Machine Learning-Based Survival Prediction Models for Progression-Free and Overall Survival in Advanced-Stage Hodgkin Lymphoma.

PURPOSE: Patients diagnosed with advanced-stage Hodgkin lymphoma (aHL) have historically been risk-stratified using the International Prognostic Score (IPS). This study investigated if a machine learning (ML) approach could outperform existing models when it comes to predicting overall survival (OS) and progression-free survival (PFS). PATIENTS AND METHODS: This study used patient data from the Danish National Lymphoma Register for model development (development cohort). The ML model was developed using stacking, which combines several predictive survival models (Cox proportional hazard, flexible parametric model, IPS, principal component, penalized regression) into a single model, and was compared with two versions of IPS (IPS-3 and IPS-7) and the newly developed aHL international prognostic index (A-HIPI). Internal model validation was performed using nested cross-validation, and external validation was performed using patient data from the Swedish Lymphoma Register and Cancer Registry of Norway (validation cohort). RESULTS: In total, 707 and 760 patients with aHL were included in the development and validation cohorts, respectively. Examining model performance for OS in the development cohort, the concordance index (C-index) for the ML model, IPS-7, IPS-3, and A-HIPI was found to be 0.789, 0.608, 0.650, and 0.768, respectively. The corresponding estimates in the validation cohort were 0.749, 0.700, 0.663, and 0.741. For PFS, the ML model achieved the highest C-index in both cohorts (0.665 in the development cohort and 0.691 in the validation cohort). The time-varying AUCs for both the ML model and the A-HIPI were consistently higher in both cohorts compared with the IPS models within the first 5 years after diagnosis. CONCLUSION: The new prognostic model for aHL on the basis of ML techniques demonstrated a substantial improvement compared with the IPS models, but yielded a limited improvement in predictive performance compared with the A-HIPI.

Long-term prescribed drug use in stage I-III rectal cancer patients in Sweden, with a focus on bowel-regulating drugs after surgical and oncological treatment.

PURPOSE: To describe long-term prescribed drug use after rectal cancer treatment. METHODS: We identified 12,871 rectal cancer patients without distant metastasis between 2005 and 2016 and 64,341 matched population comparators using CRCBaSe (a Swedish nationwide register linkage of colorectal cancer patients). Mean defined daily doses (DDDs) of drug dispensing during relapse-free follow-up were calculated by Anatomical Therapeutic Chemical drug categories. Incidence rate ratios (IRRs) and 95% confidence intervals (CIs) from negative binomial regression were used to compare drug dispensing between patients and comparators. RESULTS: The overall pattern of drug dispensing was similar among cancer survivors and comparators, although patients had higher mean DDDs of drugs regulating the digestive system. Excess dispensing of drugs for constipation (IRR, 3.35; 95% CI, 3.12-3.61), diarrhea (IRR, 6.43; 95% CI, 5.72-7.22), functional gastrointestinal disorders (IRR, 3.78; 95% CI, 3.15-4.54), and vitamin and mineral supplements (IRR, 1.37; 95% CI, 1.24-1.50) was observed up to 10 years after surgery. Treatment with Hartmann's procedure was associated with higher dispensing rates of digestive drugs compared to surgery with anterior resection and abdominoperineal resection but the association was attributed to higher use of diabetic drugs. Additionally, excess digestive drug dispensing was associated with more advanced cancer stage but not with (chemo)radiotherapy treatment. CONCLUSIONS: Excess drug use after rectal cancer is primarily driven by bowel-regulating drugs and is not modified by surgical or oncological treatment. IMPLICATIONS FOR CANCER SURVIVORS: The excess use of bowel-regulating drugs after rectal cancer indicated long-standing postsurgical gastrointestinal morbidity and need of prophylaxis. Reassuringly, no excess use of other drug classes was noted long term.

Cardiovascular diseases after high-dose chemotherapy and autologous stem cell transplant for lymphoma: A Danish population-based study.

Cardiovascular diseases, especially congestive heart failure (CHF), are known complications of anthracyclines, but the risk for patients undergoing high-dose chemotherapy and autologous stem cell transplant (HDT-ASCT) is not well established. With T-cell therapies emerging as alternatives, studies of long-term complications after HDT-ASCT are warranted. Danish patients treated with HDT-ASCT for aggressive lymphoma between 2001 and 2017 were matched 1:5 on sex, birth year and Charlson comorbidity score to the general population. Events were captured using nationwide registers. A total of 787 patients treated with HDT-ASCT were identified. Median follow-up was 7.6 years. The risk of CHF was significantly increased in the HDT-ASCT population compared to matched comparators with an adjusted hazard ratio (HR) of 5.5 (3.8-8.1). The 10-year cumulative incidence of CHF was 8.0% versus 2.0% (p < 0.001). Male sex, ≥2 lines of therapy, hypertension and cumulative anthracycline dose (≥300 mg/m2 ) were risk factors for CHF. In a separate cohort of 4089 lymphoma patients, HDT-ASCT was also significantly associated with increased risk of CHF (adjusted HR of 2.6 [1.8-3.8]) when analysed as a time-dependent exposure. HDT-ASCT also increased the risk of other cardiac diseases. These findings are applicable for the benefit/risk assessment of HDT-ASCT versus novel therapies.

ProFertil study protocol for the investigation of gonadotropin-releasing hormone agonists (GnRHa) during chemotherapy aiming at fertility protection of young women and teenagers with cancer in Sweden-a phase III randomised double-blinded placebo-controlled study.

BACKGROUND: Gonadotropin-releasing hormone agonists (GnRHa) cotreatment used to transiently suppress ovarian function during chemotherapy to prevent ovarian damage and preserve female fertility is used globally but efficacy is debated. Most clinical studies investigating a beneficial effect of GnRHa cotreatment on ovarian function have been small, retrospective and uncontrolled. Unblinded randomised studies on women with breast cancer have suggested a beneficial effect, but results are mixed with lack of evidence of improvement in markers of ovarian reserve. Unblinded randomised studies of women with lymphoma have not shown any benefit regarding fertility markers after long-term follow-up and no placebo-controlled study has been conducted so far. The aim of this study is to investigate if administration of GnRHa during cancer treatment can preserve fertility in young female cancer patients in a double-blind, placebo-controlled clinical trial. METHODS AND ANALYSIS: A prospective, randomised, double-blinded, placebo-controlled, phase III study including 300 subjects with breast cancer. In addition, 200 subjects with lymphoma, acute leukemias and sarcomas will be recruited. Women aged 14-42 will be randomised 1:1 to treatment with GnRHa (triptorelin) or placebo for the duration of their gonadotoxic chemotherapy. Follow-up until 5 years from end of treatment (EoT). The primary endpoint will be change in anti-Müllerian hormone (AMH) recovery at follow-up 12 months after EoT, relative to AMH levels at EoT, comparing the GnRHa group and the placebo group in women with breast cancer. ETHICS AND DISSEMINATION: This study is designed in accordance with the principles of Good Clinical Practice (ICH-GCP E6 (R2)), local regulations (ie, European Directive 2001/20/EC) and the ethical principles of the Declaration of Helsinki. Within 6 months of study completion, the results will be analysed and the study results shall be reported in the EudraCT database. STUDY REGISTRATION: The National Institutional review board in Sweden dnr:2021-03379, approval date 12 October 2021 (approved amendments 12 June 2022, dnr:2022-02924-02 and 13 December 2022, dnr:2022-05565-02). The Swedish Medical Product Agency 19 January 2022, Dnr:5.1-2021-98927 (approved amendment 4 February 2022). Manufacturing authorisation for authorised medicinal products approved 6 December 2021, Dnr:6.2.1-2020-079580. Stockholm Medical Biobank approved 22 June 2022, RBC dnr:202 253. TRIAL REGISTRATION NUMBER: NCT05328258; EudraCT number:2020-004780-71.

Secondary malignancies among mantle cell lymphoma patients.

PURPOSE: With modern treatments, mantle cell lymphoma (MCL) patients more frequently experience long-lasting remission resulting in a growing population of long-term survivors. Follow-up care includes identification and management of treatment-related late-effects, such as secondary malignancies (SM). We conducted a population-based study to describe the burden of SM in MCL patients. METHODS: All patients with a primary diagnosis of MCL, aged ≥ 18 years and diagnosed between 2000 and 2017 in Sweden were included along with up to 10 individually matched population comparators. Follow-up was from twelve months after diagnosis/matching until death, emigration, or December 2019, whichever occurred first. Rates of SM among patients and comparators were estimated using the Anderson-Gill method (accounting for repeated events) and presented as hazard ratios (HR) with 95% confidence intervals (CI) adjusted for age at diagnosis, calendar year, sex, and the number of previous events. RESULTS: Overall, 1 452 patients and 13 992 comparators were followed for 6.6 years on average. Among patients, 230 (16%) developed at least one SM, and 264 SM were observed. Relative to comparators, patients had a higher rate of SM, HRadj= 1.6 (95%CI:1.4-1.8), and higher rates were observed across all primary treatment groups: the Nordic-MCL2 protocol, R-CHOP, R-bendamustine, ibrutinib, lenalidomide, and R-CHOP/Cytarabine. Compared to Nordic-MCL2, treatment with R-bendamustine was independently associated with an increased risk of SM, HRadj= 2.0 (95%CI:1.3-3.2). Risk groups among patients were those with a higher age at diagnosis (p < 0.001), males (p = 0.006), and having a family history of lymphoma (p = 0.009). Patients had preferably higher risk of melanoma, other neoplasms of the skin and other hematopoietic and lymphoid malignancies. CONCLUSIONS: MCL survivors have an increased risk of SM, particularly if treated with R-bendamustine. The intensive treatments needed for long-term remissions are a concern, and transition to treatment protocols with sustained efficacy but with a lower risk of SM is needed.

Second primary malignancies in patients with lymphoma in Denmark after high-dose chemotherapy and autologous haematopoietic stem-cell transplantation: a population-based, retrospective cohort study.

BACKGROUND: Second primary malignancies (SPMs) are known complications after chemotherapy, but the risk is not well characterised for patients with lymphoma treated with high-dose chemotherapy and autologous haematopoietic stem-cell transplantation (HSCT). We aimed to investigate the rate of SPMs in this population relative to matched control individuals from the general population. METHODS: In this retrospective, population-based cohort study, patients aged 18 years or older with an aggressive lymphoma who received high-dose chemotherapy and autologous HSCT in Denmark between Jan 1, 2001, and Dec 31, 2017, were included from the Danish Lymphoma Registry and matched (1:5) to control individuals from the general population on birth year and sex via the Danish Civil Registration System. Patients were eligible if they had a registered date of autologous HSCT and patients with primary CNS lymphoma were excluded. Exclusion criteria for both patients and matched control individuals were HIV infection, organ transplantation, or other malignancies before inclusion. The key endpoint was the incidence of SPMs assessed in all study participants. The effect of treatment on SPMs was also investigated in patients who were followed up from first lymphoma diagnosis, with high-dose chemotherapy and autologous HSCT as a time-dependent exposure. FINDINGS: Of 910 patients with lymphoma assessed, 803 were included (537 [67%] were male and 266 [33%] were female); 4015 matched control individuals were included (2685 [67%] were male and 1330 [33%] were female). Ethnicity data were not available. Median follow-up was 7·76 years (IQR 4·77-11·73). The SPM rate was higher among patients receiving high-dose chemotherapy and autologous HSCT than matched control individuals (adjusted hazard ratio [HR] 2·35, 95% CI 1·93-2·87, p<0·0001). Patients receiving high-dose chemotherapy and autologous HSCT had a higher rate of non-melanoma skin cancer (2·94, 2·10-4·11, p<0·0001) and of myelodysplastic syndrome or acute myeloid leukaemia (AML; 41·13, 15·77-107·30, p<0·0001) than matched control individuals, but there was no significant difference in the rate of solid tumours (1·21, 0·89-1·64, p=0·24). The cumulative risk of SPMs at 10 years was 20% (95% CI 17-23) in patients compared with 14% (13-15) in matched control individuals. High-dose chemotherapy and autologous HSCT was associated with an increased risk of SPMs when analysed as a time-dependent exposure from first lymphoma diagnosis (adjusted HR 1·58, 95% CI 1·14-2·17, p=0·0054). INTERPRETATION: High-dose chemotherapy and autologous HSCT was associated with an increased risk of non-melanoma skin cancer and myelodysplastic syndrome or AML but not with increased risk of solid tumours in patients treated for lymphoma. These findings are relevant for future individualised risk-benefit assessments when choosing between high-dose chemotherapy and autologous HSCT and chimeric antigen receptor T-cell therapy in this setting. FUNDING: Danish Cancer Society.

Reproduction patterns among non-Hodgkin lymphoma survivors by subtype in Sweden, Denmark and Norway: A population-based matched cohort study.

Previous studies concerning reproductive patterns among non-Hodgkin lymphoma (NHL) survivors are scarce and those available have reported conflicting results. Treatment regimens vary considerably between aggressive and indolent NHL and studies of reproductive patterns by subtypes are warranted. In this matched cohort study, we identified all NHL patients aged 18-40 years and diagnosed between 2000 and 2018 from the Swedish and Danish lymphoma registers, and the clinical database at Oslo University Hospital (n = 2090). Population comparators were matched on sex, birth year and country (n = 19 427). Hazard ratios (HRs) were estimated using Cox regression. Males and females diagnosed with aggressive lymphoma subtypes had lower childbirth rates (HRfemale : 0.43, 95% CI: 0.31-0.59, HRmale : 0.61, 95% CI: 0.47-0.78) than comparators during the first 3 years after diagnosis. For indolent lymphomas, childbirth rates were not significantly different from comparators (HRfemale : 0.71, 95% CI: 0.48-1.04, HRmale : 0.94, 95% CI: 0.70-1.27) during the same period. Childbirth rates reached those of comparators for all subtypes after 3 years but the cumulative incidence of childbirths was decreased throughout the 10-year follow-up for aggressive NHL. Children of NHL patients were more likely to be born following assisted reproductive technology than those of comparators, except for male indolent lymphoma patients. In conclusion, fertility counselling is particularly important for patients with aggressive NHL.

Reproduction patterns among classical Hodgkin lymphoma survivors treated with BEACOPP and ABVD in Sweden, Denmark and Norway-A population-based matched cohort study.

Childbirth rates in classical Hodgkin lymphoma (cHL) survivors have historically been reduced compared to the general population. Understanding if contemporary treatment protocols are associated with reduced fertility is crucial as treatment guidelines shift toward more liberal use of intensive chemotherapy. We identified 2834 individuals aged 18-40 years with cHL in Swedish and Danish lymphoma registers, and in the clinical database at Oslo University Hospital diagnosed 1995-2018, who were linked to national medical birth registers. Cox regression adjusted for stage, performance status, year, and age at diagnosis was used to estimate hazard ratios (HRs) and 95% confidence intervals (CI) contrasting time to first childbirth by treatment groups (ABVD, 2-4 BEACOPP, 6-8 BEACOPP) up to 10 years after diagnosis. Overall, 74.8% of patients were treated with ABVD, 3.1% with 2-4 BEACOPP and 11.2% with 6-8 BEACOPP. Adjusted HRs comparing childbirth rates in individuals treated with 6-8 BEACOPP, and 2-4 BEACOPP to ABVD were 0.53 (CI: 0.36-0.77) and 0.33 (CI: 0.12-0.91) for males, and 0.91 (CI: 0.61-1.34) and 0.38 (CI: 0.12-1.21) for females. Cumulative incidence of childbirths after 10 years was 19.8% (CI: 14.5%-27.0%) for males and 34.3% (CI: 25.8%-45.6%) for females treated with 6-8 BEACOPP. Proportions of children born after assisted reproductive technique (ART) treatments were 77.4% (CI: 60.2-88.6%) for males following 6-8 BEACOPP, and <11% for females. Among ABVD treated patients the corresponding proportions were 12.2% (CI: 8.5%-17.3%) and 10.6% (CI: 7.4%-14.9%). BEACOPP treatment is associated with decreased childbirth rates compared to ABVD in male, but not female, cHL patients, despite widespread access to ART in the Nordics.

Data-driven support to decision-making in molecular tumour boards for lymphoma: A design science approach.

Background: The increasing amount of molecular data and knowledge about genomic alterations from next-generation sequencing processes together allow for a greater understanding of individual patients, thereby advancing precision medicine. Molecular tumour boards feature multidisciplinary teams of clinical experts who meet to discuss complex individual cancer cases. Preparing the meetings is a manual and time-consuming process. Purpose: To design a clinical decision support system to improve the multimodal data interpretation in molecular tumour board meetings for lymphoma patients at Karolinska University Hospital, Stockholm, Sweden. We investigated user needs and system requirements, explored the employment of artificial intelligence, and evaluated the proposed design with primary stakeholders. Methods: Design science methodology was used to form and evaluate the proposed artefact. Requirements elicitation was done through a scoping review followed by five semi-structured interviews. We used UML Use Case diagrams to model user interaction and UML Activity diagrams to inform the proposed flow of control in the system. Additionally, we modelled the current and future workflow for MTB meetings and its proposed machine learning pipeline. Interactive sessions with end-users validated the initial requirements based on a fictive patient scenario which helped further refine the system. Results: The analysis showed that an interactive secure Web-based information system supporting the preparation of the meeting, multidisciplinary discussions, and clinical decision-making could address the identified requirements. Integrating artificial intelligence via continual learning and multimodal data fusion were identified as crucial elements that could provide accurate diagnosis and treatment recommendations. Impact: Our work is of methodological importance in that using artificial intelligence for molecular tumour boards is novel. We provide a consolidated proof-of-concept system that could support the end-to-end clinical decision-making process and positively and immediately impact patients. Conclusion: Augmenting a digital decision support system for molecular tumour boards with retrospective patient material is promising. This generates realistic and constructive material for human learning, and also digital data for continual learning by data-driven artificial intelligence approaches. The latter makes the future system adaptable to human bias, improving adequacy and decision quality over time and over tasks, while building and maintaining a digital log.

Cardiovascular, bone, and metabolic health in men with castrate-resistant prostate cancer treated with androgen deprivation: a matched cohort study.

BACKGROUND: Descriptive data on late effects associated with castrate-resistant prostate cancer (CRPC) are sparse. We aimed to define the timing and incidence of cardiovascular disease (CVD), fractures, and diabetes in a patient population with CRPC. METHODS: In the population-based STHLM0 cohort 1464 men with CRPC were identified and matched with three men free from prostate cancer (PC) in the Stockholm region of Sweden. Kaplan-Meier estimates of net survival were used to describe time to CVD, fracture, and diabetes. Cox regression was used to compare incidence rates (IRRs) for the respective late effects. Cumulative incidence analyses of late effects in the presence of the competing risk of death were performed to estimate absolute risks. RESULTS: The Kaplan Meier estimates demonstrated a higher net probability for CVD, fracture, and diabetes among men diagnosed with CRPC compared to the matched comparators. The IRRs were 1.94 (95% CI: 1.79-2.12) for CVD, 2.08 (95% CI: 1.70-2.53) for fracture, and 2.00 (95% CI: 1.31-3.05) for diabetes, respectively, comparing men diagnosed with CRPC to men free from PC. The cumulative incidence of CVD at 12 months of follow-up was higher in men diagnosed with CRPC compared to healthy controls regardless of age with a difference in cumulative incidence being 0.20 for men aged <65 and 0.11 for men aged >84. CONCLUSIONS: In this cohort, the incidence of CVD was significantly higher among men with CRPC compared to healthy controls. Despite having this end-stage disease this finding proves that clinicians must recognize this late effect in men diagnosed with CRPC to improve preventive actions. These men did not have a higher absolute risk of fractures and diabetes after accounting for deaths due to any cause compared to healthy controls.

Patient trajectories after diagnosis of diffuse large B-cell lymphoma-a multistate modelling approach to estimate the chance of lasting remission.

BACKGROUND: Achieving lasting remission for at least 2 years is a good indicator for favourable prognosis long term after Diffuse large B-cell lymphoma (DLBCL). The aim of this study was to provide real-world probabilities, useful in risk communication and clinical decision-making, of the chance for lasting remissions by clinical characteristics. METHODS: DLBCL patients in remission after primary treatment recorded in the Swedish Lymphoma register 2007-2014 (n = 2941) were followed for relapse and death using multistate models to study patient trajectories. Flexible parametric models were used to estimate transition rates. RESULTS: At 2 years, 80.7% (95% CI: 79.0-82.2) of the patients were predicted to remain in remission and 13.2% (95% CI: 11.9-14.6) to have relapsed. The relapse risk peaked at 7 months, and the annual decline of patients in remission stabilised after 2 years. The majority of patients in the second remission transitioned into a new relapse. The probability of a lasting remission was reduced by 20.4% units for patients with IPI 4-5 compared to patients with IPI 0-1, and time in remission was shortened by 3.5 months. CONCLUSION: The long-term prognosis was overall favourable with 80% achieving durable first remissions. However, prognosis varied by clinical subgroups and relapsing patients seldom achieved durable second remissions.

Risk of diabetes and the impact on preexisting diabetes in patients with lymphoma treated with steroid-containing immunochemotherapy.

First-line treatments for lymphomas often include high doses of prednisolone, but the risks of new-onset diabetes mellitus (DM) or worsening of preexisting DM following treatment with cyclic high dose corticosteroids is unknown. This cohort study matched non-Hodgkin lymphoma (NHL) patients treated with steroid-containing immunochemotherapy (ie, R-CHOP[-like] and R-CVP) between 2002 and 2015 to individuals from the Danish population to investigate the risks of new-onset DM. For patients with preexisting DM, the risks of insulin dependency and anthracycline-associated cardiovascular diseases (CVDs) were assessed. In total, 5672 NHL patients and 28 360 matched comparators were included. Time-varying incidence rate ratios (IRRs) showed increased risk of DM in the first year after treatment compared with matched comparators, with the highest IRR being 2.7. The absolute risks were higher among patients in the first 2 years, but the difference was clinically insignificant. NHL patients with preexisting DM had increased risks of insulin prescriptions with 0.5-, 5-, and 10-year cumulative risk differences of insulin treatment of 15.3, 11.8, and 6.0 percentage units as compared with the DM comparators. In a landmark analysis at 1 year, DM patients with lymphoma had decreased risks of insulin dependency compared with comparators. Time-varying IRRs showed a higher CVD risk for NHL patients with DM as compared with comparators in the first year after treatment. NHL patients treated with steroid-containing immunochemotherapy regimens have a clinically insignificant increased risk of DM in the first year following treatment, and patients with preexisting DM have a temporary increased risk of insulin prescriptions and CVD.

Outcomes of relapsed/refractory diffuse large B-cell lymphoma and influence of chimaeric antigen receptor T trial eligibility criteria in second line-A population-based study of 736 patients.

Several recently published trials investigate novel therapies for relapsed/refractory diffuse large B-cell lymphoma (R/R DLBCL). To estimate the benefit of these therapies in the real-world setting, comprehensive data on patients treated in clinical routine are needed. We report outcomes for 736 R/R DLBCL patients identified among all curatively treated DLBCL patients in Sweden in the period 2007-2014. Survival and associations with disease characteristics, second-line treatment and fulfilment of chimaeric antigen receptor (CAR) T-cell trial criteria were assessed. Median overall survival (OS) was 6.6 months (≤70 years 9.6 months, >70 years 4.9 months). Early relapse (≤12 months) was strongly associated with selection of less intensive treatment and poor survival. Among patients of at most 70 years of age, 63% started intensive second-line treatment and 34% received autologous stem cell transplantation (ASCT). Two-year OS among transplanted patients was 56% (early relapse ≤12 months 40%, late relapse >12 months 66%). A minority of patients 76 years (n = 178/506, 35%) fitted CAR T trial criteria. Median progression-free survival (PFS) for patients with early relapse fitting trial criteria was 4.8 months. In conclusion, most R/R DLBCL manifest early and are often ineligible for or cannot complete intensive regimens resulting in dismal survival. Real-world patients eligible for CAR T trials also did poorly, providing a benchmark for efficacy of novel therapies.

Reproductive history, as measured by parity, age at first birth and sex of offspring, and cancer-specific survival after a haematological malignancy.

BACKGROUND: Overall, women have better cancer-specific survival than men following haematological malignancies. The effect of reproductive factors on prognosis in women remains unknown and population-based studies are needed. MATERIAL AND METHODS: A nationwide cohort of 21,237 Swedish women with a recorded haematological malignancy at ages 18-69 years was identified in the Swedish Cancer Register 1970-2018. Pre-diagnosis childbirths for each woman were linked to the Swedish Multigeneration Register. Net survival and excess hazard ratios for parity, age at first birth, time since the latest birth, and sex of offspring were estimated using flexible parametric models adjusted for age, year, and educational level. RESULTS: In unadjusted analyses, parity (p = 0.0012) and high age at first birth (p < 0.0001) were associated with better survival. After co-adjustments for reproductive factors and confounders, the associations were attenuated. The adjusted association with parity was mainly observed among women aged above 40 years at diagnosis (p = 0.0033). The associations with reproductive factors were non-significant across subtypes of haematological malignancy. There was a tendency of higher excess mortality for an increasing number of boys compared to girls, although only significant for women with three or more children (p = 0.0126). CONCLUSION: Reproductive factors were in part associated with survival following diagnosis of a haematological malignancy. However, the effect sizes were small with inconsistent association patterns, and thus reproductive factors may only partly contribute to the survival advantage of women over men.

Predictive models for clinical decision making: Deep dives in practical machine learning.

The deployment of machine learning for tasks relevant to complementing standard of care and advancing tools for precision health has gained much attention in the clinical community, thus meriting further investigations into its broader use. In an introduction to predictive modelling using machine learning, we conducted a review of the recent literature that explains standard taxonomies, terminology and central concepts to a broad clinical readership. Articles aimed at readers with little or no prior experience of commonly used methods or typical workflows were summarised and key references are highlighted. Continual interdisciplinary developments in data science, biostatistics and epidemiology also motivated us to further discuss emerging topics in predictive and data-driven (hypothesis-less) analytics with machine learning. Through two methodological deep dives using examples from precision psychiatry and outcome prediction after lymphoma, we highlight how the use of, for example, natural language processing can outperform established clinical risk scores and aid dynamic prediction and adaptive care strategies. Such realistic and detailed examples allow for critical analysis of the importance of new technological advances in artificial intelligence for clinical decision-making. New clinical decision support systems can assist in prevention and care by leveraging precision medicine.

Prevalence and comorbidity of psychiatric disorders among treatment-seeking elite athletes and high-performance coaches.

Objectives: Few studies have evaluated the prevalence of psychiatric disorders among treatment-seeking elite athletes (EA) or high-performance coaches (HPC) in psychiatric outpatient settings. Methods: Descriptive overview of EA and HPC with psychiatric disorders at two publicly funded psychiatric outpatient treatment clinics in Stockholm and Malmö, Sweden. Co-occurring psychiatric disorders were illustrated using Venn diagrams for EA and HPC, and male and female EA separately, among patients from the Stockholm clinic (SC) that used standardised diagnostic interviews. Results: Overall, most patients were EA (n=221) compared with HPC (n=34). The mean age was 23.5 (±5.9) years for EA and 42.8 (±8.8) for HPC. Anxiety disorders were most common at the SC in EA and HPC (69% vs 91%, respectively). Stress-related disorders were found in 72% of HPC compared with 25% of EA. Affective disorders were found in 51% of EA and 52% of HPC. Eating disorders were common among EA (26%), especially females (37%). Substance use disorders were found in 17% of HPC. Comorbidity was generally common between affective and anxiety disorders. Conclusion: Stress and adjustment disorders were found in nearly three of the four HPC compared with one in four EA. Eating disorders were prevalent in around one in four athletes and about one in six HPC had a substance use disorder.

Incidence and time trends of second primary malignancies after non-Hodgkin lymphoma: a Swedish population-based study.

Considering treatment changes and an improved prognosis of non-Hodgkin lymphoma (NHL) over time, knowledge regarding long-term health outcomes, including late effects of treatment, has become increasingly important. We report on time trends of second primary malignancies (SPMs) in Swedish NHL patients, encompassing the years before as well as after the introduction of anti-CD20 antibody therapy. We identified NHL patients in the Swedish Cancer Register 1993 to 2014 and matched comparators from the Swedish Total Population Register. The matched cohort was followed through 2017. By linking to the Swedish Lymphoma Register, subcohort analyses by NHL subtype were performed. Flexible parametric survival models were used to estimate hazard ratios (HRs) with 95% confidence intervals (CIs) of SPM among patients and comparators. Among 32 100 NHL patients, 3619 solid tumors and 217 myelodysplastic syndrome (MDS)/acute myeloid leukemia (AML) cases were observed, corresponding to a 40% higher rate of solid tumors (HRsolid tumors = 1.4; 95% CI, 1.4-1.5) and a 5-fold higher rate of MDS/AML (HRMDS/AML = 5.2; 95% CI, 4.4-6.2) than for comparators. Overall, the observed excess risks for solid tumors or MDS/AML remained stable over the study period, except for follicular lymphoma, where the excess rate of MDS/AML attenuated with time (P for trend = .012). We conclude that NHL survivors have an increased risk of both solid tumors and hematologic malignancies, in particular MDS/AML. Stable excess risks over time indicate that contemporary treatment standards are not associated with modified SPM risk. Encouragingly, decreasing rates of MDS/AML were noted among patients with follicular lymphoma, possibly due to the increasing use of nonchemotherapy-based treatments.

Patients in complete remission after R-CHOP(-like) therapy for diffuse large B-cell lymphoma have limited excess use of health care services in Denmark.

For most patients with newly diagnosed diffuse large B-cell lymphoma (DLBCL), R-CHOP immunochemotherapy leads to complete remission and 60-70% of patients remain progression-free after 5 years. Given a median age of 65, it is relevant to disentangle how DLBCL and DLBCL therapy influence health care use among the survivors. In this nationwide study, the health care use among Danish DLBCL patients diagnosed in 2007-2015, who achieved complete remission after R-CHOP(-like) therapy, was explored and compared to matched comparators from the Danish general population. The post-remission 5-year risk of hospitalization was significantly higher among DLBCL survivors (55%) compared to matched comparators (49%, P < 0.001). DLBCL survivors had on average 10.3 (9.3-11.3) inpatient bed days within 5 years of response evaluation, whereas matched comparators had 8.4 (7.9-8.8). The rate of outpatient visits was also significantly higher(excluding routine follow-up visits, incidence rate ratio, 1.3, P < 0.001), but translated into only a very small absolute difference of <1 outpatient visits within 5 years between DLBCL survivors (4.2 visits, 95% CI, 4.0-4.4) and matched comparators (3.8 visits, 95% CI, 3.7-3.9). In conclusion, DLBCL survivors have an increased incidence of hospital visits due to a wide range of conditions, but in absolute terms the excess use of health care services in DLBCL survivors was small.

Statin use and survival in 16 098 patients with non-Hodgkin lymphoma or chronic lymphocytic leukaemia treated in the rituximab era.

Statin use has been associated with reduced mortality from several cancers but also suggested, in vitro, to diminish the effectiveness of lymphoma treatments including rituximab. The present study aimed to assess the association of statin use with mortality in patients with non-Hodgkin lymphoma (NHL) and chronic lymphocytic leukaemia (CLL). We identified all incident NHLs and CLLs in Sweden from 2007 to 2013 with subtype information in the Swedish Lymphoma and Cancer Registers. Using Cox regression, we estimated hazard ratios (HRs) and 95% confidence intervals (CIs) for the association of pre- or post-diagnosis statin use (yes/no, intensity) with lymphoma-specific, cardiovascular, or all-cause mortality; and for follicular lymphoma (FL) by initial treatment strategy (active/watch-and-wait). Among 16 098 incident NHL/CLL patients, 20% used statins at diagnosis. Pre- and post-diagnosis statin use, and statin intensity were not consistently associated with any mortality outcome in patients with NHL, overall or for any subtype. For actively treated patients with FL, statin use did not appear to increase lymphoma-specific mortality (vs. non-users, HR [95% CI]after diagnosis 0·87 [0·45-1·67]). For CLL, statin use was associated with all-cause and cardiovascular but not consistently with lymphoma-specific mortality. In conclusion, statin use was not associated with improved lymphoma survival but appears safe to use during lymphoma treatment.