Development and validation of a prediction model for 1-year mortality among older adults with Hodgkin Lymphoma who receive dose-intense chemotherapy

Determining health care cost drivers in older Hodgkin lymphoma survivors using interpretable machine learning methods

BACKGROUND

The cost of health care for patients with Hodgkin lymphoma (HL) is projected to rise, making it essential to understand expenditure drivers across different demographics, including the older adult population. Although older HL patients constitute a significant number of HL patients, the literature on health care expenditures in older HL patients is lacking. Predictive capabilities of machine learning (ML) methods enhance our ability to leverage a data-driven approach, which helps identify key predictors of expenditures and strategically plan future expenditures.

OBJECTIVE

To determine the leading predictors of health care expenditures among older HL survivors across prediagnosis, treatment, and posttreatment phases of care.

METHODS

The study uses a retrospective research design to identify the incident cases of HL diagnosed between 2009 and 2017 using Surveillance, Epidemiology, and End Results-Medicare data. Three phases of cancer care (prediagnosis, treatment, and posttreatment) were indexed around the diagnosis date, with each phase divided into 12 months of baseline and 12 months of follow-up. ML methods, including XGBoost, Random Forest, and Cross-Validated linear regressions, were used to identify the best regression model for predicting Medicare and out-of-pocket (OOP) health care expenditures. Interpretable ML SHapley Additive exPlanations method was used to identify the leading predictors of Medicare and OOP health care expenditures in each phase.

RESULTS

The study analyzed 1,242 patients in the prediagnosis phase, 902 in the treatment phase, and 873 in the posttreatment phase. XGBoost regression outperformed Random Forest and Cross-Validated linear regression models with overall performance in predicting Medicare expenditures, with R-squared (root mean square error) values of 0.42 (1.39), 0.43 (0.56), and 0.46 (0.90) across the 3 phases of care, respectively. Interpretable ML methods highlighted baseline expenditures, number of prescription medications, and cardiac dysrhythmia as the leading predictors for Medicare and OOP expenditures in the prediagnosis phase. Chemotherapy and immunotherapy and surgical treatment and immunotherapy were the leading predictors of expenditures in the treatment and posttreatment phases, respectively.

CONCLUSIONS

As ML applications increase in predicting health care expenditure, researchers should consider implementing models in different phases of care to identify the changes in the predictors. Leading predictors of health care expenditures can be targeted for informed policy development to address financial hardship in HL survivors.

Leveraging social media data to study disease and treatment characteristics of Hodgkin's lymphoma Using Natural Language Processing methods

BACKGROUND

The use of social media platforms in health research is increasing, yet their application in studying rare diseases is limited. Hodgkin's lymphoma (HL) is a rare malignancy with a high incidence in young adults. This study evaluates the feasibility of using social media data to study the disease and treatment characteristics of HL.

METHODS

We utilized the X (formerly Twitter) API v2 developer portal to download posts (formerly tweets) from January 2010 to October 2022. Annotation guidelines were developed from literature and a manual review of limited posts was performed to identify the class and attributes (characteristics) of HL discussed on X, and create a gold standard dataset. This dataset was subsequently employed to train, test, and validate a Named Entity Recognition (NER) Natural Language Processing (NLP) application.

RESULTS

After data preparation, 80,811 posts were collected: 500 for annotation guideline development, 2,000 for NLP application development, and the remaining 78,311 for deploying the application. We identified nine classes related to HL, such as HL classification, etiopathology, stages and progression, and treatment. The treatment class and HL stages and progression were the most frequently discussed, with 20,013 (25.56%) posts mentioning HL's treatments and 17,177 (21.93%) mentioning HL stages and progression. The model exhibited robust performance, achieving 86% accuracy and an 87% F1 score. The etiopathology class demonstrated excellent performance, with 93% accuracy and a 95% F1 score.

DISCUSSION

The NLP application displayed high efficacy in extracting and characterizing HL-related information from social media posts, as evidenced by the high F1 score. Nonetheless, the data presented limitations in distinguishing between patients, providers, and caregivers and in establishing the temporal relationships between classes and attributes. Further research is necessary to bridge these gaps.

CONCLUSION

Our study demonstrated potential of using social media as a valuable preliminary research source for understanding the characteristics of rare diseases such as Hodgkin's Lymphoma.

A new scoring system to predict survival in elderly advanced stage Hodgkin lymphoma patients

Predictive prognostic scoring (PS) systems are not primarily applicable to elderly patients with classical Hodgkin lymphoma (cHL). The objective of this study was to develop a PS system for these patients. The derivation cohort (DC) was utilized for model development, consisting of 97 variables. The resulting algorithm was named as Hodgkin's Lymphoma Early Death in the Elderly within 12 months (HEDEL12). Internal and external validation cohorts (IVC and EVC) were employed for validation. A total of 286 patients were evaluated retrospectively. In DC 38 of 178 patients died within the first 12 months and overall survival (OS) at 12-month was 78.6%. Independent predictors of HEDEL12 were female sex, low albumin levels (<3.5 g/dL), and ECOG scores 2-4. According to HEDEL12 scores 0-1, OS at 12- months were 89.8% and 91.0% for IVC and EVC, respectively. The HEDEL12 scoring is useful in predicting the survival of advanced-stage cHL patients.

Overall survival and causes of death in elderly patients with Hodgkin lymphoma: a Norwegian population-based case-control study

Elderly Hodgkin lymphoma (HL) patients are poorly characterized and under-represented in studies. In this national population- based study, we investigated cause-specific survival using competing-risk analysis in elderly HL patients compared to the normal population. Patients ≥60 years of age diagnosed between 2000-2015 were identified by the Cancer Registry of Norway, and records were reviewed in detail and compared to data from the Norwegian Cause of Death Registry for patients and cancer-free controls. Of 492 patients, 81 (17%) were ineligible for treatment directed specifically towards HL, mostly because of an underlying other lymphoma entity, whereas 74 (15%) and 337 (69%) were treated with palliative or curative intent, respectively. Median overall survival in patients ineligible for assessment of HL-directed therapies was 0.5 years (95% Confidence Interval [CI]: 0.4-0.6), and for palliatively and curatively treated patients 0.8 (0.4-1.2) and 9.1 (7.5-10.7) years, respectively. After correction of discrepancies in registry data, with 359 deaths, 108 (30%) died of HL, the most common cause of death. In curatively treated patients, treatment-related mortality was 6.5% and the risk difference of dying from HL compared to controls was 28% (95% CI: 23-33%) after ten years. These numbers indicate disease control in a majority of elderly patients eligible for curative treatment, compared to risk differences for death from HL of 59% (48-71%) and 42% (31-53%) after ten years in the palliative and ineligible groups, respectively. There was an increased risk of dying from hematologic malignancies other than HL in all groups, but not from other competing causes of death, showing no excess mortality from long-term treatment complications.

Hodgkin lymphoma treatment for older persons in the modern era

There has been a renewed effort globally in the study of older Hodgkin lymphoma (HL) patients, generating a multitude of new data. For prognostication, advancing age, comorbidities, altered functional status, Hispanic ethnicity, and lack of dose intensity (especially without anthracycline) portend inferior survival. Geriatric assessments (GA), including activities of daily living (ADL) and comorbidities, should be objectively measured in all patients. In addition, proactive multidisciplinary medical management is recommended (eg, geriatrics, cardiology, primary care), and pre-phase therapy should be considered for most patients. Treatment for fit older HL patients should be given with curative intent, including anthracyclines, and bleomycin should be minimized (or avoided). Brentuximab vedotin given sequentially before and after doxorubicin, vinblastine, dacarbazine (AVD) chemotherapy for untreated patients is tolerable and effective, and frontline checkpoint inhibitor/AVD platforms are rapidly emerging. Therapy for patients who are unfit or frail, whether due to comorbidities and/or ADL loss, is less clear and should be individualized with consideration of attenuated anthracycline-based therapy versus lower-intensity regimens with inclusion of brentuximab vedotin +/- checkpoint inhibitors. For all patients, there should be clinical vigilance with close monitoring for treatment-related toxicities, including neurotoxicity, cardiopulmonary, and infectious complications. Finally, active surveillance for "postacute" complications 1 to 10 years post therapy, especially cardiac disease, is needed for cured patients. Altogether, therapy for older HL patients should include anthracycline-based therapy in most cases, and novel targeted agents should continue to be integrated into treatment paradigms, with more research needed on how best to utilize GAs for treatment decisions.

Understanding treatment decisions for Hodgkin lymphoma: a qualitative study

Hodgkin lymphoma (HL) affects older and younger patients and includes multiple options for initial treatment. We sought to examine the decision processes of practicing oncologists caring for patients with newly diagnosed HL. Through semi-structured interviews, we explored their perspectives about treatment decisions. We completed thematic analysis using the Anderson Behavioral Model of Health Services framework to identify factors associated with initial decisions. We completed 22 interviews, grouping findings into contextual factors, individual characteristics, and physician preferences. Paternalism was widely cited, along with collaboration between community and academic colleagues. Participants used sequential therapy but not geriatric assessment in care for older patients. Physicians had varied responses about use of frontline brentuximab vedotin (Bv)-based therapy based on perceptions about benefit versus toxicity. Our work suggests a need to further understand the heterogeneity of clinical practices, especially in the post-approval setting of new therapies.

The Advanced-Stage Hodgkin Lymphoma International Prognostic Index: Development and Validation of a Clinical Prediction Model From the HoLISTIC Consortium

PURPOSE

The International Prognostic Score (IPS) has been used in classic Hodgkin lymphoma (cHL) for 25 years. However, analyses have documented suboptimal performance of the IPS among contemporarily treated patients. Harnessing multisource individual patient data from the Hodgkin Lymphoma International Study for Individual Care consortium, we developed and validated a modern clinical prediction model.

METHODS

Model development via Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guidelines was performed on 4,022 patients with newly diagnosed advanced-stage adult cHL from eight international phase III clinical trials, conducted from 1996 to 2014. External validation was performed on 1,431 contemporaneously treated patients from four real-world cHL registries. To consider association over a full range of continuous variables, we evaluated piecewise linear splines for potential nonlinear relationships. Five-year progression-free survival (PFS) and overall survival (OS) were estimated using Cox proportional hazard models.

RESULTS

The median age in the development cohort was 33 (18-65) years; nodular sclerosis was the most common histology. Kaplan-Meier estimators were 0.77 for 5-year PFS and 0.92 for 5-year OS. Significant predictor variables included age, sex, stage, bulk, absolute lymphocyte count, hemoglobin, and albumin, with slight variation for PFS versus OS. Moreover, age and absolute lymphocyte count yielded nonlinear relationships with outcomes. Optimism-corrected c-statistics in the development model for 5-year PFS and OS were 0.590 and 0.720, respectively. There was good discrimination and calibration in external validation and consistent performance in internal-external validation. Compared with the IPS, there was superior discrimination for OS and enhanced calibration for PFS and OS.

CONCLUSION

We rigorously developed and externally validated a clinical prediction model in > 5,000 patients with advanced-stage cHL. Furthermore, we identified several novel nonlinear relationships and improved the prediction of patient outcomes. An online calculator was created for individualized point-of-care use.

Older patients with Hodgkin Lymphoma: Walking the tightrope of efficacy and toxicity

Since its initial description, classical Hodgkin lymphoma (cHL) portends a greatly improved prognosis and the goal of treatment in most patients is cure with minimisation of toxicity from treatment. Outcomes in older patients (>60 years old) lag behind those of their younger counterparts however, and cure remains achievable mostly for those who can tolerate full doses of conventional chemotherapy. This review addresses the difference in biology between younger and older patients with cHL and examines the impact of frailty and comorbidities on outcomes. The toxicities of conventional chemotherapy in anthracycline-fit and -unfit patients are examined, with a particular focus on pulmonary toxicity associated with bleomycin in older patients. New advances are discussed, including the possibility of using more targeted therapies such as the anti-CD30 antibody brentuximab vedotin (BV) and checkpoint inhibitors as a method of reducing dependency on conventional chemotherapy for those less well able to tolerate it. Treatment of older patients with cHL remains an area of unmet need in hematological research, and efforts to rectify this knowledge gap should continue.

Clinical Dilemmas in the Treatment of Elderly Patients Suffering from Hodgkin Lymphoma: A Review

Elderly patients make up a significant number of cases of newly diagnosed Hodgkin lymphoma. However, unlike in young patients, the outcomes of elderly patients are poor, and they are under-represented in phase III trials. Prior to treatment initiation, geriatric assessment should ideally be performed to address the patient's fitness and decide whether to pursue a curative or palliative approach. The ABVD regimen is poorly tolerated in unfit patients, with high treatment-related mortality. Alternative chemotherapy approaches have been explored, with mixed results obtained concerning their feasibility and toxicity in phase II trials. The introduction of brentuximab vedotin-based regimens led to a paradigm shift in first- and further-line treatment of elderly Hodgkin lymphoma patients, providing adequate disease control within a broader patient population. As far as checkpoint inhibitors are concerned, we are only just beginning to understand the role in the treatment of this population. In relapsed/refractory settings there are few options, ranging from autologous stem cell transplantation in selected patients to pembrolizumab, but unfortunately, palliative care is the most common modality. Importantly, published studies are frequently burdened with numerous biases (such as low numbers of patients, selection bias and lack of geriatric assessment), leading to low level of evidence. Furthermore, there are few ongoing studies on this topic. Thus, elderly Hodgkin lymphoma patients are hard to treat and represent an unmet need in hematologic oncology. In conclusion, treatment needs to be personalized and tailored on a case-by-case basis. In this article, we outline treatment options for elderly Hodgkin lymphoma patients.