Mortality risk after liver transplantation in hepatocellular carcinoma recipients: A nonlinear predictive model

Predicting lower limb lymphedema after cervical cancer surgery using artificial neural network and decision tree models

PURPOSE

This study aimed to develop and validate accessible artificial neural network and decision tree models to predict the risk of lower limb lymphedema after cervical cancer surgery.

METHODS

We selected 759 patients who underwent cervical cancer surgery at the Hunan Cancer Hospital from January 2010 to January 2020, collecting demographic, behavioral, clinicopathological, and disease-related data. The artificial neural network and decision tree techniques were used to construct prediction models for lower limb lymphedema after cervical cancer surgery. Then, the models' predictive efficacies were evaluated to select the optimal model using several methods, such as the area under the receiver operating characteristic curve and accuracy, sensitivity, and specificity tests.

RESULTS

In the training set, the artificial neural network and decision tree model accuracies for predicting lower limb lymphedema after cervical cancer surgery were 99.80% and 88.14%, and the sensitivities 99.50% and 74.01%, respectively; the specificities were 100% and 95.20%, respectively. The area under the receiver operating characteristic curve was 1.00 for the artificial neural network and 0.92 for the decision tree model. In the test set, the artificial neural network and decision tree models' accuracies were 86.70% and 82.02%, and the sensitivities 65.70% and 67.11%, respectively; the specificities were 96.00% and 89.47%, respectively.

CONCLUSION

Both models had good predictive efficacy for lower limb lymphedema after cervical cancer surgery. However, the predictive performance and stability were superior in the artificial neural network model than in the decision tree model.

Should AI allocate livers for transplant? Public attitudes and ethical considerations

BACKGROUND

Allocation of scarce organs for transplantation is ethically challenging. Artificial intelligence (AI) has been proposed to assist in liver allocation, however the ethics of this remains unexplored and the view of the public unknown. The aim of this paper was to assess public attitudes on whether AI should be used in liver allocation and how it should be implemented.

METHODS

We first introduce some potential ethical issues concerning AI in liver allocation, before analysing a pilot survey including online responses from 172 UK laypeople, recruited through Prolific Academic.

FINDINGS

Most participants found AI in liver allocation acceptable (69.2%) and would not be less likely to donate their organs if AI was used in allocation (72.7%). Respondents thought AI was more likely to be consistent and less biased compared to humans, although were concerned about the "dehumanisation of healthcare" and whether AI could consider important nuances in allocation decisions. Participants valued accuracy, impartiality, and consistency in a decision-maker, more than interpretability and empathy. Respondents were split on whether AI should be trained on previous decisions or programmed with specific objectives. Whether allocation decisions were made by transplant committee or AI, participants valued consideration of urgency, survival likelihood, life years gained, age, future medication compliance, quality of life, future alcohol use and past alcohol use. On the other hand, the majority thought the following factors were not relevant to prioritisation: past crime, future crime, future societal contribution, social disadvantage, and gender.

CONCLUSIONS

There are good reasons to use AI in liver allocation, and our sample of participants appeared to support its use. If confirmed, this support would give democratic legitimacy to the use of AI in this context and reduce the risk that donation rates could be affected negatively. Our findings on specific ethical concerns also identify potential expectations and reservations laypeople have regarding AI in this area, which can inform how AI in liver allocation could be best implemented.

A Surgeon's Guide to Artificial Intelligence-Driven Predictive Models

Artificial intelligence (AI) focuses on processing and interpreting complex information as well as identifying relationships and patterns among complex data. Artificial intelligence- and machine learning (ML)-driven predictions have shown promising potential in influencing real-time decisions and improving surgical outcomes by facilitating screening, diagnosis, risk assessment, preoperative planning, and shared decision-making. Fundamental understanding of the algorithms, as well as their development and interpretation, is essential for the evolution of AI in surgery. In this article, we provide surgeons with a fundamental understanding of AI-driven predictive models through an overview of common ML and deep learning algorithms, model development, performance metrics and interpretation. This would serve as a basis for understanding ML-based research, while fostering new ideas and innovations for furthering the reach of this emerging discipline.

Machine Learning-Based Short-Term Mortality Prediction Models for Patients With Cancer Using Electronic Health Record Data: Systematic Review and Critical Appraisal

BACKGROUND

In the United States, national guidelines suggest that aggressive cancer care should be avoided in the final months of life. However, guideline compliance currently requires clinicians to make judgments based on their experience as to when a patient is nearing the end of their life. Machine learning (ML) algorithms may facilitate improved end-of-life care provision for patients with cancer by identifying patients at risk of short-term mortality.

OBJECTIVE

This study aims to summarize the evidence for applying ML in ≤1-year cancer mortality prediction to assist with the transition to end-of-life care for patients with cancer.

METHODS

We searched MEDLINE, Embase, Scopus, Web of Science, and IEEE to identify relevant articles. We included studies describing ML algorithms predicting ≤1-year mortality in patients of oncology. We used the prediction model risk of bias assessment tool to assess the quality of the included studies.

RESULTS

We included 15 articles involving 110,058 patients in the final synthesis. Of the 15 studies, 12 (80%) had a high or unclear risk of bias. The model performance was good: the area under the receiver operating characteristic curve ranged from 0.72 to 0.92. We identified common issues leading to biased models, including using a single performance metric, incomplete reporting of or inappropriate modeling practice, and small sample size.

CONCLUSIONS

We found encouraging signs of ML performance in predicting short-term cancer mortality. Nevertheless, no included ML algorithms are suitable for clinical practice at the current stage because of the high risk of bias and uncertainty regarding real-world performance. Further research is needed to develop ML models using the modern standards of algorithm development and reporting.

Current updates in machine learning in the prediction of therapeutic outcome of hepatocellular carcinoma: what should we know?

With the development of machine learning (ML) algorithms, a growing number of predictive models have been established for predicting the therapeutic outcome of patients with hepatocellular carcinoma (HCC) after various treatment modalities. By using the different combinations of clinical and radiological variables, ML algorithms can simulate human learning to detect hidden patterns within the data and play a critical role in artificial intelligence techniques. Compared to traditional statistical methods, ML methods have greater predictive effects. ML algorithms are widely applied in nearly all steps of model establishment, such as imaging feature extraction, predictive factor classification, and model development. Therefore, this review presents the literature pertaining to ML algorithms and aims to summarize the strengths and limitations of ML, as well as its potential value in prognostic prediction, after various treatment modalities for HCC.

Machine learning in liver transplantation: a tool for some unsolved questions?

Machine learning has recently been proposed as a useful tool in many fields of Medicine, with the aim of increasing diagnostic and prognostic accuracy. Models based on machine learning have been introduced in the setting of solid organ transplantation too, where prognosis depends on a complex, multidimensional and nonlinear relationship between variables pertaining to the donor, the recipient and the surgical procedure. In the setting of liver transplantation, machine learning models have been developed to predict pretransplant survival in patients with cirrhosis, to assess the best donor-to-recipient match during allocation processes, and to foresee postoperative complications and outcomes. This is a narrative review on the role of machine learning in the field of liver transplantation, highlighting strengths and pitfalls, and future perspectives.

Using Artificial Intelligence for Predicting Survival of Individual Grafts in Liver Transplantation: A Systematic Review

The demand for liver transplantation far outstrips the supply of deceased donor organs, and so, listing and allocation decisions aim to maximize utility. Most existing methods for predicting transplant outcomes use basic methods, such as regression modeling, but newer artificial intelligence (AI) techniques have the potential to improve predictive accuracy. The aim was to perform a systematic review of studies predicting graft outcomes following deceased donor liver transplantation using AI techniques and to compare these findings to linear regression and standard predictive modeling: donor risk index (DRI), Model for End-Stage Liver Disease (MELD), and Survival Outcome Following Liver Transplantation (SOFT). After reviewing available article databases, a total of 52 articles were reviewed for inclusion. Of these articles, 9 met the inclusion criteria, which reported outcomes from 18,771 liver transplants. Artificial neural networks (ANNs) were the most commonly used methodology, being reported in 7 studies. Only 2 studies directly compared machine learning (ML) techniques to liver scoring modalities (i.e., DRI, SOFT, and balance of risk [BAR]). Both studies showed better prediction of individual organ survival with the optimal ANN model, reporting an area under the receiver operating characteristic curve (AUROC) 0.82 compared with BAR (0.62) and SOFT (0.57), and the other ANN model gave an AUC ROC of 0.84 compared with a DRI (0.68) and SOFT (0.64). AI techniques can provide high accuracy in predicting graft survival based on donors and recipient variables. When compared with the standard techniques, AI methods are dynamic and are able to be trained and validated within every population. However, the high accuracy of AI may come at a cost of losing explainability (to patients and clinicians) on how the technology works.

Charting the Path Forward for Risk Prediction in Liver Transplant for Hepatocellular Carcinoma: International Validation of HALTHCC Among 4,089 Patients

Prognosticating outcomes in liver transplant (LT) for hepatocellular carcinoma (HCC) continues to challenge the field. Although Milan Criteria (MC) generalized the practice of LT for HCC and improved outcomes, its predictive character has degraded with increasing candidate and oncological heterogeneity. We sought to validate and recalibrate a previously developed, preoperatively calculated, continuous risk score, the Hazard Associated with Liver Transplantation for Hepatocellular Carcinoma (HALTHCC), in an international cohort. From 2002 to 2014, 4,089 patients (both MC in and out [25.2%]) across 16 centers in North America, Europe, and Asia were included. A continuous risk score using pre-LT levels of alpha-fetoprotein, Model for End-Stage Liver Disease Sodium score, and tumor burden score was recalibrated among a randomly selected cohort (n = 1,021) and validated in the remainder (n = 3,068). This study demonstrated significant heterogeneity by site and year, reflecting practice trends over the last decade. On explant pathology, both vascular invasion (VI) and poorly differentiated component (PDC) increased with increasing HALTHCC score. The lowest-risk patients (HALTHCC 0-5) had lower rates of VI and PDC than the highest-risk patients (HALTHCC > 35) (VI, 7.7%[ 1.2-14.2] vs. 70.6% [48.3-92.9] and PDC:4.6% [0.1%-9.8%] vs. 47.1% [22.6-71.5]; P < 0.0001 for both). This trend was robust to MC status. This international study was used to adjust the coefficients in the HALTHCC score. Before recalibration, HALTHCC had the greatest discriminatory ability for overall survival (OS; C-index = 0.61) compared to all previously reported scores. Following recalibration, the prognostic utility increased for both recurrence (C-index = 0.71) and OS (C-index = 0.63). Conclusion: This large international trial validated and refined the role for the continuous risk metric, HALTHCC, in establishing pre-LT risk among candidates with HCC worldwide. Prospective trials introducing HALTHCC into clinical practice are warranted.

Compliance with ethical standards in the reporting of donor sources and ethics review in peer-reviewed publications involving organ transplantation in China: a scoping review

OBJECTIVES

The objective of this study is to investigate whether papers reporting research on Chinese transplant recipients comply with international professional standards aimed at excluding publication of research that: (1) involves any biological material from executed prisoners; (2) lacks Institutional Review Board (IRB) approval and (3) lacks consent of donors.

DESIGN

Scoping review based on Arksey and O'Mallee's methodological framework.

DATA SOURCES

Medline, Scopus and Embase were searched from January 2000 to April 2017.

ELIGIBILITY CRITERIA

We included research papers published in peer-reviewed English-language journals reporting on outcomes of research involving recipients of transplanted hearts, livers or lungs in mainland China.

DATA EXTRACTION AND SYNTHESIS

Data were extracted by individual authors working independently following training and benchmarking. Descriptive statistics were compiled using Excel.

RESULTS

445 included studies reported on outcomes of 85 477 transplants. 412 (92.5%) failed to report whether or not organs were sourced from executed prisoners; and 439 (99%) failed to report that organ sources gave consent for transplantation. In contrast, 324 (73%) reported approval from an IRB. Of the papers claiming that no prisoners' organs were involved in the transplants, 19 of them involved 2688 transplants that took place prior to 2010, when there was no volunteer donor programme in China.

DISCUSSION

The transplant research community has failed to implement ethical standards banning publication of research using material from executed prisoners. As a result, a large body of unethical research now exists, raising issues of complicity and moral hazard to the extent that the transplant community uses and benefits from the results of this research. We call for retraction of this literature pending investigation of individual papers.

Macro- and micro-environmental factors in clinical hepatocellular cancer

We previously developed a network phenotyping strategy (NPS), a graph theory-based transformation of clinical practice data, for recognition of two primary subgroups of hepatocellular cancer (HCC), called S and L, which differed significantly in their tumor masses. In the current study, we have independently validated this result on 641 HCC patients from another continent. We identified the same HCC subgroups with mean tumor masses 9 cm x n (S) and 22 cm x n (L), P<10(-14). The means of survival distribution (not available previously) for this new cohort were also significantly different (S was 12 months, L was 7 months, P<10(-5)). We characterized nine unique reference patterns of interactions between tumor and clinical environment factors, identifying four subtypes for S and five subtypes for L phenotypes, respectively. In L phenotype, all reference patterns were portal vein thrombosis (PVT)-positive, all platelet/alpha fetoprotein (AFP) levels were high, and all were chronic alcohol consumers. L had phenotype landmarks with worst survival. S phenotype interaction patterns were PVT-negative, with low platelet/AFP levels. We demonstrated that tumor-clinical environment interaction patterns explained how a given parameter level can have a different significance within a different overall context. Thus, baseline bilirubin is low in S1 and S4, but high in S2 and S3, yet all are S subtype patterns, with better prognosis than in L. Gender and age, representing macro-environmental factors, and bilirubin, prothrombin time, and AST levels representing micro-environmental factors, had a major impact on subtype characterization. Clinically important HCC phenotypes are therefore represented by complete parameter relationship patterns and cannot be replaced by individual parameter levels.

Evaluation of total tumor volume and pretransplantation α-fetoprotein level as selection criteria for liver transplantation in patients with hepatocellular cancer

INTRODUCTION

Appropriate selection of hepatocellular cancer (HCC) patients for liver transplantation is crucial to minimize the risk of recurrence and provide long-term outcomes comparable with those for other indications. Selection criteria based on total tumor volume (TTV) and α-fetoprotein (AFP) concentrations were proposed in a recent large study. The aim of this study was to evaluate the results of liver transplantation for HCC within and beyond these criteria.

MATERIAL AND METHODS

This retrospective study included 104 patients with HCC who underwent liver transplantation. Risk factors for overall survival and tumor recurrence were evaluated. Overall survival and cumulative tumor recurrence rate for patients with TTV <115 cm(3), AFP concentration <400 ng/mL, and no macrovascular invasion (76/104; 73.1%) were evaluated and compared with those for the remaining patients (28/104; 26.9%).

RESULTS

Pretransplantation AFP concentration >400 ng/mL (P = .016; hazard ratio [HR], 3.36; 95% confidence intervals [CI], 1.25-9.03) was the only risk factor for overall survival. TTV >115 cm(3) (P = .021; HR 4.29; 95% CI, 1.24-14.81) and AFP concentration >400 ng/mL (P = .002; HR 6.97; 95% CI, 2.02-24.03) were independent risk factors for recurrence. The estimated 3-year tumor recurrence rate was 4.2% for patients with TTV <115 cm(3), AFP concentration <400 ng/mL, and no macrovascular invasion compared with 57.2% for the remaining patients (P < .00001). The 3-year overall survival rate of patients within and beyond this criteria was 81.7% and 64.6%, respectively (P = .0628).

CONCLUSIONS

In contrast to other criteria, selection of HCC patients for liver transplantation on the basis of TTV and AFP concentration relates to both morphological features and tumor biology. Although fulfillment of these criteria was more than 1.5-fold higher than that of the Milan criteria, the rate of tumor recurrence was exceptionally low.

HCC patients suffer less from geographic differences in organ availability

It has been suggested that the number of exception model for end-stage liver disease (MELD) points for hepatocellular carcinoma (HCC) overestimates mortality risk. Average MELD at transplant, a measure of organ availability, correlates with mortality on an intent-to-treat basis and varies by donation service area (DSA). We analyzed Scientific Registry of Transplant Recipients data from 2005 to 2010, comparing transplant and death parameters for patients transplanted with HCC exception points to patients without HCC diagnosis (non-HCC), to determine whether the two groups were impacted differentially by DSA organ availability. HCC candidates are transplanted at higher rates than non-HCC candidates and are less likely to die on the waitlist. Overall risk of death trends downward by 1% per MELD point (p = 0.65) for HCC, but increases by 7% for non-HCC patients (p < 0.0001). The difference in the change of mortality with MELD is statistically significant between HCC and non-HCC candidates p < 0.0001. Posttransplant risk of death trends downward by 2% per MELD point (p = 0.28) for HCC patients, but increases by 3% per MELD point in non-HCC patients (p = 0.027), with the difference being statistically significant with p < 0.005. In summary, increasing wait time impacts HCC candidates less than non-HCC candidates and under increased competition for donor organs, HCC candidates' advantage increases.