Deep-learning model for predicting the survival of rectal adenocarcinoma patients based on a surveillance, epidemiology, and end results analysis

Integrating Omics Data and AI for Cancer Diagnosis and Prognosis

Cancer is one of the leading causes of death, making timely diagnosis and prognosis very important. Utilization of AI (artificial intelligence) enables providers to organize and process patient data in a way that can lead to better overall outcomes. This review paper aims to look at the varying uses of AI for diagnosis and prognosis and clinical utility. PubMed and EBSCO databases were utilized for finding publications from 1 January 2020 to 22 December 2023. Articles were collected using key search terms such as "artificial intelligence" and "machine learning." Included in the collection were studies of the application of AI in determining cancer diagnosis and prognosis using multi-omics data, radiomics, pathomics, and clinical and laboratory data. The resulting 89 studies were categorized into eight sections based on the type of data utilized and then further subdivided into two subsections focusing on cancer diagnosis and prognosis, respectively. Eight studies integrated more than one form of omics, namely genomics, transcriptomics, epigenomics, and proteomics. Incorporating AI into cancer diagnosis and prognosis alongside omics and clinical data represents a significant advancement. Given the considerable potential of AI in this domain, ongoing prospective studies are essential to enhance algorithm interpretability and to ensure safe clinical integration.

Magnetic Resonance Deep Learning Radiomic Model Based on Distinct Metastatic Vascular Patterns for Evaluating Recurrence-Free Survival in Hepatocellular Carcinoma

BACKGROUND

The metastatic vascular patterns of hepatocellular carcinoma (HCC) are mainly microvascular invasion (MVI) and vessels encapsulating tumor clusters (VETC). However, most existing VETC-related radiological studies still focus on the prediction of VETC status.

PURPOSE

This study aimed to build and compare VETC-MVI related models (clinical, radiomics, and deep learning) associated with recurrence-free survival of HCC patients.

STUDY TYPE

Retrospective.

POPULATION

398 HCC patients (349 male, 49 female; median age 51.7 years, and age range: 22-80 years) who underwent resection from five hospitals in China. The patients were randomly divided into training cohort (n = 358) and test cohort (n = 40).

FIELD STRENGTH/SEQUENCE

3-T, pre-contrast T1-weighted imaging spoiled gradient recalled echo (T1WI SPGR), T2-weighted imaging fast spin echo (T2WI FSE), and contrast enhanced arterial phase (AP), delay phase (DP).

ASSESSMENT

Two radiologists performed the segmentation of HCC on T1WI, T2WI, AP, and DP images, from which radiomic features were extracted. The RFS related clinical characteristics (VETC, MVI, Barcelona stage, tumor maximum diameter, and alpha fetoprotein) and radiomic features were used to build the clinical model, clinical-radiomic (CR) nomogram, deep learning model. The follow-up process was done 1 month after resection, and every 3 months subsequently. The RFS was defined as the date of resection to the date of recurrence confirmed by radiology or the last follow-up. Patients were followed up until December 31, 2022.

STATISTICAL TESTS

Univariate COX regression, least absolute shrinkage and selection operator (LASSO), Kaplan-Meier curves, log-rank test, C-index, and area under the curve (AUC). P < 0.05 was considered statistically significant.

RESULTS

The C-index of deep learning model achieved 0.830 in test cohort compared with CR nomogram (0.731), radiomic signature (0.707), and clinical model (0.702). The average RFS of the overall patients was 26.77 months (range 1-80 months).

DATA CONCLUSION

MR deep learning model based on VETC and MVI provides a potential tool for survival assessment.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 3.

The potential of the transformer-based survival analysis model, SurvTrace, for predicting recurrent cardiovascular events and stratifying high-risk patients with ischemic heart disease

INTRODUCTION

Ischemic heart disease is a leading cause of death worldwide, and its importance is increasing with the aging population. The aim of this study was to evaluate the accuracy of SurvTrace, a survival analysis model using the Transformer-a state-of-the-art deep learning method-for predicting recurrent cardiovascular events and stratifying high-risk patients. The model's performance was compared to that of a conventional scoring system utilizing real-world data from cardiovascular patients.

METHODS

This study consecutively enrolled patients who underwent percutaneous coronary intervention (PCI) at the Department of Cardiovascular Medicine, University of Tokyo Hospital, between 2005 and 2019. Each patient's initial PCI at our hospital was designated as the index procedure, and a composite of major adverse cardiovascular events (MACE) was monitored for up to two years post-index event. Data regarding patient background, clinical presentation, medical history, medications, and perioperative complications were collected to predict MACE. The performance of two models-a conventional scoring system proposed by Wilson et al. and the Transformer-based model SurvTrace-was evaluated using Harrell's c-index, Kaplan-Meier curves, and log-rank tests.

RESULTS

A total of 3938 cases were included in the study, with 394 used as the test dataset and the remaining 3544 used for model training. SurvTrace exhibited a mean c-index of 0.72 (95% confidence intervals (CI): 0.69-0.76), which indicated higher prognostic accuracy compared with the conventional scoring system's 0.64 (95% CI: 0.64-0.64). Moreover, SurvTrace demonstrated superior risk stratification ability, effectively distinguishing between the high-risk group and other risk categories in terms of event occurrence. In contrast, the conventional system only showed a significant difference between the low-risk and high-risk groups.

CONCLUSION

This study based on real-world cardiovascular patient data underscores the potential of the Transformer-based survival analysis model, SurvTrace, for predicting recurrent cardiovascular events and stratifying high-risk patients.

SAGL: A self-attention-based graph learning framework for predicting survival of colorectal cancer patients

BACKGROUND AND OBJECTIVE

Colorectal cancer (CRC) is one of the most commonly diagnosed cancers worldwide. The accurate survival prediction for CRC patients plays a significant role in the formulation of treatment strategies. Recently, machine learning and deep learning approaches have been increasingly applied in cancer survival prediction. However, most existing methods inadequately represent and leverage the dependencies among features and fail to sufficiently mine and utilize the comorbidity patterns of CRC. To address these issues, we propose a self-attention-based graph learning (SAGL) framework to improve the postoperative cancer-specific survival prediction for CRC patients.

METHODS

We present a novel method for constructing dependency graph (DG) to reflect two types of dependencies including comorbidity-comorbidity dependencies and the dependencies between features related to patient characteristics and cancer treatments. This graph is subsequently refined by a disease comorbidity network, which offers a holistic view of comorbidity patterns of CRC. A DG-guided self-attention mechanism is proposed to unearth novel dependencies beyond what DG offers, thus augmenting CRC survival prediction. Finally, each patient will be represented, and these representations will be used for survival prediction.

RESULTS

The experimental results show that SAGL outperforms state-of-the-art methods on a real-world dataset, with the receiver operating characteristic curve for 3- and 5-year survival prediction achieving 0.849±0.002 and 0.895±0.005, respectively. In addition, the comparison results with different graph neural network-based variants demonstrate the advantages of our DG-guided self-attention graph learning framework.

CONCLUSIONS

Our study reveals that the potential of the DG-guided self-attention in optimizing feature graph learning which can improve the performance of CRC survival prediction.

Different lymph node staging systems for predicting the prognosis of colorectal neuroendocrine neoplasms

BACKGROUND

Colorectal neuroendocrine neoplasms (NENs) are a rare malignancy that primarily arises from the diffuse distribution of neuroendocrine cells in the colon and rectum. Previous studies have pointed out that the status of lymph node may be used to predict the prognosis.

AIM

To investigate the predictive values of lymph node ratio (LNR), positive lymph node (PLN), and log odds of PLNs (LODDS) staging systems on the prognosis of colorectal NENs treated surgically, and compare their predictive values.

METHODS

This cohort study included 895 patients with colorectal NENs treated surgically from the Surveillance, Epidemiology, and End Results database. The endpoint was mortality of patients with colorectal NENs treated surgically. X-tile software was utilized to identify most suitable thresholds for categorizing the LNR, PLN, and LODDS. Participants were selected in a random manner to form training and testing sets. The prognosis of surgically treating colorectal NENs was examined using multivariate cox analysis to assess the associations of LNR, PLN, and LODDS with the prognosis of colorectal NENs. C-index was used for assessing the predictive effectiveness. We conducted a subgroup analysis to explore the different lymph node staging systems' predictive values.

RESULTS

After adjusting all confounding factors, PLN, LNR and LODDS staging systems were linked with mortality in patients with colorectal NENs treated surgically (P < 0.05). We found that LODDS staging had a higher prognostic value for patients with colorectal NENs treated surgically than PLN and LNR staging systems. Similar results were obtained in the different G staging subgroup analyses. Furthermore, the area under the receiver operating characteristic curve values for LODDS staging system remained consistently higher than those of PLN or LNR, even at the 1-, 2-, 3-, 4-, 5- and 6-year follow-up periods.

CONCLUSION

LNR, PLN, and LODDS were found to significantly predict the prognosis of patients with colorectal NENs treated surgically.

Artificial intelligence-assisted ultrasound imaging in hemophilia: research, development, and evaluation of hemarthrosis and synovitis detection

Background

Joint bleeding can lead to synovitis and arthropathy in people with hemophilia, reducing quality of life. Although early diagnosis is associated with improved therapeutic outcomes, diagnostic ultrasonography requires specialist experience. Artificial intelligence (AI) algorithms may support ultrasonography diagnoses.

Objectives

This study will research, develop, and evaluate the diagnostic precision of an AI algorithm for detecting the presence or absence of hemarthrosis and synovitis in people with hemophilia.

Methods

Elbow, knee, and ankle ultrasound images were obtained from people with hemophilia from January 2010 to March 2022. The images were used to train and test the AI models to estimate the presence/absence of hemarthrosis and synovitis. The primary endpoint was the area under the curve for the diagnostic precision to diagnose hemarthrosis and synovitis. Other endpoints were the rate of accuracy, precision, sensitivity, and specificity.

Results

Out of 5649 images collected, 3435 were used for analysis. The area under the curve for hemarthrosis detection for the elbow, knee, and ankle joints was ≥0.87 and for synovitis, it was ≥0.90. The accuracy and precision for hemarthrosis detection were ≥0.74 and ≥0.67, respectively, and those for synovitis were ≥0.83 and ≥0.74, respectively. Analysis across people with hemophilia aged 10 to 60 years showed consistent results.

Conclusion

AI models have the potential to aid diagnosis and enable earlier therapeutic interventions, helping people with hemophilia achieve healthy and active lives. Although AI models show potential in diagnosis, evidence is unclear on required control for abnormal findings. Long-term observation is crucial for assessing impact on joint health.

New perspectives on cancer clinical research in the era of big data and machine learning

In the 21st century, the development of medical science has entered the era of big data, and machine learning has become an essential tool for mining medical big data. The establishment of the SEER database has provided a wealth of epidemiological data for cancer clinical research, and the number of studies based on SEER and machine learning has been growing in recent years. This article reviews recent research based on SEER and machine learning and finds that the current focus of such studies is primarily on the development and validation of models using machine learning algorithms, with the main directions being lymph node metastasis prediction, distant metastasis prediction, and prognosis-related research. Compared to traditional models, machine learning algorithms have the advantage of stronger adaptability, but also suffer from disadvantages such as overfitting and poor interpretability, which need to be weighed in practical applications. At present, machine learning algorithms, as the foundation of artificial intelligence, have just begun to emerge in the field of cancer clinical research. The future development of oncology will enter a more precise era of cancer research, characterized by larger data, higher dimensions, and more frequent information exchange. Machine learning is bound to shine brightly in this field.

Predicting cutaneous malignant melanoma patients' survival using deep learning: a retrospective cohort study

BACKGROUND

Cutaneous malignant melanoma (CMM) has the worst prognosis among skin cancers, especially metastatic CMM. Predicting its prognosis accurately could direct clinical decisions.

METHODS

The Surveillance, Epidemiology, and End Results database was screened to collect CMM patients' data. According to diagnosed time, patients were subdivided into three cohorts, train cohort (diagnosed between 2010 and 2013), validation cohort (diagnosed in 2014), and test cohort (diagnosed in 2015). Train cohort was used to train deep learning survival model for cutaneous malignant melanoma (DeepCMM). DeepCMM was then evaluated in train cohort and validation cohort internally, and validated in test cohort externally.

RESULTS

DeepCMM showed 0.8270 (95% CI, confidence interval, CI 0.8260-0.8280) as area under the receiver operating characteristic curve (AUC) in train cohort, 0.8274 (95% CI 0.8286-0.8298) AUC in validation cohort, and 0.8303 (95% CI 0.8289-0.8316) AUC in test cohort. Then DeepCMM was packaged into a Windows 64-bit software for doctors to use.

CONCLUSION

Deep learning survival model for cutaneous malignant melanoma (DeepCMM) can offer a reliable prediction on cutaneous malignant melanoma patients' overall survival.

Deep-learning-based survival prediction of patients with lower limb melanoma

BACKGROUND

For the purpose to examine lower limb melanoma (LLM) and its long-term survival rate, we used data from the Surveillance, Epidemiology and End Results (SEER) database. To estimate the prognosis of LLM patients and assess its efficacy, we used a powerful deep learning and neural network approach called DeepSurv.

METHODS

We gathered data on those who had an LLM diagnosis between 2000 and 2019 from the SEER database. We divided the people into training and testing cohorts at a 7:3 ratio using a random selection technique. To assess the likelihood that LLM patients would survive, we compared the results of the DeepSurv model with those of the Cox proportional-hazards (CoxPH) model. Calibration curves, the time-dependent area under the receiver operating characteristic curve (AUC), and the concordance index (C-index) were all used to assess how accurate the predictions were.

RESULTS

In this study, a total of 26,243 LLM patients were enrolled, with 7873 serving as the testing cohort and 18,370 as the training cohort. Significant correlations with age, gender, AJCC stage, chemotherapy status, surgery status, regional lymph node removal and the survival outcomes of LLM patients were found by the CoxPH model. The CoxPH model's C-index was 0.766, which signifies a good degree of predicted accuracy. Additionally, we created the DeepSurv model using the training cohort data, which had a higher C-index of 0.852. In addition to calculating the 3-, 5-, and 8-year AUC values, the predictive performance of both models was evaluated. The equivalent AUC values for the CoxPH model were 0.795, 0.767, and 0.847, respectively. The DeepSurv model, in comparison, had better AUC values of 0.872, 0.858, and 0.847. In comparison to the CoxPH model, the DeepSurv model demonstrated greater prediction performance for LLM patients, as shown by the AUC values and the calibration curve.

CONCLUSION

We created the DeepSurv model using LLM patient data from the SEER database, which performed better than the CoxPH model in predicting the survival time of LLM patients.

Application of machine learning in predicting survival outcomes involving real-world data: a scoping review

BACKGROUND

Despite the interest in machine learning (ML) algorithms for analyzing real-world data (RWD) in healthcare, the use of ML in predicting time-to-event data, a common scenario in clinical practice, is less explored. ML models are capable of algorithmically learning from large, complex datasets and can offer advantages in predicting time-to-event data. We reviewed the recent applications of ML for survival analysis using RWD in healthcare.

METHODS

PUBMED and EMBASE were searched from database inception through March 2023 to identify peer-reviewed English-language studies of ML models for predicting time-to-event outcomes using the RWD. Two reviewers extracted information on the data source, patient population, survival outcome, ML algorithms, and the Area Under the Curve (AUC).

RESULTS

Of 257 citations, 28 publications were included. Random survival forests (N = 16, 57%) and neural networks (N = 11, 39%) were the most popular ML algorithms. There was variability across AUC for these ML models (median 0.789, range 0.6-0.950). ML algorithms were predominately considered for predicting overall survival in oncology (N = 12, 43%). ML survival models were often used to predict disease prognosis or clinical events (N = 27, 96%) in the oncology, while less were used for treatment outcomes (N = 1, 4%).

CONCLUSIONS

The ML algorithms, random survival forests and neural networks, are mainly used for RWD to predict survival outcomes such as disease prognosis or clinical events in the oncology. This review shows that more opportunities remain to apply these ML algorithms to inform treatment decision-making in clinical practice. More methodological work is also needed to ensure the utility and applicability of ML models in survival outcomes.

A deep learning-based model (DeepMPM) to help predict survival in patients with malignant pleural mesothelioma

Background

Malignant pleural mesothelioma (MPM) is a rare disease with limited treatment and poor prognosis, and a precise and reliable means to predicting MPM remains lacking for clinical use.

Methods

In the population-based cohort study, we collected clinical characteristics from the Surveillance, Epidemiology, and End Results (SEER) database. According to the time of diagnosis, the SEER data were divided into 2 cohorts: the training cohort (from 2010 to 2016) and the test cohort (from 2017 to 2019). The training cohort was used to train a deep learning-based predictive model derived from DeepSurv theory, which was validated by both the training and the test cohorts. All clinical characteristics were included and analyzed using Cox proportional risk regression or Kaplan-Meier curve to determine the risk factors and protective factors of MPM.

Results

The survival model included 3,130 cases (2,208 in the training cohort and 922 in the test cohort). As for model's performance, the area under the receiver operating characteristics curve (AUC) was 0.7037 [95% confidence interval (CI): 0.7030-0.7045] in the training cohort and 0.7076 (95% CI: 0.7067-0.7086) in the test cohort. Older age; male sex, sarcomatoid mesothelioma; and T4, N2, and M1 stage tended to be the risk factors for survival. Meanwhile, epithelioid mesothelioma, surgery, radiotherapy, and chemotherapy tended to be the protective factors. The median overall survival (OS) of patients who underwent surgery combined with radiotherapy was the longest, followed by those who underwent a combination of surgery, radiotherapy, and chemotherapy.

Conclusions

Our deep learning-based model precisely could predict the survival of patients with MPM; moreover, multimode combination therapy might provide more meaningful survival benefits.

How to use the Surveillance, Epidemiology, and End Results (SEER) data: research design and methodology

In the United States (US), the Surveillance, Epidemiology, and End Results (SEER) program is the only comprehensive source of population-based information that includes stage of cancer at the time of diagnosis and patient survival data. This program aims to provide a database about cancer incidence and survival for studies of surveillance and the development of analytical and methodological tools in the cancer field. Currently, the SEER program covers approximately half of the total cancer patients in the US. A growing number of clinical studies have applied the SEER database in various aspects. However, the intrinsic features of the SEER database, such as the huge data volume and complexity of data types, have hindered its application. In this review, we provided a systematic overview of the commonly used methodologies and study designs for retrospective epidemiological research in order to illustrate the application of the SEER database. Therefore, the goal of this review is to assist researchers in the selection of appropriate methods and study designs for enhancing the robustness and reliability of clinical studies by mining the SEER database.

Artificial intelligence based system for predicting permanent stoma after sphincter saving operations

Although the goal of rectal cancer treatment is to restore gastrointestinal continuity, some patients with rectal cancer develop a permanent stoma (PS) after sphincter-saving operations. Although many studies have identified the risk factors and causes of PS, few have precisely predicted the probability of PS formation before surgery. To validate whether an artificial intelligence model can accurately predict PS formation in patients with rectal cancer after sphincter-saving operations. Patients with rectal cancer who underwent a sphincter-saving operation at Taipei Medical University Hospital between January 1, 2012, and December 31, 2021, were retrospectively included in this study. A machine learning technique was used to predict whether a PS would form after a sphincter-saving operation. We included 19 routinely available preoperative variables in the artificial intelligence analysis. To evaluate the efficiency of the model, 6 performance metrics were utilized: accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiving operating characteristic curve. In our classification pipeline, the data were randomly divided into a training set (80% of the data) and a validation set (20% of the data). The artificial intelligence models were trained using the training dataset, and their performance was evaluated using the validation dataset. Synthetic minority oversampling was used to solve the data imbalance. A total of 428 patients were included, and the PS rate was 13.6% (58/428) in the training set. The logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest, decision tree and light gradient boosting machine (LightGBM) algorithms were employed. The accuracies of the logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest (RF), decision tree (DT) and light gradient boosting machine (LightGBM) models were 70%, 76%, 89%, 93%, 95%, 79% and 93%, respectively. The area under the receiving operating characteristic curve values were 0.79 for the LR model, 0.84 for the GNB, 0.95 for the XGB, 0.95 for the GB, 0.99 for the RF model, 0.79 for the DT model and 0.98 for the LightGBM model. The key predictors that were identified were the distance of the lesion from the anal verge, clinical N stage, age, sex, American Society of Anesthesiologists score, and preoperative albumin and carcinoembryonic antigen levels. Integration of artificial intelligence with available preoperative data can potentially predict stoma outcomes after sphincter-saving operations. Our model exhibited excellent predictive ability and can improve the process of obtaining informed consent.

Development and validation of a competitive risk model in patients with rectal cancer: based on SEER database

BACKGROUND

Rectal cancer is one of the most common malignancies. To predict the specific mortality risk of rectal cancer patients, we constructed a predictive nomogram based on a competing risk model.

METHODS

The information on rectal cancer patients was extracted from the SEER database. Traditional survival analysis and specific death analysis were performed separately on the data.

RESULTS

The present study included 23,680 patients, with 16,580 in the training set and 7100 in the validation set. The specific mortality rate calculated by the competing risk model was lower than that of the traditional survival analysis. Age, Marriage, Race, Sex, ICD-O-3Hist/Behav, Grade, AJCC stage, T stage, N stage, Surgery, Examined LN, RX SUMM-SURG OTH, Chemotherapy, CEA, Deposits, Regional nodes positive, Brain, Bone, Liver, Lung, Tumor size, and Malignant were independent influencing factors of specific death. The overall C statistic of the model in the training set was 0.821 (Se = 0.001), and the areas under the ROC curve for cancer-specific survival (CSS) at 1, 3, and 5 years were 0.842, 0.830, and 0.812, respectively. The overall C statistic of the model in the validation set was 0.829 (Se = 0.002), and the areas under the ROC curve for CSS at 1, 3, and 5 years were 0.851, 0.836, and 0.813, respectively.

CONCLUSIONS

The predictive nomogram based on a competing risk model for time-specific mortality in patients with rectal cancer has very desirable accuracy. Thus, the application of the predictive nomogram in clinical practice can help physicians make clinical decisions and follow-up strategies.

Broad Trends in Public Health and Epidemiology Informatics

OBJECTIVES

The objective of this study is to highlight innovative research and contemporary trends in the area of Public Health and Epidemiology Informatics (PHEI).

METHODS

Following a similar approach to last year's edition, a meticulous search was conducted on PubMed (with keywords including topics related to Public Health, Epidemiological Surveillance and Medical Informatics), examining a total of 2,022 scientific publications on Public Health and Epidemiology Informatics (PHEI). The resulting references were thoroughly examined by the three section editors. Subsequently, 10 papers were chosen as potential candidates for the best paper award. These selected papers were then subjected to peer-review by six external reviewers, in addition to the section editors and two chief editors of the IMIA yearbook of medical informatics. Each paper underwent a total of five reviews.

RESULTS

Out of the 539 references retrieved from PubMed, only two were deemed worthy of the best paper award, although four papers had the potential to qualify in total. The first best paper by pertains to a study about the need for a new annotation framework due to inadequacies in existing methods and resources. The second paper elucidates the use of Weibo data to monitor the health of Chinese urbanites. The correlation between air pollution and health sensing was measured via generalized additive models.

CONCLUSIONS

One of the primary findings of this edition is the dearth of studies identified for the PHEI section, which represents a significant decline compared to the previous edition. This is particularly surprising given that the post-COVID period should have led to an increased use of information and communication technology for public health issues.

The role of deep learning in diagnosing colorectal cancer

Colon cancer is a major public health issue, affecting a growing number of individuals worldwide. Proper and early diagnosis of colon cancer is the necessary first step toward effective treatment and/or prevention of future disease relapse. Artificial intelligence and its subtypes, deep learning in particular, tend nowadays to have an expanding role in all fields of medicine, and diagnosing colon cancer is no exception. This report aims to summarize the entire application spectrum of deep learning in all diagnostic tests regarding colon cancer, from endoscopy and histologic examination to medical imaging and screening serologic tests.

Predicting the survival of patients with pancreatic neuroendocrine neoplasms using deep learning: A study based on Surveillance, Epidemiology, and End Results database

BACKGROUND

The study aims to evaluate the performance of three advanced machine learning algorithms and a traditional Cox proportional hazard (CoxPH) model in predicting the overall survival (OS) of patients with pancreatic neuroendocrine neoplasms (PNENs).

METHOD

The clinicopathological dataset obtained from the Surveillance, Epidemiology, and End Results database was randomly assigned to the training set and testing set at a ratio of 7:3. The concordance index (C-index) and integrated Brier score (IBS) were used to compare the predictive performance of the models. The accuracy of the model in predicting the 5-year and 10-year survival rates was compared using the receiver operating characteristic curve, decision curve analysis (DCA) and calibration curve.

RESULTS

This study included 3239 patients with PNENs in total. The DeepSurv model had the highest C-index of 0.7882 in the testing set and training set and the lowest IBS of 0.1278 in the testing set compared with the CoxPH, neural multitask logistic and random survival forest models (C-index = 0.7501, 0.7616, and 0.7612, respectively; IBS = 0.1397, 0.1418, and 0.1432, respectively). Moreover, the DeepSurv model had the highest accuracy in predicting 5- and 10-year OS rates (area under the curve: 0.87 and 0.90). DCA showed that the DeepSurv model had high potential for clinical decisions in 5- and 10-year OS models. Finally, we developed an online application based on the DeepSurv model for clinical use (https://whuh-ml-neuroendocrinetumor-app-predict-oyw5km.streamlit.app/).

CONCLUSIONS

All four models analyzed above can predict the prognosis of PNENs well, among which the DeepSurv model has the best prediction performance.

A novel staging system based on deep learning for overall survival in patients with esophageal squamous cell carcinoma

PURPOSE

We developed DeepSurv, a deep learning approach for predicting overall survival (OS) in patients with esophageal squamous cell carcinoma (ESCC). We validated and visualized the novel staging system based on DeepSurv using data from multiple cohorts.

METHODS

Totally 6020 ESCC patients diagnosed from January 2010 to December 2018 were included in the present study from the Surveillance, Epidemiology, and End Results database (SEER), randomly assigned to the training and test cohorts. We developed, validated and visualized a deep learning model that included 16 prognostic factors; then a novel staging system was further constructed based on the total risk score derived from the deep learning model. The classification performance at 3-year and 5-year OS was assessed by the receiver-operating characteristic (ROC) curve. Calibration curve and the Harrell's concordance index (C-index) were also used to comprehensively assess the predictive performance of the deep learning model. Decision curve analysis (DCA) was utilized to assess the clinical utility of the novel staging system.

RESULTS

A more applicable and accurate deep learning model was established, which outperformed the traditional nomogram in predicting OS in the test cohort (C-index: 0.732 [95% CI 0.714-0.750] versus 0.671 [95% CI 0.647-0.695]). The ROC curves at 3-year and 5-year OS for the model also showed good discrimination ability in the test cohort (Area Under the Curve [AUC] at 3-/5-year OS = 0.805/0.825). Moreover, using our novel staging system, we observed a clear survival difference among different risk groups (P < 0.001) and a significant positive net benefit in the DCA.

CONCLUSIONS

A novel deep learning-based staging system was constructed for patients with ESCC, which performed a significant discriminability for survival probability. Moreover, an easy-to-use web-based tool based on the deep learning model was also implemented, offering convenience for personalized survival prediction. We developed a deep learning-based system that stages patients with ESCC according to their survival probability. We also created a web-based tool that uses this system to predict individual survival outcomes.

Deep-learning-based survival prediction of patients with cutaneous malignant melanoma

Background

This study obtained data on patients with cutaneous malignant melanoma (CMM) from the Surveillance, Epidemiology, and End Results (SEER) database, and used a deep learning and neural network (DeepSurv) model to predict the survival rate of patients with CMM and evaluate its effectiveness.

Methods

We collected information on patients with CMM between 2004 and 2015 from the SEER database. We then randomly divided the patients into training and testing cohorts at a 7:3 ratio. The likelihood that patients with CMM will survive was forecasted using the DeepSurv model, and its results were compared with those of the Cox proportional-hazards (CoxPH) model. The calibration curves, time-dependent area under the receiver operating characteristic curve (AUC), and concordance index (C-index) were used to assess the prediction abilities of the model.

Results

This study comprised 37,758 patients with CMM: 26,430 in the training cohort and 11,329 in the testing cohort. The CoxPH model demonstrated that the survival of patients with CMM was significantly influenced by age, sex, marital status, summary stage, surgery, radiotherapy, chemotherapy, postoperative lymph node dissection, tumor size, and tumor extension. The C-index of the CoxPH model was 0.875. We also constructed the DeepSurv model using the data from the training cohort, and its C-index was 0.910. We examined how well the aforementioned two models predicted outcomes. The 1-, 3-, and 5-year AUCs were 0.928, 0.837, and 0.855, respectively, for the CoxPH model, and 0.971, 0.947, and 0.942 for the DeepSurv model. The DeepSurv model presented a greater predictive effect on patients with CMM, and its reliability was better than that of the CoxPH model according to both the AUC value and the calibration curve.

Conclusion

The DeepSurv model, which we developed based on the data of patients with CMM in the SEER database, was found to be more effective than the CoxPH model in predicting the survival time of patients with CMM.

Integrated Machine Learning Decision Tree Model for Risk Evaluation in Patients with Non-Valvular Atrial Fibrillation When Taking Different Doses of Dabigatran

The new generation of nonvitamin K antagonists are broadly applied for stroke prevention due to their notable efficacy and safety. Our study aimed to develop a suggestive utilization of dabigatran through an integrated machine learning (ML) decision-tree model. Participants taking different doses of dabigatran in the Randomized Evaluation of Long-Term Anticoagulant Therapy trial were included in our analysis and defined as the 110 mg and 150 mg groups. The proposed scheme integrated ML methods, namely naive Bayes, random forest (RF), classification and regression tree (CART), and extreme gradient boosting (XGBoost), which were used to identify the essential variables for predicting vascular events in the 110 mg group and bleeding in the 150 mg group. RF (0.764 for 110 mg; 0.747 for 150 mg) and XGBoost (0.708 for 110 mg; 0.761 for 150 mg) had better area under the receiver operating characteristic curve (AUC) values than logistic regression (benchmark model; 0.683 for 110 mg; 0.739 for 150 mg). We then selected the top ten important variables as internal nodes of the CART decision tree. The two best CART models with ten important variables output tree-shaped rules for predicting vascular events in the 110 mg group and bleeding in the 150 mg group. Our model can be used to provide more visualized and interpretable suggestive rules to clinicians managing NVAF patients who are taking dabigatran.

Deep learning survival model for colorectal cancer patients (DeepCRC) with Asian clinical data compared with different theories

INTRODUCTION

Colorectal cancer (CRC) is the third most common cancer. Precise prediction of CRC patients' overall survival (OS) probability could offer advice on its treatment. Neural network (NN) is the first-class algorithm, but a consensus on which NN survival models are better has not been established yet. A predictive model on CRC using Asian data is also lacking.

METHODS

We conducted 8 NN survival models of CRC (n = 416) with different theories and compared them using Asian data.

RESULTS

DeepSurv performed best with a C-index value of 0.8300 in the training cohort and 0.7681 in the test cohort.

CONCLUSIONS

The deep learning survival model for CRC patients (DeepCRC) could predict CRC's OS accurately.

Machine learning models for predicting survival in patients with ampullary adenocarcinoma

Objective

The aim of this study was to predict the long-term survival probability of patients with ampullary adenocarcinoma (AAC), which would provide a theoretical basis for the long-term care of these patients.

Methods

Data on patients with AAC during 2004–2015 were obtained from the Surveillance, Epidemiology, and End Results database, which were split at a 7:3 ratio into two independent cohorts: training and testing cohorts. Differences in survival between the two groups were tested using the Kaplan–Meier estimator and log-rank test methods. We constructed six survival analysis methods: the American Joint Committee on Cancer TNM stage, Cox Proportional Hazards regression, CoxTime, DeepSurv, XGBoost Survival Embeddings, and Random Survival Forest. The performances of these models were evaluated using the C-index, receiver operating characteristic (ROC), and calibration curves.

Results

This study included 2,935 patients with AAC. Univariate Cox regression analyses of the training cohort indicated that race, marital status at diagnosis, scope of regional lymph node surgery, tumor grade, summary stage, American Joint Committee on Cancer stage, TNM stage T, and TNM stage N were important factors affecting survival (P ​< ​0.05). The results of the C-index indicated that DeepSurv performed the best among the six models, with the highest C-index of 0.731. The areas under the ROC curves of the DeepSurv model at the 1-year, 3-year, 5-year, and 10-year time points were 0.823, 0.786, 0.803, and 0.813, respectively. The calibration curve indicated that DeepSurv performed well, with good calibration.

Conclusions

Machine learning models such as DeepSurv have a stronger performance in the survival analysis of patients with AAC.