Survival prediction models since liver transplantation - comparisons between Cox models and machine learning techniques

Computer-Aided Diagnosis of Complications After Liver Transplantation Based on Transfer Learning

Liver transplantation is one of the most effective treatments for acute liver failure, cirrhosis, and even liver cancer. The prediction of postoperative complications is of great significance for liver transplantation. However, the existing prediction methods based on traditional machine learning are often unavailable or unreliable due to the insufficient amount of real liver transplantation data. Therefore, we propose a new framework to increase the accuracy of computer-aided diagnosis of complications after liver transplantation with transfer learning, which can handle small-scale but high-dimensional data problems. Furthermore, since data samples are often high dimensional in the real world, capturing key features that influence postoperative complications can help make the correct diagnosis for patients. So, we also introduce the SHapley Additive exPlanation (SHAP) method into our framework for exploring the key features of postoperative complications. We used data obtained from 425 patients with 456 features in our experiments. Experimental results show that our approach outperforms all compared baseline methods in predicting postoperative complications. In our work, the average precision, the mean recall, and the mean F1 score reach 91.22%, 91.70%, and 91.18%, respectively.

Artificial Intelligence in Liver Diseases: Recent Advances

Liver diseases cause a significant burden on public health worldwide. In spite of great advances during recent years, there are still many challenges in the diagnosis and treatment of liver diseases. During recent years, artificial intelligence (AI) has been widely used for the diagnosis, risk stratification, and prognostic prediction of various diseases based on clinical datasets and medical images. Accumulative studies have shown its performance for diagnosing patients with nonalcoholic fatty liver disease and liver fibrosis and assessing their severity, and for predicting treatment response and recurrence of hepatocellular carcinoma, outcomes of liver transplantation recipients, and risk of drug-induced liver injury. Herein, we aim to comprehensively summarize the current evidence regarding diagnostic, prognostic, and/or therapeutic role of AI in these common liver diseases.

Influence of donor age on liver transplantation outcomes: A multivariate analysis and comparative study

BACKGROUND

The growing disparity between the rising demand for liver transplantation (LT) and the limited availability of donor organs has prompted a greater reliance on older liver grafts. Traditionally, utilizing livers from elderly donors has been associated with outcomes inferior to those achieved with grafts from younger donors. By accounting for additional risk factors, we hypothesize that the utilization of older liver grafts has a relatively minor impact on both patient survival and graft viability.

AIM

To evaluate the impact of donor age on LT outcomes using multivariate analysis and comparing young and elderly donor groups.

METHODS

In the period from April 2013 to December 2018, 656 adult liver transplants were performed at the University Hospital Merkur. Several multivariate Cox proportional hazards models were developed to independently assess the significance of donor age. Donor age was treated as a continuous variable. The approach involved univariate and multivariate analysis, including variable selection and assessment of interactions and transformations. Additionally, to exemplify the similarity of using young and old donor liver grafts, the group of 87 recipients of elderly donor liver grafts (≥ 75 years) was compared to a group of 124 recipients of young liver grafts (≤ 45 years) from the dataset. Survival rates of the two groups were estimated using the Kaplan-Meier method and the log-rank test was used to test the differences between groups.

RESULTS

Using multivariate Cox analysis, we found no statistical significance in the role of donor age within the constructed models. Even when retained during the entire model development, the donor age's impact on survival remained insignificant and transformations and interactions yielded no substantial effects on survival. Consistent insignificance and low coefficient values suggest that donor age does not impact patient survival in our dataset. Notably, there was no statistical evidence that the five developed models did not adhere to the proportional hazards assumption. When comparing donor age groups, transplantation using elderly grafts showed similar early graft function, similar graft (P = 0.92), and patient survival rates (P = 0.86), and no significant difference in the incidence of postoperative complications.

CONCLUSION

Our center's experience indicates that donor age does not play a significant role in patient survival, with elderly livers performing comparably to younger grafts when accounting for other risk factors.

A transformer-based deep learning approach for fairly predicting post-liver transplant risk factors

Liver transplantation is a life-saving procedure for patients with end-stage liver disease. There are two main challenges in liver transplant: finding the best matching patient for a donor and ensuring transplant equity among different subpopulations. The current MELD scoring system evaluates a patient's mortality risk if not receiving an organ within 90 days. However, the donor-patient matching should also consider post-transplant risk factors, such as cardiovascular disease, chronic rejection, etc., which are all common complications after transplant. Accurate prediction of these risk scores remains a significant challenge. In this study, we used predictive models to solve the above challenges. Specifically, we proposed a deep learning model to predict multiple risk factors after a liver transplant. By formulating it as a multi-task learning problem, the proposed deep neural network was trained to simultaneously predict the five post-transplant risks and achieve equal good performance by exploiting task-balancing techniques. We also proposed a novel fairness-achieving algorithm to ensure prediction fairness across different subpopulations. We used electronic health records of 160,360 liver transplant patients, including demographic information, clinical variables, and laboratory values, collected from the liver transplant records of the United States from 1987 to 2018. The model's performance was evaluated using various performance metrics such as AUROC and AUPRC. Our experiment results highlighted the success of our multi-task model in achieving task balance while maintaining accuracy. The model significantly reduced the task discrepancy by 39 %. Further application of the fairness-achieving algorithm substantially reduced fairness disparity among all sensitive attributes (gender, age group, and race/ethnicity) in each risk factor. It underlined the potency of integrating fairness considerations into the task-balancing framework, ensuring robust and fair predictions across multiple tasks and diverse demographic groups.

Development of a model to predict the risk of early graft failure after adult-to-adult living donor liver transplantation: An ELTR study

Graft survival is a critical end point in adult-to-adult living donor liver transplantation (ALDLT), where graft procurement endangers the lives of healthy individuals. Therefore, ALDLT must be responsibly performed in the perspective of a positive harm-to-benefit ratio. This study aimed to develop a risk prediction model for early (3 months) graft failure (EGF) following ALDLT. Donor and recipient factors associated with EGF in ALDLT were studied using data from the European Liver Transplant Registry. An artificial neural network classification algorithm was trained on a set of 2073 ALDLTs, validated using cross-validation, tested on an independent random-split sample (n=518), and externally validated on United Network for Organ Sharing Standard Transplant Analysis and Research data. Model performance was assessed using the AUC, calibration plots, and decision curve analysis. Graft type, graft weight, level of hospitalization, and the severity of liver disease were associated with EGF. The model ( http://ldlt.shinyapps.io/eltr_app ) presented AUC values at cross-validation, in the independent test set, and at external validation of 0.69, 0.70, and 0.68, respectively. Model calibration was fair. The decision curve analysis indicated a positive net benefit of the model, with an estimated net reduction of 5-15 EGF per 100 ALDLTs. Estimated risks>40% and<5% had a specificity of 0.96 and sensitivity of 0.99 in predicting and excluding EGF, respectively. The model also stratified long-term graft survival ( p <0.001), which ranged from 87% in the low-risk group to 60% in the high-risk group. In conclusion, based on a panel of donor and recipient variables, an artificial neural network can contribute to decision-making in ALDLT by predicting EGF risk.

Artificial intelligence, machine learning, and deep learning in liver transplantation

Liver transplantation (LT) is a life-saving treatment for individuals with end-stage liver disease. The management of LT recipients is complex, predominantly because of the need to consider demographic, clinical, laboratory, pathology, imaging, and omics data in the development of an appropriate treatment plan. Current methods to collate clinical information are susceptible to some degree of subjectivity; thus, clinical decision-making in LT could benefit from the data-driven approach offered by artificial intelligence (AI). Machine learning and deep learning could be applied in both the pre- and post-LT settings. Some examples of AI applications pre-transplant include optimising transplant candidacy decision-making and donor-recipient matching to reduce waitlist mortality and improve post-transplant outcomes. In the post-LT setting, AI could help guide the management of LT recipients, particularly by predicting patient and graft survival, along with identifying risk factors for disease recurrence and other associated complications. Although AI shows promise in medicine, there are limitations to its clinical deployment which include dataset imbalances for model training, data privacy issues, and a lack of available research practices to benchmark model performance in the real world. Overall, AI tools have the potential to enhance personalised clinical decision-making, especially in the context of liver transplant medicine.

Statistical models versus machine learning for competing risks: development and validation of prognostic models

BACKGROUND

In health research, several chronic diseases are susceptible to competing risks (CRs). Initially, statistical models (SM) were developed to estimate the cumulative incidence of an event in the presence of CRs. As recently there is a growing interest in applying machine learning (ML) for clinical prediction, these techniques have also been extended to model CRs but literature is limited. Here, our aim is to investigate the potential role of ML versus SM for CRs within non-complex data (small/medium sample size, low dimensional setting).

METHODS

A dataset with 3826 retrospectively collected patients with extremity soft-tissue sarcoma (eSTS) and nine predictors is used to evaluate model-predictive performance in terms of discrimination and calibration. Two SM (cause-specific Cox, Fine-Gray) and three ML techniques are compared for CRs in a simple clinical setting. ML models include an original partial logistic artificial neural network for CRs (PLANNCR original), a PLANNCR with novel specifications in terms of architecture (PLANNCR extended), and a random survival forest for CRs (RSFCR). The clinical endpoint is the time in years between surgery and disease progression (event of interest) or death (competing event). Time points of interest are 2, 5, and 10 years.

RESULTS

Based on the original eSTS data, 100 bootstrapped training datasets are drawn. Performance of the final models is assessed on validation data (left out samples) by employing as measures the Brier score and the Area Under the Curve (AUC) with CRs. Miscalibration (absolute accuracy error) is also estimated. Results show that the ML models are able to reach a comparable performance versus the SM at 2, 5, and 10 years regarding both Brier score and AUC (95% confidence intervals overlapped). However, the SM are frequently better calibrated.

CONCLUSIONS

Overall, ML techniques are less practical as they require substantial implementation time (data preprocessing, hyperparameter tuning, computational intensity), whereas regression methods can perform well without the additional workload of model training. As such, for non-complex real life survival data, these techniques should only be applied complementary to SM as exploratory tools of model's performance. More attention to model calibration is urgently needed.

A comparison of machine learning models and Cox proportional hazards models regarding their ability to predict the risk of gastrointestinal cancer based on metabolic syndrome and its components

Background

Little is known about applying machine learning (ML) techniques to identify the important variables contributing to the occurrence of gastrointestinal (GI) cancer in epidemiological studies. We aimed to compare different ML models to a Cox proportional hazards (CPH) model regarding their ability to predict the risk of GI cancer based on metabolic syndrome (MetS) and its components.

Methods

A total of 41,837 participants were included in a prospective cohort study. Incident cancer cases were identified by following up with participants until December 2019. We used CPH, random survival forest (RSF), survival trees (ST), gradient boosting (GB), survival support vector machine (SSVM), and extra survival trees (EST) models to explore the impact of MetS on GI cancer prediction. We used the C-index and integrated Brier score (IBS) to compare the models.

Results

In all, 540 incident GI cancer cases were identified. The GB and SSVM models exhibited comparable performance to the CPH model concerning the C-index (0.725). We also recorded a similar IBS for all models (0.017). Fasting glucose and waist circumference were considered important predictors.

Conclusions

Our study found comparably good performance concerning the C-index for the ML models and CPH model. This finding suggests that ML models may be considered another method for survival analysis when the CPH model's conditions are not satisfied.

Developing an Improved Survival Prediction Model for Disease Prognosis

Machine learning has become an important research field in genetics and molecular biology. Survival analysis using machine learning can provide an important computed-aid clinical research scheme for evaluating tumor treatment options. However, the genomic features are high-dimensional, which limits the prediction performance of the survival learning model. Therefore, in this paper, we propose an improved survival prediction model using a deep forest and self-supervised learning. It uses a deep survival forest to perform adaptive learning of high-dimensional genomic data and ensure robustness. In addition, self-supervised learning, as a semi-supervised learning style, is designed to utilize unlabeled samples to improve model performance. Based on four cancer datasets from The Cancer Genome Atlas (TCGA), the experimental results show that our proposed method outperforms four advanced survival analysis methods in terms of the C-index and brier score. The developed prediction model will help doctors rethink patient characteristics' relevance to survival time and personalize treatment decisions.

Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods

Air pollution exposure has been linked to various diseases, including dementia. However, a novel method for investigating the associations between air pollution exposure and disease is lacking. The objective of this study was to investigate whether long-term exposure to ambient particulate air pollution increases dementia risk using both the traditional Cox model approach and a novel machine learning (ML) with random forest (RF) method. We used health data from a national population-based cohort in Taiwan from 2000 to 2017. We collected the following ambient air pollution data from the Taiwan Environmental Protection Administration (EPA): fine particulate matter (PM_2.5) and gaseous pollutants, including sulfur dioxide (SO₂), carbon monoxide (CO), ozone (O₃), nitrogen oxide (NO_x), nitric oxide (NO), and nitrogen dioxide (NO₂). Spatiotemporal-estimated air quality data calculated based on a geostatistical approach, namely, the Bayesian maximum entropy method, were collected. Each subject's residential county and township were reviewed monthly and linked to air quality data based on the corresponding township and month of the year for each subject. The Cox model approach and the ML with RF method were used. Increasing the concentration of PM_2.5 by one interquartile range (IQR) increased the risk of dementia by approximately 5% (HR = 1.05 with 95% CI = 1.04-1.05). The comparison of the performance of the extended Cox model approach with the RF method showed that the prediction accuracy was approximately 0.7 by the RF method, but the AUC was lower than that of the Cox model approach. This national cohort study over an 18-year period provides supporting evidence that long-term particulate air pollution exposure is associated with increased dementia risk in Taiwan. The ML with RF method appears to be an acceptable approach for exploring associations between air pollutant exposure and disease.

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.

Avoiding C-hacking when evaluating survival distribution predictions with discrimination measures

MOTIVATION

In this article, we consider how to evaluate survival distribution predictions with measures of discrimination. This is non-trivial as discrimination measures are the most commonly used in survival analysis and yet there is no clear method to derive a risk prediction from a distribution prediction. We survey methods proposed in literature and software and consider their respective advantages and disadvantages.

RESULTS

Whilst distributions are frequently evaluated by discrimination measures, we find that the method for doing so is rarely described in the literature and often leads to unfair comparisons or 'C-hacking'. We demonstrate by example how simple it can be to manipulate results and use this to argue for better reporting guidelines and transparency in the literature. We recommend that machine learning survival analysis software implements clear transformations between distribution and risk predictions in order to allow more transparent and accessible model evaluation.

AVAILABILITY AND IMPLEMENTATION

The code used in the final experiment is available at https://github.com/RaphaelS1/distribution_discrimination.

Artificial Intelligence: Present and Future Potential for Solid Organ Transplantation

Artificial intelligence (AI) refers to computer algorithms used to complete tasks that usually require human intelligence. Typical examples include complex decision-making and- image or speech analysis. AI application in healthcare is rapidly evolving and it undoubtedly holds an enormous potential for the field of solid organ transplantation. In this review, we provide an overview of AI-based approaches in solid organ transplantation. Particularly, we identified four key areas of transplantation which could be facilitated by AI: organ allocation and donor-recipient pairing, transplant oncology, real-time immunosuppression regimes, and precision transplant pathology. The potential implementations are vast—from improved allocation algorithms, smart donor-recipient matching and dynamic adaptation of immunosuppression to automated analysis of transplant pathology. We are convinced that we are at the beginning of a new digital era in transplantation, and that AI has the potential to improve graft and patient survival. This manuscript provides a glimpse into how AI innovations could shape an exciting future for the transplantation community.

A scoping methodological review of simulation studies comparing statistical and machine learning approaches to risk prediction for time-to-event data

BACKGROUND

There is substantial interest in the adaptation and application of so-called machine learning approaches to prognostic modelling of censored time-to-event data. These methods must be compared and evaluated against existing methods in a variety of scenarios to determine their predictive performance. A scoping review of how machine learning methods have been compared to traditional survival models is important to identify the comparisons that have been made and issues where they are lacking, biased towards one approach or misleading.

METHODS

We conducted a scoping review of research articles published between 1 January 2000 and 2 December 2020 using PubMed. Eligible articles were those that used simulation studies to compare statistical and machine learning methods for risk prediction with a time-to-event outcome in a medical/healthcare setting. We focus on data-generating mechanisms (DGMs), the methods that have been compared, the estimands of the simulation studies, and the performance measures used to evaluate them.

RESULTS

A total of ten articles were identified as eligible for the review. Six of the articles evaluated a method that was developed by the authors, four of which were machine learning methods, and the results almost always stated that this developed method's performance was equivalent to or better than the other methods compared. Comparisons were often biased towards the novel approach, with the majority only comparing against a basic Cox proportional hazards model, and in scenarios where it is clear it would not perform well. In many of the articles reviewed, key information was unclear, such as the number of simulation repetitions and how performance measures were calculated.

CONCLUSION

It is vital that method comparisons are unbiased and comprehensive, and this should be the goal even if realising it is difficult. Fully assessing how newly developed methods perform and how they compare to a variety of traditional statistical methods for prognostic modelling is imperative as these methods are already being applied in clinical contexts. Evaluations of the performance and usefulness of recently developed methods for risk prediction should be continued and reporting standards improved as these methods become increasingly popular.

Switched alternative splicing events as attractive features in lung squamous cell carcinoma

Background

Alternative splicing (AS) plays important roles in transcriptome and proteome diversity. Its dysregulation has a close affiliation with oncogenic processes. This study aimed to evaluate AS-based biomarkers by machine learning algorithms for lung squamous cell carcinoma (LUSC) patients.

Method

The Cancer Genome Atlas (TCGA) database and TCGA SpliceSeq database were utilized. After data composition balancing, Boruta feature selection and Spearman correlation analysis were used for differentially expressed AS events. Random forests and a nested fivefold cross-validation were applied for lymph node metastasis (LNM) classifier building. Random survival forest combined with Cox regression model was performed for a prognostic model, based on which a nomogram was developed. Functional enrichment analysis and Spearman correlation analysis were also conducted to explore underlying mechanisms. The expression of some switch-involved AS events along with parent genes was verified by qRT-PCR with 20 pairs of normal and LUSC tissues.

Results

We found 16 pairs of splicing events from same parent genes which were strongly related to the splicing switch (intrapair correlation coefficient = − 1). Next, we built a reliable LNM classifier based on 13 AS events as well as a nice prognostic model, in which switched AS events behaved prominently. The qRT-PCR presented consistent results with previous bioinformatics analysis, and some AS events like ITIH5-10715-AT and QKI-78404-AT showed remarkable detection efficiency for LUSC.

Conclusion

AS events, especially switched ones from the same parent genes, could provide new insights into the molecular diagnosis and therapeutic drug design of LUSC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12935-021-02429-2.

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.

Machine Learning Applications in Solid Organ Transplantation and Related Complications

The complexity of transplant medicine pushes the boundaries of innate, human reasoning. From networks of immune modulators to dynamic pharmacokinetics to variable postoperative graft survival to equitable allocation of scarce organs, machine learning promises to inform clinical decision making by deciphering prodigious amounts of available data. This paper reviews current research describing how algorithms have the potential to augment clinical practice in solid organ transplantation. We provide a general introduction to different machine learning techniques, describing their strengths, limitations, and barriers to clinical implementation. We summarize emerging evidence that recent advances that allow machine learning algorithms to predict acute post-surgical and long-term outcomes, classify biopsy and radiographic data, augment pharmacologic decision making, and accurately represent the complexity of host immune response. Yet, many of these applications exist in pre-clinical form only, supported primarily by evidence of single-center, retrospective studies. Prospective investigation of these technologies has the potential to unlock the potential of machine learning to augment solid organ transplantation clinical care and health care delivery systems.

Two-Stage Approaches to Accounting for Patient Heterogeneity in Machine Learning Risk Prediction Models in Oncology

PURPOSE

Machine learning models developed from electronic health records data have been increasingly used to predict risk of mortality for general oncology patients. But these models may have suboptimal performance because of patient heterogeneity. The objective of this work is to develop a new modeling approach to predicting short-term mortality that accounts for heterogeneity across multiple subgroups in the presence of a large number of electronic health record predictors.

METHODS

We proposed a two-stage approach to addressing heterogeneity among oncology patients of different cancer types for predicting their risk of mortality. Structured data were extracted from the University of Pennsylvania Health System for 20,723 patients of 11 cancer types, where 1,340 (6.5%) patients were deceased. We first modeled the overall risk for all patients without differentiating cancer types, as is done in the current practice. We then developed cancer type-specific models using the overall risk score as a predictor along with preselected type-specific predictors. The overall and type-specific models were compared with respect to discrimination using the area under the precision-recall curve (AUPRC) and calibration using the calibration slope. We also proposed metrics that characterize the degree of risk heterogeneity by comparing risk predictors in the overall and type-specific models.

RESULTS

The two-stage modeling resulted in improved calibration and discrimination across all 11 cancer types. The improvement in AUPRC was significant for hematologic malignancies including leukemia, lymphoma, and myeloma. For instance, the AUPRC increased from 0.358 to 0.519 (∆ = 0.161; 95% CI, 0.102 to 0.224) and from 0.299 to 0.354 (∆ = 0.055; 95% CI, 0.009 to 0.107) for leukemia and lymphoma, respectively. For all 11 cancer types, the two-stage approach generated well-calibrated risks. A high degree of heterogeneity between type-specific and overall risk predictors was observed for most cancer types.

CONCLUSION

Our two-stage modeling approach that accounts for cancer type-specific risk heterogeneity has improved calibration and discrimination than a model agnostic to cancer types.

iCOVID: interpretable deep learning framework for early recovery-time prediction of COVID-19 patients

Most prior studies focused on developing models for the severity or mortality prediction of COVID-19 patients. However, effective models for recovery-time prediction are still lacking. Here, we present a deep learning solution named iCOVID that can successfully predict the recovery-time of COVID-19 patients based on predefined treatment schemes and heterogeneous multimodal patient information collected within 48 hours after admission. Meanwhile, an interpretable mechanism termed FSR is integrated into iCOVID to reveal the features greatly affecting the prediction of each patient. Data from a total of 3008 patients were collected from three hospitals in Wuhan, China, for large-scale verification. The experiments demonstrate that iCOVID can achieve a time-dependent concordance index of 74.9% (95% CI: 73.6-76.3%) and an average day error of 4.4 days (95% CI: 4.2-4.6 days). Our study reveals that treatment schemes, age, symptoms, comorbidities, and biomarkers are highly related to recovery-time predictions.

Estimating the predictive power of silent mutations on cancer classification and prognosis

In recent years it has been shown that silent mutations, in and out of the coding region, can affect gene expression and may be related to tumorigenesis and cancer cell fitness. However, the predictive ability of these mutations for cancer type diagnosis and prognosis has not been evaluated yet. In the current study, based on the analysis of 9,915 cancer genomes and approximately three million mutations, we provide a comprehensive quantitative evaluation of the predictive power of various types of silent and non-silent mutations over cancer classification and prognosis. The results indicate that silent-mutation models outperform the equivalent null models in classifying all examined cancer types and in estimating the probability of survival 10 years after the initial diagnosis. Additionally, combining both non-silent and silent mutations achieved the best classification results for 68% of the cancer types and the best survival estimation results for up to nine years after the diagnosis. Thus, silent mutations hold considerable predictive power over both cancer classification and prognosis, most likely due to their effect on gene expression. It is highly advised that silent mutations are integrated in cancer research in order to unravel the full genomic landscape of cancer and its ramifications on cancer fitness.