Cancer cells resistant to immune checkpoint blockade acquire interferon-associated epigenetic memory to sustain T cell dysfunction.

Prolonged interferon (IFN) signaling in cancer cells can promote resistance to immune checkpoint blockade (ICB). How cancer cells retain effects of prolonged IFN stimulation to coordinate resistance is unclear. We show that, across human and/or mouse tumors, immune dysfunction is associated with cancer cells acquiring epigenetic features of inflammatory memory. Here, inflammatory memory domains, many of which are initiated by chronic IFN-γ, are maintained by signal transducer and activator of transcription (STAT)1 and IFN regulatory factor (IRF)3 and link histone 3 lysine 4 monomethylation (H3K4me1)-marked chromatin accessibility to increased expression of a subset of IFN-stimulated genes (ISGs). These ISGs include the RNA sensor OAS1 that amplifies type I IFN (IFN-I) and immune inhibitory genes. Abrogating cancer cell IFN-I signaling restores anti-programmed cell death protein 1 (PD1) response by increasing IFN-γ in immune cells, promoting dendritic cell and CD8+ T cell interactions, and expanding T cells toward effector-like states rather than exhausted states. Thus, cancer cells acquire inflammatory memory to augment a subset of ISGs that promote and predict IFN-driven immune dysfunction.

Adjuvant Therapy After Neoadjuvant Therapy for Esophageal Cancer: Who Needs It?

OBJECTIVE: We hypothesized that, on average, patients do not benefit from additional adjuvant therapy after neoadjuvant therapy for locally advanced esophageal cancer, although subsets of patients might. Therefore, we sought to identify profiles of patients predicted to receive the most survival benefit or greatest detriment from adding adjuvant therapy. BACKGROUND: Although neoadjuvant therapy has become the treatment of choice for locally advanced esophageal cancer, the value of adding adjuvant therapy is unknown. METHODS: From 1970 to 2014, 22,123 patients were treated for esophageal cancer at 33 centers on 6 continents (Worldwide Esophageal Cancer Collaboration), of whom 7731 with adenocarcinoma or squamous cell carcinoma received neoadjuvant therapy; 1348 received additional adjuvant therapy. Random forests for survival and virtual-twin analyses were performed for all-cause mortality. RESULTS: Patients received a small survival benefit from adjuvant therapy (3.2±10 months over the subsequent 10 years for adenocarcinoma, 1.8±11 for squamous cell carcinoma). Consistent benefit occurred in ypT3-4 patients without nodal involvement and those with ypN2-3 disease. The small subset of patients receiving most benefit had high nodal burden, ypT4, and positive margins. Patients with ypT1-2N0 cancers had either no benefit or a detriment in survival. CONCLUSIONS: Adjuvant therapy after neoadjuvant therapy has value primarily for patients with more advanced esophageal cancer. Because the benefit is often small, patients considering adjuvant therapy should be counseled on benefits versus morbidity. In addition, given that the overall benefit was meaningful in a small number of patients, emerging modalities such as immunotherapy may hold more promise in the adjuvant setting.

Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning.

BACKGROUND: Machine learning (ML) is increasingly used to predict suicide deaths but their value for suicide prevention has not been established. Our first objective was to identify risk and protective factors in a general population. Our second objective was to identify factors indicating imminent suicide risk. METHODS: We used survival and ML models to identify lifetime predictors using the Cohort of Norway (n=173,275) and hospital diagnoses in a Saskatoon clinical sample (n=12,614). The mean follow-up times were 17 years and 3 years for the Cohort of Norway and Saskatoon respectively. People in the clinical sample had a longitudinal record of hospital visits grouped in six-month intervals. We developed models in a training set and these models predicted survival probabilities in held-out test data. RESULTS: In the general population, we found that a higher proportion of low-income residents in a county, mood symptoms, and daily smoking increased the risk of dying from suicide in both genders. In the clinical sample, the only predictors identified were male gender and older age. CONCLUSION: Suicide prevention probably requires individual actions with governmental incentives. The prediction of imminent suicide remains highly challenging, but machine learning can identify early prevention targets.

BOOSTED NONPARAMETRIC HAZARDS WITH TIME-DEPENDENT COVARIATES.

Given functional data from a survival process with time-dependent covariates, we derive a smooth convex representation for its nonparametric log-likelihood functional and obtain its functional gradient. From this we devise a generic gradient boosting procedure for estimating the hazard function nonparametrically. An illustrative implementation of the procedure using regression trees is described to show how to recover the unknown hazard. The generic estimator is consistent if the model is correctly specified; alternatively an oracle inequality can be demonstrated for tree-based models. To avoid overfitting, boosting employs several regularization devices. One of them is step-size restriction, but the rationale for this is somewhat mysterious from the viewpoint of consistency. Our work brings some clarity to this issue by revealing that step-size restriction is a mechanism for preventing the curvature of the risk from derailing convergence.

Cure and death play a role in understanding dynamics for COVID-19: Data-driven competing risk compartmental models, with and without vaccination.

Several factors have played a strong role in influencing the dynamics of COVID-19 in the U.S. One being the economy, where a tug of war has existed between lockdown measures to control disease versus loosening of restrictions to address economic hardship. A more recent effect has been availability of vaccines and the mass vaccination efforts of 2021. In order to address the challenges in analyzing this complex process, we developed a competing risk compartmental model framework with and without vaccination compartment. This framework separates instantaneous risk of removal for an infectious case into competing risks of cure and death, and when vaccinations are present, the vaccinated individual can also achieve immunity before infection. Computations are performed using a simple discrete time algorithm that utilizes a data driven contact rate. Using population level pre-vaccination data, we are able to identify and characterize three wave patterns in the U.S. Estimated mortality rates for second and third waves are 1.7%, which is a notable decrease from 8.5% of a first wave observed at onset of disease. This analysis reveals the importance cure time has on infectious duration and disease transmission. Using vaccination data from 2021, we find a fourth wave, however the effect of this wave is suppressed due to vaccine effectiveness. Parameters playing a crucial role in this modeling were a lower cure time and a signficantly lower mortality rate for the vaccinated.

The CHA2DS2-VASc Score for Risk Stratification of Stroke in Heart Failure With-vs-Without Atrial Fibrillation.

A recent study suggested that the CHA2DS2-VASc score can risk stratify heart failure (HF) patients without atrial fibrillation (AF) for stroke. We performed a retrospective analysis using the national Veteran Affairs database to externally validate the findings. Crude incidence rates of end points were calculated. A Cox proportional model was used to study the association between the CHA2DS2-VASc score and outcomes. In HF patients with AF (n = 17,481) and without AF (n = 36,935), the 1 year incidence rate for ischemic stroke, thromboembolism, thromboembolism (without MI), and death were 2.7 and 2.0%; 10.3 and 7.9%; 4.1 and 3.1%; and 19.2 and 26.0%, respectively, with higher rates with increasing CHA2DS2-VASc scores both with and without AF. CHA2DS2-VASc score predicted strokes in HF patients without AF (1-year C-statistic 0.62, 95% CI 0.60-0.64; NPV 85.4%, 95% CI 83.4-87.4%) with similar predictive ability to those with AF (C-statistic 0.59, 95% CI 0.56-0.62; NPV 86.4%, 95% CI 82.6-90.2%). Among patients with HF, there was an increased risk of stroke, thromboembolism, and death with increasing CHA2DS2-VASc scores regardless of AF status. Our findings support the use of the CHA2DS2-VASc score as a prognostic tool in HF.

Unsupervised random forests.

sidClustering is a new random forests unsupervised machine learning algorithm. The first step in sidClustering involves what is called sidification of the features: staggering the features to have mutually exclusive ranges (called the staggered interaction data [SID] main features) and then forming all pairwise interactions (called the SID interaction features). Then a multivariate random forest (able to handle both continuous and categorical variables) is used to predict the SID main features. We establish uniqueness of sidification and show how multivariate impurity splitting is able to identify clusters. The proposed sidClustering method is adept at finding clusters arising from categorical and continuous variables and retains all the important advantages of random forests. The method is illustrated using simulated and real data as well as two in depth case studies, one from a large multi-institutional study of esophageal cancer, and the other involving hospital charges for cardiovascular patients.

Random Survival Forests Analysis of Intraoperative Complications as Predictors of Descemet Stripping Automated Endothelial Keratoplasty Graft Failure in the Cornea Preservation Time Study.

Importance: A new analytic method can evaluate factors of interest associated with graft failure after Descemet stripping automated endothelial keratoplasty (DSAEK) or more generally in any ophthalmic surgical setting with a time-to-event outcome. Objective: To reanalyze types of intraoperative complications associated with DSAEK graft failure in the Cornea Preservation Time Study using random survival forests. Design, Setting, and Participants: This cohort study, initially conceived in April 2019, used a prediction model to conduct a post hoc secondary analysis of data collected in a multicenter, double-masked, randomized clinical trial. Forty US clinical sites with 70 surgeons participated, with donor corneas provided by 23 US eye banks. The study included 1090 participants, representing 1330 eyes, undergoing DSAEK for Fuchs dystrophy (1255 eyes [94.4%]) or pseudophakic or aphakic corneal edema (75 eyes [5.6%]). Enrollment occurred between April 16, 2012, and February 20, 2014, and follow-up ended June 5, 2017. Statistical analysis was performed from July 10, 2019, to May 29, 2020. Intervention: Descemet stripping automated endothelial keratoplasty with random assignment of a donor cornea with preservation time of 7 days or less or 8 to 14 days. Main Outcomes and Measures: Ranked variable importance for intraoperative complications among 50 donor, recipient, and eye bank variables and restricted mean survival time through 47 months (1434 days) after DSAEK were examined. Random survival forests, a nonparametric method (with less restrictive model assumptions) that is far more flexible in its ability to model nonlinear effects and interactions, was used to analyze the data. Results: This study included 1090 participants (663 women [60.8%]; median age, 70 years [range, 42-90 years]), representing 1330 eyes. Random survival forests ranked a DSAEK intraoperative complication as the third most predictive factor of graft failure, after surgeon and eye bank, in the final model with 5 predictors. In the first 47 months after DSAEK, the estimated mean difference in restricted mean survival time for grafts that experienced a DSAEK intraoperative complication vs those that did not was -227 days (99% CI, -352 to -70 days) based on the final RSF model. Conclusions and Relevance: These findings, while post hoc, support the hypothesis that random survival forests allow for an improved analytic approach for identifying factors predictive of graft failure and for obtaining adjusted graft survival estimates. Random survival forests offer the opportunity to guide the development of future population-based cohort ophthalmic surgical studies, establishing definitive factors for procedural success.

Value of Lymphadenectomy in Patients Receiving Neoadjuvant Therapy for Esophageal Adenocarcinoma.

OBJECTIVE: The aim of this study was to assess the effect on survival of extent of lymphadenectomy during esophagectomy for patients undergoing multimodality (neoadjuvant) therapy for adenocarcinoma of the esophagus and esophagogastric junction using Worldwide Esophageal Cancer Collaboration data. SUMMARY BACKGROUND DATA: Previous worldwide data demonstrated that optimum lymphadenectomy during esophagectomy alone for esophageal cancer provides accurate staging and maximum survival. However, for patients undergoing neoadjuvant therapy for locally advanced adenocarcinoma, its value is unclear, leading to wide practice variability. METHODS: A total of 3859 patients with adenocarcinoma of the esophagus or esophagogastric junction received neoadjuvant therapy. The endpoint was all-cause mortality, reported as gain or loss of lifetime within 10 years. Lifetime predicted for each regional lymph node resected used quantile survival random forest methodology. RESULTS: Across all post-neoadjuvant ypTNM cancer categories, some degree of lymphadenectomy was associated with longer lifetime, but in a nonlinear fashion. For patients with ypN0 cancers, there was a modest gain in lifetime up to 25 lymph nodes resected and an incremental loss in lifetime as >25 were resected. For patients with ypN+ cancers, there was a robust gain in lifetime up to 30 lymph nodes resected and then an incremental loss in lifetime. CONCLUSIONS: Worldwide data for adenocarcinoma of the esophagus and esophagogastric junction demonstrate that lymphadenectomy during esophagectomy is a valuable component of neoadjuvant therapy. Survival is maximized when an optimum range of nodes is resected.

Dynamic Competing Risk Modeling COVID-19 in a Pandemic Scenario.

The emergence of coronavirus disease 2019 (COVID-19) in the United States has forced federal and local governments to implement containment measures. Moreover, the severity of the situation has sparked engagement by both the research and clinical community with the goal of developing effective treatments for the disease. This article proposes a time dynamic prediction model with competing risks for the infected individual and develops a simple tool for policy makers to compare different strategies in terms of when to implement the strictest containment measures and how different treatments can increase or suppress infected cases. Two types of containment strategies are compared: (1) a constant containment strategy that could satisfy the needs of citizens for a long period; and (2) an adaptive containment strategy whose strict level changes across time. We consider how an effective treatment of the disease can affect the dynamics in a pandemic scenario. For illustration we consider a region with population 2.8 million and 200 initial infectious cases assuming a 4% mortality rate compared with a 2% mortality rate if a new drug is available. Our results show compared with a constant containment strategy, adaptive containment strategies shorten the outbreak length and reduce maximum daily number of cases. This, along with an effective treatment plan for the disease can minimize death rate.

Heart Transplantation: An In-Depth Survival Analysis.

OBJECTIVES: This study aims to understand the complex factors affecting heart transplant survival and to determine the importance of possible sex-specific risk factors. BACKGROUND: Heart transplant allocation is primarily focused on preventing waitlist mortality. To prevent organ wastage, future allocation must balance risk of waitlist mortality with post-transplantation mortality. However, more information regarding risk factors after heart transplantation is needed. METHODS: We included all adults (30,606) in the Scientific Registry of Transplant Recipients database who underwent isolated heart transplantation from January 1, 2004, to July 1, 2018. Mortality (8,278 deaths) was verified with the complete Social Security Death Index with a median follow-up of 3.9 years. Temporal decomposition was used to identify phases of survival and phase-specific risk factors. The random survival forests method was used to determine importance of mortality risk factors and their interactions. RESULTS: We identified 3 phases of mortality risk: early post-transplantation, constant, and late. Sex was not a significant risk factor. There were several interactions predicting early mortality such as pretransplantation mechanical ventilation with presence of end-organ function (bilirubin, renal function) and interactions predicting later mortality such as diabetes and older age (donor and recipient). More complex interactions predicting early-, mid-, and late-mortality existed and were identified with machine learning (i.e., elevated bilirubin, mechanical ventilation, and dialysis). CONCLUSIONS: Post-heart transplant mortality risk is complex and dynamic, changing with time and events. Sex is not an important mortality risk factor. To prevent organ wastage, end-organ dysfunction should be resolved before transplantation as much as possible.

Precision Surgical Therapy for Adenocarcinoma of the Esophagus and Esophagogastric Junction.

INTRODUCTION: To facilitate the initial clinical decision regarding whether to use esophagectomy alone or neoadjuvant therapy in surgical care for individual patients with adenocarcinoma of the esophagus and esophagogastric junction-information not available from randomized trials-a machine-learning analysis was performed using worldwide real-world data on patients undergoing different therapies for this rare adenocarcinoma. METHODS: Using random forest technology in a sequential analysis, we (1) identified eligibility for each of four therapies among 13,365 patients: esophagectomy alone (n = 6649), neoadjuvant therapy (n = 4706), esophagectomy and adjuvant therapy (n = 998), and neoadjuvant and adjuvant therapy (n = 1022); (2) performed survival analyses incorporating interactions of patient and cancer characteristics with therapy; (3) determined optimal therapy as that predicted to maximize lifetime within 10 years (restricted mean survival time; RMST) for each patient; and (4) compared lifetime gained from optimal versus actual therapies. RESULTS: Actual therapy was optimal in 61% of those receiving esophagectomy alone; neoadjuvant therapy was optimal for 36% receiving neoadjuvant therapy. Many patients were predicted to benefit from postoperative adjuvant therapy. Total RMST for actual therapy received was 58,825 years. Had patients received optimal therapy, total RMST was predicted to be 62,982 years, a 7% gain. CONCLUSIONS: Average treatment effect for adenocarcinoma of the esophagus yields only crude evidence-based therapy guidelines. However, patient response to therapy is widely variable, and survival after data-driven predicted optimal therapy often differs from actual therapy received. Therapy must address an individual patient's cancer and clinical characteristics to provide precision surgical therapy for adenocarcinoma of the esophagus and esophagogastric junction.

Opposing Functions of Interferon Coordinate Adaptive and Innate Immune Responses to Cancer Immune Checkpoint Blockade.

Interferon-gamma (IFNG) augments immune function yet promotes T cell exhaustion through PDL1. How these opposing effects are integrated to impact immune checkpoint blockade (ICB) is unclear. We show that while inhibiting tumor IFNG signaling decreases interferon-stimulated genes (ISGs) in cancer cells, it increases ISGs in immune cells by enhancing IFNG produced by exhausted T cells (TEX). In tumors with favorable antigenicity, these TEX mediate rejection. In tumors with neoantigen or MHC-I loss, TEX instead utilize IFNG to drive maturation of innate immune cells, including a PD1+TRAIL+ ILC1 population. By disabling an inhibitory circuit impacting PD1 and TRAIL, blocking tumor IFNG signaling promotes innate immune killing. Thus, interferon signaling in cancer cells and immune cells oppose each other to establish a regulatory relationship that limits both adaptive and innate immune killing. In melanoma and lung cancer patients, perturbation of this relationship is associated with ICB response independent of tumor mutational burden.

A Random Forests Quantile Classifier for Class Imbalanced Data.

Extending previous work on quantile classifiers (q-classifiers) we propose the q*-classifier for the class imbalance problem. The classifier assigns a sample to the minority class if the minority class conditional probability exceeds 0 < q* < 1, where q* equals the unconditional probability of observing a minority class sample. The motivation for q*-classification stems from a density-based approach and leads to the useful property that the q*-classifier maximizes the sum of the true positive and true negative rates. Moreover, because the procedure can be equivalently expressed as a cost-weighted Bayes classifier, it also minimizes weighted risk. Because of this dual optimization, the q*-classifier can achieve near zero risk in imbalance problems, while simultaneously optimizing true positive and true negative rates. We use random forests to apply q*-classification. This new method which we call RFQ is shown to outperform or is competitive with existing techniques with respect to tt-mean performance and variable selection. Extensions to the multiclass imbalanced setting are also considered.

Variables of importance in the Scientific Registry of Transplant Recipients database predictive of heart transplant waitlist mortality.

The prelisting variables essential for creating an accurate heart transplant allocation score based on survival are unknown. To identify these we studied mortality of adults on the active heart transplant waiting list in the Scientific Registry of Transplant Recipients database from January 1, 2004 to August 31, 2015. There were 33 069 candidates awaiting heart transplantation: 7681 UNOS Status 1A, 13 027 Status 1B, and 12 361 Status 2. During a median waitlist follow-up of 4.3 months, 5514 candidates died. Variables of importance for waitlist mortality were identified by machine learning using Random Survival Forests. Strong correlates predicting survival were estimated glomerular filtration rate (eGFR), serum albumin, extracorporeal membrane oxygenation, ventricular assist device, mechanical ventilation, peak oxygen capacity, hemodynamics, inotrope support, and type of heart disease with less predictive variables including antiarrhythmic agents, history of stroke, vascular disease, prior malignancy, and prior tobacco use. Complex interactions were identified such as an additive risk in mortality based on renal function and serum albumin, and sex-differences in mortality when eGFR >40 mL/min/1.73 m. Most predictive variables for waitlist mortality are in the current tiered allocation system except for eGFR and serum albumin which have an additive risk and complex interactions.