiovascular disease (CVD). Matrix metalloproteinase 9 (MMP9), Pellino E3 ubiquitin protein ligase 1 (PELI1), thrombomodulin (THBD), and zinc finger protein 36 (ZFP36) were screened by the intersection of OFGs obtained from LASSO, SVM-REF, and RF algorithms. CAD patients had a lower proportion of memory B cells (P=0.019), CD8 T cells (P<0.001), resting memory CD4 T cells (P<0.001), regulatory T cells (P=0.028), and gamma delta T cells (P<0.001) than normal controls, while the proportion of activated memory CD4 T cells (P=0.014), resting natural killer (NK) cells (P<0.001), monocytes (P<0.001), M0 macrophages (P=0.023), activated mast cells (P<0.001), and neutrophils (P<0.001) in CAD patients were higher than normal controls. MMP9, PELI1, THBD, and ZFP36 were correlated with immune cells.ConclusionsMMP9, PELI1, THBD, and ZFP36 may be predicted biomarkers for CAD. The OFGs and association between OFGs and immune infiltration may provide potential biomarkers for CAD prediction along with the better assessment of the disease.