Artificial neural networks – A method for prediction of survival following liver resection for colorectal cancer metastases

Clinical Prediction Models for Prognosis of Colorectal Liver Metastases: A Comprehensive Review of Regression-Based and Machine Learning Models

Colorectal liver metastasis (CRLM) is a disease entity that warrants special attention due to its high frequency and potential curability. Identification of "high-risk" patients is increasingly popular for risk stratification and personalization of the management pathway. Traditional regression-based methods have been used to derive prediction models for these patients, and lately, focus has shifted to artificial intelligence-based models, with employment of variable supervised and unsupervised techniques. Multiple endpoints, like overall survival (OS), disease-free survival (DFS) and development or recurrence of postoperative complications have all been used as outcomes in these studies. This review provides an extensive overview of available clinical prediction models focusing on the prognosis of CRLM and highlights the different predictor types incorporated in each model. An overview of the modelling strategies and the outcomes chosen is provided. Specific patient and treatment characteristics included in the models are discussed in detail. Model development and validation methods are presented and critically appraised, and model performance is assessed within a proposed framework.

Follow up after surgery for colorectal liver metastases: A systematic review

INTRODUCTION

Recurrence post hepatectomy for colorectal liver metastases (CRLM) occurs in 70 % of patients within two years. No established guidance on the method or intensity of follow-up currently exists. The aim of this systematic review was to summarise literature and determine whether it is possible to identify an optimal follow up regime. To this date there are no randomised prospective studies investigating this.

METHODS

A systematic review was performed according to PRISMA guidelines. Outcomes included general demographics, method, frequency and duration of follow up, survival and recurrence data. Quality assessment of the papers was performed.

RESULTS

Twenty-five articles published between 1994 and 2022 were included, including 9945 patients. CT was the most common imaging modality (n = 14) and CEA most common blood test (n = 11). Intensity of follow up was higher in the first two years post resection and only two papers continued follow up post 5 years resection. There was wide variation in outcome measures - Overall survival (OS) was most commonly reported. Nine papers reported OS ranging between 39 and 78.1 %.

CONCLUSIONS

There is wide variation in follow up methods and outcome reporting. There is no strong evidence to support intensive follow up, and the benefits of long term follow up are also unknown due to the lack of patient centred data. High quality, prospective studies should be the focus of future research as further retrospective data is unlikely to resolve uncertainties around optimal follow up.

Artificial intelligence in colorectal surgery: an AI-powered systematic review

Artificial intelligence (AI) has the potential to revolutionize surgery in the coming years. Still, it is essential to clarify what the meaningful current applications are and what can be reasonably expected. This AI-powered review assessed the role of AI in colorectal surgery. A Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-compliant systematic search of PubMed, Embase, Scopus, Cochrane Library databases, and gray literature was conducted on all available articles on AI in colorectal surgery (from January 1 1997 to March 1 2021), aiming to define the perioperative applications of AI. Potentially eligible studies were identified using novel software powered by natural language processing (NLP) and machine learning (ML) technologies dedicated to systematic reviews. Out of 1238 articles identified, 115 were included in the final analysis. Available articles addressed the role of AI in several areas of interest. In the preoperative phase, AI can be used to define tailored treatment algorithms, support clinical decision-making, assess the risk of complications, and predict surgical outcomes and survival. Intraoperatively, AI-enhanced surgery and integration of AI in robotic platforms have been suggested. After surgery, AI can be implemented in the Enhanced Recovery after Surgery (ERAS) pathway. Additional areas of applications included the assessment of patient-reported outcomes, automated pathology assessment, and research. Available data on these aspects are limited, and AI in colorectal surgery is still in its infancy. However, the rapid evolution of technologies makes it likely that it will increasingly be incorporated into everyday practice.

Artificial Intelligence-Based Prediction of Recurrence after Curative Resection for Colorectal Cancer from Digital Pathological Images

BACKGROUND

To develop an artificial intelligence-based model to predict recurrence after curative resection for stage I-III colorectal cancer from digitized pathological slides.

PATIENTS AND METHODS

In this retrospective study, 471 consecutive patients who underwent curative resection for stage I-III colorectal cancer at our institution from 2004 to 2015 were enrolled, and 512 randomly selected tiles from digitally scanned images of hematoxylin and eosin-stained tumor tissue sections were used to train a convolutional neural network. Five-fold cross-validation was used to validate the model. The association between recurrence and the model's output scores were analyzed in the test cohorts.

RESULTS

The area under the receiver operating characteristic curve of the cross-validation was 0.7245 [95% confidence interval (CI) 0.6707-0.7783; P < 0.0001]. The score successfully classified patients into those with better and worse recurrence free survival (P < 0.0001). Multivariate analysis revealed that a high score was significantly associated with worse recurrence free survival [odds ratio (OR) 1.857; 95% CI 1.248-2.805; P = 0.0021], which was independent from other predictive factors: male sex (P = 0.0238), rectal cancer (P = 0.0396), preoperative abnormal carcinoembryonic antigen (CEA) level (P = 0.0216), pathological T3/T4 stage (P = 0.0162), and pathological positive lymph node metastasis (P < 0.0001).

CONCLUSIONS

The artificial intelligence-based prediction model discriminated patients with a high risk of recurrence. This approach could help decision-makers consider the benefits of adjuvant chemotherapy.

Neural Networks for Survival Prediction in Medicine Using Prognostic Factors: A Review and Critical Appraisal

Survival analysis deals with the expected duration of time until one or more events of interest occur. Time to the event of interest may be unobserved, a phenomenon commonly known as right censoring, which renders the analysis of these data challenging. Over the years, machine learning algorithms have been developed and adapted to right-censored data. Neural networks have been repeatedly employed to build clinical prediction models in healthcare with a focus on cancer and cardiology. We present the first ever attempt at a large-scale review of survival neural networks (SNNs) with prognostic factors for clinical prediction in medicine. This work provides a comprehensive understanding of the literature (24 studies from 1990 to August 2021, global search in PubMed). Relevant manuscripts are classified as methodological/technical (novel methodology or new theoretical model; 13 studies) or applications (11 studies). We investigate how researchers have used neural networks to fit survival data for prediction. There are two methodological trends: either time is added as part of the input features and a single output node is specified, or multiple output nodes are defined for each time interval. A critical appraisal of model aspects that should be designed and reported more carefully is performed. We identify key characteristics of prediction models (i.e., number of patients/predictors, evaluation measures, calibration), and compare ANN's predictive performance to the Cox proportional hazards model. The median sample size is 920 patients, and the median number of predictors is 7. Major findings include poor reporting (e.g., regarding missing data, hyperparameters) as well as inaccurate model development/validation. Calibration is neglected in more than half of the studies. Cox models are not developed to their full potential and claims for the performance of SNNs are exaggerated. Light is shed on the current state of art of SNNs in medicine with prognostic factors. Recommendations are made for the reporting of clinical prediction models. Limitations are discussed, and future directions are proposed for researchers who seek to develop existing methodology.

The Prediction of Peritoneal Carcinomatosis in Patients with Colorectal Cancer Using Machine Learning

The incidence of colon, rectal, and colorectal cancer is very high, and diagnosis is often made in the advanced stages of the disease. In cases where peritoneal carcinomatosis is limited, patients can benefit from newer treatment options if the disease is promptly identified, and they are referred to specialized centers. Therefore, an essential diagnostic benefit would be identifying those factors that could lead to early diagnosis. A retrospective study was performed using patient data gathered from 2010 to 2020. The collected data were represented by routine blood tests subjected to stringent inclusion and exclusion criteria. In order to determine the presence or absence of peritoneal carcinomatosis in colorectal cancer patients, three types of machine learning approaches were applied: a neuro-evolutive methodology based on artificial neural network (ANN), support vector machines (SVM), and random forests (RF), all combined with differential evolution (DE). The optimizer (DE in our case) determined the internal and structural parameters that defined the ANN, SVM, and RF in their optimal form. The RF strategy obtained the best accuracy in the testing phase (0.75). Using this RF model, a sensitivity analysis was applied to determine the influence of each parameter on the presence or absence of peritoneal carcinomatosis.

Development and internal validation of a machine-learning-developed model for predicting 1-year mortality after fragility hip fracture

Background

Fragility hip fracture increases morbidity and mortality in older adult patients, especially within the first year. Identification of patients at high risk of death facilitates modification of associated perioperative factors that can reduce mortality. Various machine learning algorithms have been developed and are widely used in healthcare research, particularly for mortality prediction. This study aimed to develop and internally validate 7 machine learning models to predict 1-year mortality after fragility hip fracture.

Methods

This retrospective study included patients with fragility hip fractures from a single center (Siriraj Hospital, Bangkok, Thailand) from July 2016 to October 2018. A total of 492 patients were enrolled. They were randomly categorized into a training group (344 cases, 70%) or a testing group (148 cases, 30%). Various machine learning techniques were used: the Gradient Boosting Classifier (GB), Random Forests Classifier (RF), Artificial Neural Network Classifier (ANN), Logistic Regression Classifier (LR), Naive Bayes Classifier (NB), Support Vector Machine Classifier (SVM), and K-Nearest Neighbors Classifier (KNN). All models were internally validated by evaluating their performance and the area under a receiver operating characteristic curve (AUC).

Results

For the testing dataset, the accuracies were GB model = 0.93, RF model = 0.95, ANN model = 0.94, LR model = 0.91, NB model = 0.89, SVM model = 0.90, and KNN model = 0.90. All models achieved high AUCs that ranged between 0.81 and 0.99. The RF model also provided a negative predictive value of 0.96, a positive predictive value of 0.93, a specificity of 0.99, and a sensitivity of 0.68.

Conclusions

Our machine learning approach facilitated the successful development of an accurate model to predict 1-year mortality after fragility hip fracture. Several machine learning algorithms (eg, Gradient Boosting and Random Forest) had the potential to provide high predictive performance based on the clinical parameters of each patient. The web application is available at www.hipprediction.com. External validation in a larger group of patients or in different hospital settings is warranted to evaluate the clinical utility of this tool.

Trial registration

Thai Clinical Trials Registry (22 February 2021; reg. no. TCTR20210222003).

Supplementary Information

The online version contains supplementary material available at 10.1186/s12877-022-03152-x.

Scoring systems for the management of oncological hepato-pancreato-biliary patients

Oncological scoring systems in surgery are used as evidence-based decision aids to best support management through assessing prognosis, effectiveness and recurrence. Currently, the use of scoring systems in the hepato-pancreato-biliary (HPB) field is limited as concerns over precision and applicability prevent their widespread clinical implementation. The aim of this review was to discuss clinically useful oncological scoring systems for surgical management of HPB patients. A narrative review was conducted to appraise oncological HPB scoring systems. Original research articles of established and novel scoring systems were searched using Google Scholar, PubMed, Cochrane, and Ovid Medline. Selected models were determined by authors. This review discusses nine scoring systems in cancers of the liver (CLIP, BCLC, ALBI Grade, RETREAT, Fong's score), pancreas (Genç's score, mGPS), and biliary tract (TMHSS, MEGNA). Eight models used exclusively objective measurements to compute their scores while one used a mixture of both subjective and objective inputs. Seven models evaluated their scoring performance in external populations, with reported discriminatory c-statistic ranging from 0.58 to 0.82. Selection of model variables was most frequently determined using a combination of univariate and multivariate analysis. Calibration, another determinant of model accuracy, was poorly reported amongst nine scoring systems. A diverse range of HPB surgical scoring systems may facilitate evidence-based decisions on patient management and treatment. Future scoring systems need to be developed using heterogenous patient cohorts with improved stratification, with future trends integrating machine learning and genetics to improve outcome prediction.

Is precision medicine for colorectal liver metastases still a utopia? New perspectives by modern biomarkers, radiomics, and artificial intelligence

The management of patients with liver metastases from colorectal cancer is still debated. Several therapeutic options and treatment strategies are available for an extremely heterogeneous clinical scenario. Adequate prediction of patients’ outcomes and of the effectiveness of chemotherapy and loco-regional treatments are crucial to reach a precision medicine approach. This has been an unmet need for a long time, but recent studies have opened new perspectives. New morphological biomarkers have been identified. The dynamic evaluation of the metastases across a time interval, with or without chemotherapy, provided a reliable assessment of the tumor biology. Genetics have been explored and, thanks to their strong association with prognosis, have the potential to drive treatment planning. The liver-tumor interface has been identified as one of the main determinants of tumor progression, and its components, in particular the immune infiltrate, are the focus of major research. Image mining and analyses provided new insights on tumor biology and are expected to have a relevant impact on clinical practice. Artificial intelligence is a further step forward. The present paper depicts the evolution of clinical decision-making for patients affected by colorectal liver metastases, facing modern biomarkers and innovative opportunities that will characterize the evolution of clinical research and practice in the next few years.

Artificial intelligence in the diagnosis and management of colorectal cancer liver metastases

Colorectal cancer (CRC) is the third most common malignancy worldwide, with approximately 50% of patients developing colorectal cancer liver metastasis (CRLM) during the follow-up period. Management of CRLM is best achieved via a multidisciplinary approach and the diagnostic and therapeutic decision-making process is complex. In order to optimize patients' survival and quality of life, there are several unsolved challenges which must be overcome. These primarily include a timely diagnosis and the identification of reliable prognostic factors. Furthermore, to allow optimal treatment options, a precision-medicine, personalized approach is required. The widespread digitalization of healthcare generates a vast amount of data and together with accessible high-performance computing, artificial intelligence (AI) technologies can be applied. By increasing diagnostic accuracy, reducing timings and costs, the application of AI could help mitigate the current shortcomings in CRLM management. In this review we explore the available evidence of the possible role of AI in all phases of the CRLM natural history. Radiomics analysis and convolutional neural networks (CNN) which combine computed tomography (CT) images with clinical data have been developed to predict CRLM development in CRC patients. AI models have also proven themselves to perform similarly or better than expert radiologists in detecting CRLM on CT and magnetic resonance scans or identifying them from the noninvasive analysis of patients' exhaled air. The application of AI and machine learning (ML) in diagnosing CRLM has also been extended to histopathological examination in order to rapidly and accurately identify CRLM tissue and its different histopathological growth patterns. ML and CNN have shown good accuracy in predicting response to chemotherapy, early local tumor progression after ablation treatment, and patient survival after surgical treatment or chemotherapy. Despite the initial enthusiasm and the accumulating evidence, AI technologies' role in healthcare and CRLM management is not yet fully established. Its limitations mainly concern safety and the lack of regulation and ethical considerations. AI is unlikely to fully replace any human role but could be actively integrated to facilitate physicians in their everyday practice. Moving towards a personalized and evidence-based patient approach and management, further larger, prospective and rigorous studies evaluating AI technologies in patients at risk or affected by CRLM are needed.

A Simulation Study to Compare the Predictive Performance of Survival Neural Networks with Cox Models for Clinical Trial Data

Background

Studies focusing on prediction models are widespread in medicine. There is a trend in applying machine learning (ML) by medical researchers and clinicians. Over the years, multiple ML algorithms have been adapted to censored data. However, the choice of methodology should be motivated by the real-life data and their complexity. Here, the predictive performance of ML techniques is compared with statistical models in a simple clinical setting (small/moderate sample size and small number of predictors) with Monte-Carlo simulations.

Methods

Synthetic data (250 or 1000 patients) were generated that closely resembled 5 prognostic factors preselected based on a European Osteosarcoma Intergroup study (MRC BO06/EORTC 80931). Comparison was performed between 2 partial logistic artificial neural networks (PLANNs) and Cox models for 20, 40, 61, and 80% censoring. Survival times were generated from a log-normal distribution. Models were contrasted in terms of the C-index, Brier score at 0-5 years, integrated Brier score (IBS) at 5 years, and miscalibration at 2 and 5 years (usually neglected). The endpoint of interest was overall survival.

Results

PLANNs original/extended were tuned based on the IBS at 5 years and the C-index, achieving a slightly better performance with the IBS. Comparison with Cox models showed that PLANNs can reach similar predictive performance on simulated data for most scenarios with respect to the C-index, Brier score, or IBS. However, Cox models were frequently less miscalibrated. Performance was robust in scenario data where censored patients were removed before 2 years or curtailing at 5 years was performed (on training data).

Conclusion

Survival neural networks reached a comparable predictive performance with Cox models but were generally less well calibrated. All in all, researchers should be aware of burdensome aspects of ML techniques such as data preprocessing, tuning of hyperparameters, and computational intensity that render them disadvantageous against conventional regression models in a simple clinical setting.

Application of an artificial neural network for predicting the potential chemotherapy benefit of patients with gastric cancer after radical surgery

BACKGROUND

Artificial neural network models have a strong self-learning ability and can deal with complex biological information, but there is no artificial neural network model for predicting the benefits of adjuvant chemotherapy in patients with gastric cancer.

METHODS

The clinicopathological data of patients who underwent radical resection of gastric cancer from January 2010 to September 2014 were analyzed retrospectively. Patients who underwent surgery combined with adjuvant chemotherapy were randomly divided into a training cohort (70%) and a validation cohort (30%). An artificial neural network model (potential-CT-benefit-ANN) was established, and its ability to predict the potential benefit of chemotherapy was evaluated by the C-index. The prognostic prediction and stratification ability of potential-CT-benefit-ANN and the eighth American Joint Committee on Cancer staging system were compared by receiver operating characteristic curves and Kaplan-Meier curves.

RESULTS

In both the training and validation cohort, potential-CT-benefit-ANN shows good prediction accuracy for potential adjuvant chemotherapy benefit. The receiver operating characteristic curve showed that the prediction accuracy of potential-CT-benefit-ANN was better than that of the eighth American Joint Committee on Cancer staging system in all groups. The calibration plots showed that the predicted prognosis of potential-CT-benefit-ANN was highly consistent with the actual value. The survival curves showed that potential-CT-benefit-ANN could stratify prognosis well for all groups and performed significantly better than the eighth AJCC staging system.

CONCLUSION

The potential-CT-benefit-ANN model developed in this study can accurately predict the potential benefits of adjuvant chemotherapy in patients with stage II/III gastric cancer. The benefit score based on potential-CT-benefit-ANN can predict the long-term prognosis of patients with adjuvant chemotherapy and has good prognostic stratification ability.

Status quo and future prospects of artificial neural network from the perspective of gastroenterologists

Artificial neural networks (ANNs) are one of the primary types of artificial intelligence and have been rapidly developed and used in many fields. In recent years, there has been a sharp increase in research concerning ANNs in gastrointestinal (GI) diseases. This state-of-the-art technique exhibits excellent performance in diagnosis, prognostic prediction, and treatment. Competitions between ANNs and GI experts suggest that efficiency and accuracy might be compatible in virtue of technique advancements. However, the shortcomings of ANNs are not negligible and may induce alterations in many aspects of medical practice. In this review, we introduce basic knowledge about ANNs and summarize the current achievements of ANNs in GI diseases from the perspective of gastroenterologists. Existing limitations and future directions are also proposed to optimize ANN’s clinical potential. In consideration of barriers to interdisciplinary knowledge, sophisticated concepts are discussed using plain words and metaphors to make this review more easily understood by medical practitioners and the general public.

Application of Artificial Intelligence Algorithms to Estimate the Success Rate in Medically Assisted Procreation

The aim of this study was to build an Artificial Neural Network (ANN) complemented by a decision tree to predict the chance of live birth after an In Vitro Fertilization (IVF)/Intracytoplasmic Sperm Injection (ICSI) treatment, before the first embryo transfer, using demographic and clinical data. Overall, 26 demographic and clinical data from 1193 cycles who underwent an IVF/ICSI treatment at Centro de Infertilidade e Reprodução Medicamente Assistida, between 2012 and 2019, were analyzed. An ANN was constructed by selecting experimentally the input variables which most correlated to the target through Pearson correlation. The final used variables were: woman’s age, total dose of gonadotropin, number of eggs, number of embryos and Antral Follicle Count (AFC). A decision tree was developed considering as an initial set the input variables integrated in the previous model. The ANN model was validated by the holdout method and the decision tree model by the 10-fold cross method. The ANN accuracy was 75.0% and the Area Under the Receiver Operating Characteristic (AUROC) curve was 75.2% (95% Confidence Interval (CI): 72.5–77.5%), whereas the decision tree model reached 75.0% and 74.9% (95% CI: 72.3–77.5%). These results demonstrated that both ANN and decision tree methods are fair for prediction the chance of conceive after an IVF/ICSI cycle.

External Validation of the Long Short-Term Memory Artificial Neural Network-Based SCaP Survival Calculator for Prediction of Prostate Cancer Survival

Purpose

Decision-making for treatment of newly diagnosed prostate cancer (PCa) is complex due to the multiple initial treatment modalities available. We aimed to externally validate the SCaP (Severance Study Group of Prostate Cancer) Survival Calculator that incorporates a long short-term memory artificial neural network (ANN) model to estimate survival outcomes of PCa according to initial treatment modality.

Materials and Methods

The validation cohort consisted of clinicopathological data of 4,415 patients diagnosed with biopsy-proven PCa between April 2005 and November 2018 at three institutions. Area under the curves (AUCs) and time-to-event calibration plots were utilized to determine the predictive accuracies of the SCaP Survival Calculator in terms of progression to castration-resistant PCa (CRPC)–free survival, cancer-specific survival (CSS), and overall survival (OS).

Results

Excellent discrimination was observed for CRPC-free survival, CSS, and OS outcomes, with AUCs of 0.962, 0.944, and 0.884 for 5-year outcomes and 0.959, 0.928, and 0.854 for 10-year outcomes, respectively. The AUC values were higher for all survival endpoints compared to those of the development cohort. Calibration plots showed that predicted probabilities of 5-year survival endpoints had concordance comparable to those of the observed frequencies. However, calibration performances declined for 10-year predictions with an overall underestimation.

Conclusion

The SCaP Survival Calculator is a reliable and useful tool for determining the optimal initial treatment modality and for guiding survival predictions for patients with newly diagnosed PCa. Further modifications in the ANN model incorporating cases with more extended follow-up periods are warranted to improve the ANN model for long-term predictions.

Improved myocardial perfusion PET imaging using artificial neural networks

Myocardial perfusion (MP) PET imaging plays a key role in risk assessment and stratification of patients with coronary artery disease. In this work, we proposed a patch-based artificial neural network (ANN) fusion approach that integrates information from the ML and the post-smoothed ML reconstruction to improve MP PET imaging. The proposed method was applied to images reconstructed from different noise levels to enhance quantification and task-based MP defect detection. Using the XCAT phantom, we simulated three MP PET imaging cases, one with normal perfusion and the other two with non-transmural and transmural regionally reduced perfusion of the left ventricular (LV) myocardium. The proposed ANN fusion technique was quantitatively evaluated in terms of the noise versus bias and noise versus contrast tradeoff, and compared with the post-smoothed ML reconstruction. Using the channelized Hotelling observer, we evaluated the detectability of the non-transmural and transmural defects through the receiver operating characteristic analysis. The quantitative results demonstrated that the ANN enhancement method reduced bias and improved contrast while reaching comparable noise to what the post-smoothed ML reconstruction achieved. Moreover, the ANN fusion technique significantly improved the defect detectability of both the non-transmural and transmural defects. In addition to the simulation study, we further evaluated the proposed method using patient data. Compared with the post-smoothed ML reconstruction, the ANN fusion improved the tradeoff between noise and the mean value on the LV myocardium, indicating its potential clinical application in MP PET imaging.

Development and validation of an artificial neural network prognostic model after gastrectomy for gastric carcinoma: An international multicenter cohort study

BACKGROUND

Recently, artificial neural network (ANN) methods have also been adopted to deal with the complex multidimensional nonlinear relationship between clinicopathologic variables and survival for patients with gastric cancer. Using a multinational cohort, this study aimed to develop and validate an ANN-based survival prediction model for patients with gastric cancer.

METHODS

Patients with gastric cancer who underwent gastrectomy in a Chinese center, a Japanese center, and recorded in the Surveillance, Epidemiology, and End Results database, respectively, were included in this study. Multilayer perceptron neural network was used to develop the prediction model. Time-dependent receiver operating characteristic (ROC) curves, area under the curves (AUCs), and decision curve analysis (DCA) were used to compare the ANN model with previous prediction models.

RESULTS

An ANN model with nine input nodes, nine hidden nodes, and two output nodes was constructed. These three cohort's data showed that the AUC of the model was 0.795, 0.836, and 0.850 for 5-year survival prediction, respectively. In the calibration curve analysis, the ANN-predicted survival had a high consistency with the actual survival. Comparison of the DCA and time-dependent ROC between the ANN model and previous prediction models showed that the ANN model had good and stable prediction capability compared to the previous models in all cohorts.

CONCLUSIONS

The ANN model has significantly better discriminative capability and allows an individualized survival prediction. This model has good versatility in Eastern and Western data and has high clinical application value.

Artificial Neural Network and Cox Regression Models for Predicting Mortality after Hip Fracture Surgery: A Population-Based Comparison

This study purposed to validate the accuracy of an artificial neural network (ANN) model for predicting the mortality after hip fracture surgery during the study period, and to compare performance indices between the ANN model and a Cox regression model. A total of 10,534 hip fracture surgery patients during 1996–2010 were recruited in the study. Three datasets were used: a training dataset (n = 7374) was used for model development, a testing dataset (n = 1580) was used for internal validation, and a validation dataset (1580) was used for external validation. Global sensitivity analysis also was performed to evaluate the relative importances of input predictors in the ANN model. Mortality after hip fracture surgery was significantly associated with referral system, age, gender, urbanization of residence area, socioeconomic status, Charlson comorbidity index (CCI) score, intracapsular fracture, hospital volume, and surgeon volume (p < 0.05). For predicting mortality after hip fracture surgery, the ANN model had higher prediction accuracy and overall performance indices compared to the Cox model. Global sensitivity analysis of the ANN model showed that the referral to lower-level medical institutions was the most important variable affecting mortality, followed by surgeon volume, hospital volume, and CCI score. Compared with the Cox regression model, the ANN model was more accurate in predicting postoperative mortality after a hip fracture. The forecasting predictors associated with postoperative mortality identified in this study can also bae used to educate candidates for hip fracture surgery with respect to the course of recovery and health outcomes.

Machine learning application for prediction of locoregional recurrences in early oral tongue cancer: a Web-based prognostic tool

Estimation of risk of recurrence in early-stage oral tongue squamous cell carcinoma (OTSCC) remains a challenge in the field of head and neck oncology. We examined the use of artificial neural networks (ANNs) to predict recurrences in early-stage OTSCC. A Web-based tool available for public use was also developed. A feedforward neural network was trained for prediction of locoregional recurrences in early OTSCC. The trained network was used to evaluate several prognostic parameters (age, gender, T stage, WHO histologic grade, depth of invasion, tumor budding, worst pattern of invasion, perineural invasion, and lymphocytic host response). Our neural network model identified tumor budding and depth of invasion as the most important prognosticators to predict locoregional recurrence. The accuracy of the neural network was 92.7%, which was higher than that of the logistic regression model (86.5%). Our online tool provided 88.2% accuracy, 71.2% sensitivity, and 98.9% specificity. In conclusion, ANN seems to offer a unique decision-making support predicting recurrences and thus adding value for the management of early OTSCC. To the best of our knowledge, this is the first study that applied ANN for prediction of recurrence in early OTSCC and provided a Web-based tool.

Effectiveness of simple tracing test as an objective evaluation of hand dexterity

This study aimed to demonstrate that the simple tracing test (STT) is useful for assessing the hand dexterity in patients with cervical spondylotic myelopathy (CSM) by comparing STT scores between healthy volunteers and CSM patients. This study included 25 CSM patients and 38 healthy volunteers. In the STT, the participants traced a sine wave displayed on a tablet device at a comfortable pace, and the tracing accuracy, changes in the total sum of pen pressures, and tracing duration were assessed. Data were analyzed using an artificial neural networks (ANN) model to obtain STT scores. All participants were evaluated using the subsection for the upper extremity function of the Japanese Orthopaedic Association (JOA) scoring system for cervical myelopathy (JOA subscore for upper extremity function) and the grip and release test (GRT). The results were compared with the STT scores. The mean STT scores were 24.4 ± 32.8 in the CSM patients and 84.9 ± 31.3 in the healthy volunteers, showing a significant difference. The STT scores showed highly positive correlations with both the JOA subscore for upper extremity function (r = 0.66; P < 0.001) and GRT values (r = 0.74; P < 0.001). Furthermore, receiver operating characteristic analysis showed an area under the curve of 0.89 (95% confidence interval, 0.76-1.00), demonstrating that STT has excellent discriminative ability. This study revealed that STT enables accurate assessment of the hand dexterity in CSM patients.

Establishment of multiple diagnosis models for colorectal cancer with artificial neural networks

The current study aimed to develop multiple diagnosis models for colorectal cancer (CRC) based on data from The Cancer Genome Atlas database and analysis with artificial neural networks in order to enhance CRC diagnosis methods. A genetic algorithm and mean impact value were used to select genes to be used as numerical encoded parameters to reflect cancer metastasis or aggression. Back propagation and learning vector quantization neural networks were used to build four diagnosis models: Cancer/Normal, M0/M1, carcinoembryonic antigen (CEA) <5/≥5 and Clinical stage I-II/III-IV. The performance of each model was evaluated by predictive accuracy (ACC), the area under the receiver operating characteristic curve (AUC) and a 10-fold cross-validation test. The ACC and AUC of the Cancer/Normal, M0/M1, CEA and Clinical stage models were 100%, 1.000; 87.14%, 0.670; 100%, 1.000; and 100%, 1.000, respectively. The 10-fold cross-validation test of the ACC values and sensitivity for each test were 93.75-99.39%, 1.0000; 80.58-88.24%, 0.9286-1.0000; 67.21-92.31%, 0.7091-1.0000; and 59.13-68.85%, 0.6017-0.6585, respectively. The diagnosis models developed in the current study combined gene expression profiling data and artificial intelligence algorithms to create tools for improved diagnosis of CRC.

Thymidylate synthase: a predictive biomarker in resected colorectal liver metastases receiving 5-FU treatment

AIM

To investigate the role of thymidylate synthase (TS) as a predictive biomarker in patients with resected colorectal liver metastases (CRLM).

MATERIALS & METHODS

PubMed, EMBASE and Cochrane Library were queried up to June 2017. Meta-analysis was performed using random-effects model. Risk of bias was assessed using funnel plots.

RESULTS

Six eligible studies were included, comprising a total of 542 patients. Meta-analysis demonstrated a trend to reduced overall survival in patients with resected CRLM with TS overexpression, with a hazard ratio of 1.13 (95% CI: 0.99-1.29; p = 0.08). In three studies where patients received systemic fluorouracil, the pooled hazard ratio was 2.25 (95% CI: 1.37-3.71; p = 0.001).

CONCLUSION

TS appears to be a clinically relevant predictive biomarker in patients with resected CRLM receiving systemic 5-FU.

A scoring system based on artificial neural network for predicting 10-year survival in stage II A colon cancer patients after radical surgery

Nearly 20% patients with stage II A colon cancer will develop recurrent disease post-operatively. The present study aims to develop a scoring system based on Artificial Neural Network (ANN) model for predicting 10-year survival outcome. The clinical and molecular data of 117 stage II A colon cancer patients from Sun Yat-sen University Cancer Center were used for training set and test set; poor pathological grading (score 49), reduced expression of TGFBR2 (score 33), over-expression of TGF-β (score 45), MAPK (score 32), pin1 (score 100), β-catenin in tumor tissue (score 50) and reduced expression of TGF-β in normal mucosa (score 22) were selected as the prognostic risk predictors. According to the developed scoring system, the patients were divided into 3 subgroups, which were supposed with higher, moderate and lower risk levels. As a result, for the 3 subgroups, the 10-year overall survival (OS) rates were 16.7%, 62.9% and 100% (P < 0.001); and the 10-year disease free survival (DFS) rates were 16.7%, 61.8% and 98.8% (P < 0.001) respectively. It showed that this scoring system for stage II A colon cancer could help to predict long-term survival and screen out high-risk individuals for more vigorous treatment.

Comparison of Basic and Ensemble Data Mining Methods in Predicting 5-Year Survival of Colorectal Cancer Patients

INTRODUCTION

Colorectal cancer (CRC) is one of the most common malignancies and cause of cancer mortality worldwide. Given the importance of predicting the survival of CRC patients and the growing use of data mining methods, this study aims to compare the performance of models for predicting 5-year survival of CRC patients using variety of basic and ensemble data mining methods.

METHODS

The CRC dataset from The Shahid Beheshti University of Medical Sciences Research Center for Gastroenterology and Liver Diseases were used for prediction and comparative study of the base and ensemble data mining techniques. Feature selection methods were used to select predictor attributes for classification. The WEKA toolkit and MedCalc software were respectively utilized for creating and comparing the models.

RESULTS

The obtained results showed that the predictive performance of developed models was altogether high (all greater than 90%). Overall, the performance of ensemble models was higher than that of basic classifiers and the best result achieved by ensemble voting model in terms of area under the ROC curve (AUC= 0.96).

CONCLUSION

AUC Comparison of models showed that the ensemble voting method significantly outperformed all models except for two methods of Random Forest (RF) and Bayesian Network (BN) considered the overlapping 95% confidence intervals. This result may indicate high predictive power of these two methods along with ensemble voting for predicting 5-year survival of CRC patients.

Feature selection through validation and un-censoring of endovascular repair survival data for predicting the risk of re-intervention

Background

Feature selection (FS) process is essential in the medical area as it reduces the effort and time needed for physicians to measure unnecessary features. Choosing useful variables is a difficult task with the presence of censoring which is the unique characteristic in survival analysis. Most survival FS methods depend on Cox’s proportional hazard model; however, machine learning techniques (MLT) are preferred but not commonly used due to censoring. Techniques that have been proposed to adopt MLT to perform FS with survival data cannot be used with the high level of censoring. The researcher’s previous publications proposed a technique to deal with the high level of censoring. It also used existing FS techniques to reduce dataset dimension. However, in this paper a new FS technique was proposed and combined with feature transformation and the proposed uncensoring approaches to select a reduced set of features and produce a stable predictive model.

Methods

In this paper, a FS technique based on artificial neural network (ANN) MLT is proposed to deal with highly censored Endovascular Aortic Repair (EVAR). Survival data EVAR datasets were collected during 2004 to 2010 from two vascular centers in order to produce a final stable model. They contain almost 91% of censored patients. The proposed approach used a wrapper FS method with ANN to select a reduced subset of features that predict the risk of EVAR re-intervention after 5 years to patients from two different centers located in the United Kingdom, to allow it to be potentially applied to cross-centers predictions. The proposed model is compared with the two popular FS techniques; Akaike and Bayesian information criteria (AIC, BIC) that are used with Cox’s model.

Results

The final model outperforms other methods in distinguishing the high and low risk groups; as they both have concordance index and estimated AUC better than the Cox’s model based on AIC, BIC, Lasso, and SCAD approaches. These models have p-values lower than 0.05, meaning that patients with different risk groups can be separated significantly and those who would need re-intervention can be correctly predicted.

Conclusion

The proposed approach will save time and effort made by physicians to collect unnecessary variables. The final reduced model was able to predict the long-term risk of aortic complications after EVAR. This predictive model can help clinicians decide patients’ future observation plan.

Electronic supplementary material

The online version of this article (doi:10.1186/s12911-017-0508-3) contains supplementary material, which is available to authorized users.

Complementarity of Clinician Judgment and Evidence Based Models in Medical Decision Making: Antecedents, Prospects, and Challenges

Early accounts of the development of modern medicine suggest that the clinical skills, scientific competence, and doctors' judgment were the main impetus for treatment decision, diagnosis, prognosis, therapy assessment, and medical progress. Yet, clinician judgment has its own critics and is sometimes harshly described as notoriously fallacious and an irrational and unfathomable black box with little transparency. With the rise of contemporary medical research, the reputation of clinician judgment has undergone significant reformation in the last century as its fallacious aspects are increasingly emphasized relative to the evidence based options. Within the last decade, however, medical forecasting literature has seen tremendous change and new understanding is emerging on best ways of sharing medical information to complement the evidence based medicine practices. This review revisits and highlights the core debate on clinical judgments and its interrelations with evidence based medicine. It outlines the key empirical results of clinician judgments relative to evidence based models and identifies its key strengths and prospects, the key limitations and conditions for the effective use of clinician judgment, and the extent to which it can be optimized and professionalized for medical use.

Boosting backpropagation algorithm by stimulus-sampling: Application in computer-aided medical diagnosis

Neural networks (NNs), in general, and multi-layer perceptron (MLP), in particular, represent one of the most efficient classifiers among the machine learning (ML) algorithms. Inspired by the stimulus-sampling paradigm, it is plausible to assume that the association of stimuli with the neurons in the output layer of a MLP can increase its performance. The stimulus-sampling process is assumed memoryless (Markovian), in the sense that the choice of a particular stimulus at a certain step, conditioned by the whole prior evolution of the learning process, depends only on the network's answer at the previous step. This paper proposes a novel learning technique, by enhancing the standard backpropagation algorithm performance with the aid of a stimulus-sampling procedure applied to the output neurons. The network uses the observable behavior that varies throughout the training process by stimulating the correct answers through corresponding rewards/penalties assigned to the output neurons. The proposed model has been applied in computer-aided medical diagnosis using five real-life breast cancer, colon cancer, diabetes, thyroid, and fetal heartbeat databases. The statistical comparison to well-established ML algorithms proved beyond doubt its efficiency and robustness.

Using machine learning methods for predicting inhospital mortality in patients undergoing open repair of abdominal aortic aneurysm

An abdominal aortic aneurysm is an abnormal dilatation of the aortic vessel at abdominal level. This disease presents high rate of mortality and complications causing a decrease in the quality of life and increasing the cost of treatment. To estimate the mortality risk of patients undergoing surgery is complex due to the variables associated. The use of clinical decision support systems based on machine learning could help medical staff to improve the results of surgery and get a better understanding of the disease. In this work, the authors present a predictive system of inhospital mortality in patients who were undergoing to open repair of abdominal aortic aneurysm. Different methods as multilayer perceptron, radial basis function and Bayesian networks are used. Results are measured in terms of accuracy, sensitivity and specificity of the classifiers, achieving an accuracy higher than 95%. The developing of a system based on the algorithms tested can be useful for medical staff in order to make a better planning of care and reducing undesirable surgery results and the cost of the post-surgical treatments.

Machine Learning Approaches for Predicting Radiation Therapy Outcomes: A Clinician's Perspective

Radiation oncology has always been deeply rooted in modeling, from the early days of isoeffect curves to the contemporary Quantitative Analysis of Normal Tissue Effects in the Clinic (QUANTEC) initiative. In recent years, medical modeling for both prognostic and therapeutic purposes has exploded thanks to increasing availability of electronic data and genomics. One promising direction that medical modeling is moving toward is adopting the same machine learning methods used by companies such as Google and Facebook to combat disease. Broadly defined, machine learning is a branch of computer science that deals with making predictions from complex data through statistical models. These methods serve to uncover patterns in data and are actively used in areas such as speech recognition, handwriting recognition, face recognition, "spam" filtering (junk email), and targeted advertising. Although multiple radiation oncology research groups have shown the value of applied machine learning (ML), clinical adoption has been slow due to the high barrier to understanding these complex models by clinicians. Here, we present a review of the use of ML to predict radiation therapy outcomes from the clinician's point of view with the hope that it lowers the "barrier to entry" for those without formal training in ML. We begin by describing 7 principles that one should consider when evaluating (or creating) an ML model in radiation oncology. We next introduce 3 popular ML methods--logistic regression (LR), support vector machine (SVM), and artificial neural network (ANN)--and critique 3 seminal papers in the context of these principles. Although current studies are in exploratory stages, the overall methodology has progressively matured, and the field is ready for larger-scale further investigation.

An Artificial Neural Network Stratifies the Risks of Reintervention and Mortality after Endovascular Aneurysm Repair; a Retrospective Observational study

Background

Lifelong surveillance after endovascular repair (EVAR) of abdominal aortic aneurysms (AAA) is considered mandatory to detect potentially life-threatening endograft complications. A minority of patients require reintervention but cannot be predictively identified by existing methods. This study aimed to improve the prediction of endograft complications and mortality, through the application of machine-learning techniques.

Methods

Patients undergoing EVAR at 2 centres were studied from 2004-2010. Pre-operative aneurysm morphology was quantified and endograft complications were recorded up to 5 years following surgery. An artificial neural networks (ANN) approach was used to predict whether patients would be at low- or high-risk of endograft complications (aortic/limb) or mortality. Centre 1 data were used for training and centre 2 data for validation. ANN performance was assessed by Kaplan-Meier analysis to compare the incidence of aortic complications, limb complications, and mortality; in patients predicted to be low-risk, versus those predicted to be high-risk.

Results

761 patients aged 75 +/- 7 years underwent EVAR. Mean follow-up was 36+/- 20 months. An ANN was created from morphological features including angulation/length/areas/diameters/volume/tortuosity of the aneurysm neck/sac/iliac segments. ANN models predicted endograft complications and mortality with excellent discrimination between a low-risk and high-risk group. In external validation, the 5-year rates of freedom from aortic complications, limb complications and mortality were 95.9% vs 67.9%; 99.3% vs 92.0%; and 87.9% vs 79.3% respectively (p<0.001)

Conclusion

This study presents ANN models that stratify the 5-year risk of endograft complications or mortality using routinely available pre-operative data.

The potential of interleukin 12 receptor beta 2 (IL12RB2) and tumor necrosis factor receptor superfamily member 8 (TNFRSF8) gene as diagnostic biomarkers of oral lichen planus (OLP)

OBJECTIVE

This study evaluated the potential of interleukin 12 receptor beta 2 and tumor necrosis factor receptor superfamily member 8 as diagnostic biomarkers of oral lichen planus (OLP).

MATERIALS AND METHODS

The mRNA expression of IL12RB2 and TNFRSF8 in FFPE OLP samples (OLP group, n = 38) were investigated with quantitative reverse transcriptase-polymerase chain reaction (qRT-PCR) analysis and compared to those of chronic non-specific mucositis (Non-OLP group, n = 25) and normal mucosa (Normal group, n = 18). Predictive modeling of the expression of IL12RB2 and TNFRSF8 was constructed using support vector machine (SVM), random forest (RF), linear discriminant analysis (LDA), neural network (NN) and naive Bayes (NB) methods.

RESULTS

Normalized expression of IL12RB2 in the OLP group (3.78 ± 1.67) was significantly higher than the Normal group (1.97 ± 1.12), but lower than the Non-OLP group (6.86 ± 1.67). TNFRSF8 gene expression in the OLP group (7.46 ± 1.51) was significantly higher than the Normal group (2.90 ± 1.61), but no significant difference was found between the OLP and Non-OLP groups. The ratio of IL12RB2/TNFRSF8 in the OLP group (0.52 ± 0.23) was significantly lower than the Normal group (0.74 ± 0.39) and the Non-OLP group (1.07 ± 0.38). In the predictive modeling, the area under receiver operating characteristic (ROC) curves (AUC) ranged from 0.83-0.92 and their accuracy was higher than 0.75 in all methods.

CONCLUSIONS

The IL12RB2/TNFRSF8 ratio can be a useful diagnostic tool for OLP.

Pre-operative prediction of surgical morbidity in children: comparison of five statistical models

BACKGROUND

The accurate prediction of surgical risk is important to patients and physicians. Logistic regression (LR) models are typically used to estimate these risks. However, in the fields of data mining and machine-learning, many alternative classification and prediction algorithms have been developed. This study aimed to compare the performance of LR to several data mining algorithms for predicting 30-day surgical morbidity in children.

METHODS

We used the 2012 National Surgical Quality Improvement Program-Pediatric dataset to compare the performance of (1) a LR model that assumed linearity and additivity (simple LR model) (2) a LR model incorporating restricted cubic splines and interactions (flexible LR model) (3) a support vector machine, (4) a random forest and (5) boosted classification trees for predicting surgical morbidity.

RESULTS

The ensemble-based methods showed significantly higher accuracy, sensitivity, specificity, PPV, and NPV than the simple LR model. However, none of the models performed better than the flexible LR model in terms of the aforementioned measures or in model calibration or discrimination.

CONCLUSION

Support vector machines, random forests, and boosted classification trees do not show better performance than LR for predicting pediatric surgical morbidity. After further validation, the flexible LR model derived in this study could be used to assist with clinical decision-making based on patient-specific surgical risks.

Diagnosis of pancreatic carcinoma based on combined measurement of multiple serum tumor markers using artificial neural network analysis

BACKGROUND

Artificial neural network (ANN) has demonstrated the ability to assimilate information from multiple sources to enable the detection of subtle and complex patterns. In this research, we evaluated an ANN model in the diagnosis of pancreatic cancer using multiple serum markers.

METHODS

In this retrospective analysis, 913 serum specimens collected at the Department of General Surgery of Beijing Friendship Hospital were analyzed for carbohydrate antigen 19-9 (CA19-9), carbohydrate antigen 125 (CA125), and carcinoembryonic antigen (CEA). The three tumor marker values were used as inputs into an ANN and randomized into a training set of 658 (70.31% were malignant) and a test set of the remaining 255 samples (70.69% were malignant). The samples were also evaluated using a Logistic regression (LR) model.

RESULTS

The ANN-derived composite index was superior to each of the serum tumor markers alone and the Logistic regression model. The areas under receiver operating characteristic curves (AUROC) was 0.905 (95% confidence Interval (CI) 0.868-0.942) for ANN, 0.812 (95% CI 0.762-0.863) for the Logistic regression model, 0.845 (95% CI 0.798-0.893) for CA19-9, 0.795 (95% CI 0.738-0.851) for CA125, and 0.800 (95% CI 0.746-0.854) for CEA. ANN analysis of multiple markers yielded a high level of diagnostic accuracy (83.53%) compared to LR (74.90%).

CONCLUSION

The performance of ANN model in the diagnosis of pancreatic cancer is better than the single tumor marker and LR model.