Search

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., QC 20230124

There is a lack of data regarding treatment and prognosis for the growing group of oldest old patients with lymphoma. Therefore, we studied 2347 patients aged >= 85 years from the Danish and Swedish lymphoma registers 2000-2016 (Denmark) and 2007-2013 (Sweden). Outcome was assessed using relative survival (RS). The 2-year RS overall for patients with aggressive lymphomas was 38% [95% confidence interval (CI) 35-42%], of whom 845 (66%) patients received active treatment (chemotherapy, radiotherapy, immunotherapy, other). For aggressive lymphomas, not receiving active treatment was associated with an inferior 2-year RS of 12% (95% CI 9-17%) compared to 49% (95% CI 45-53%) for patients who received active treatment (excess mortality rate ratio 2 center dot 84, 95% CI 2 center dot 3-3 center dot 5; P < 0 center dot 0001). For patients with indolent lymphoma, the 2-year RS was 77% (95% CI 72-82%). Here, 383 (46%) patients received active treatment at diagnosis, but did not have better 2-year RS (75%, 95% CI 67-81%) compared to those who did not receive active treatment (83%, 95% CI 74-89%). We conclude that outcomes for the oldest old patients with lymphoma are encouraging for several subtypes and that active treatment is associated with improved outcome amongst the oldest old patients with aggressive lymphomas, indicating that age itself should not be a contraindication to treatment.

The prognosis for mantle cell lymphoma (MCL) remains poor. Our aim was to assess the impact of comorbidities on survival and causes of death. For 1,385 MCL patients (1,009 males, 376 females) diagnosed in 2000-2014 (median age 71 years, range 22-96) comorbidities ≤ 10 years of diagnosis were classified according to the Charlson comorbidity index (CCI; 0, 1, 2+). Hazard ratios (HRs) with 95% confidence intervals (CIs) were estimated to compare lymphoma-specific and all-cause mortality rates. Model-based predictions were used to obtain probabilities of death. Overall, 44% had any comorbidity (CCI 1+) and 28% severe comorbidity (CCI 2+). Over a median follow-up of 3·7 years (range 0-16), 633 (46%) died, the majority (76%) from lymphoma. Severe comorbidity was independently associated with higher all-cause [hazard ratio (HR) = 1·52; 95% CI: 1·24-1·85) and lymphoma-specific mortality (HR = 1·31; 95% CI: 1·04-1·65). Particularly among patients with connective tissue, renal and psychiatric diseases, and dementia. Among females with any comorbidity, non-lymphoma deaths represented a larger proportion of all deaths, compared to males with any comorbidity. In general, more efficient lymphoma treatments need to be considered also for patients with severe comorbidity. However, among females with any comorbidity, the likelihood of non-lymphoma death was still considerable, perhaps favouring a more liberal use of a "wait and watch" approach.

Non-Hodgkin lymphoma (NHL) prognosis has improved in recent years, yet the number of patients living with the diagnosis, i.e. the prevalence, has seldom been reported. The prevalence provides a measure of the burden of disease, useful for healthcare planning and to optimise resource allocation. We provide a systematic presentation of temporal trends in absolute numbers of prevalent patients by NHL subtypes, linking them to trends in incidence, survival and mortality. Patients diagnosed 2000-2016 were identified in the national Swedish lymphoma register. Incidence and mortality rates, relative survival and prevalence were estimated for NHL overall and for major clinical and morphological subtypes. Poisson regression was used to test for temporal trends. Increasing incidence and improved survival have led to a 47% increase in the five-year prevalence of NHL overall in 2016 compared to 2004. An increasing prevalence was observed for all investigated subtypes during the study period, but most notably for diffuse large B cell lymphomas among aggressive subtypes (66%), and marginal zone lymphomas among indolent subtypes (135%). This dramatic increase in NHL prevalence underscores the need to develop and evaluate alternative follow-up schemes to use resources efficiently and still ensure optimal care of lymphoma survivors.

Solid organ transplant recipients (OTRs) have an increased cancer risk but their survival once diagnosed with cancer has seldom been assessed. We therefore investigated cancer-specific survival among OTRs with a wide range of cancer forms nationally in Sweden. The study included 2,143 OTRs with cancer, and 946,089 nontransplanted cancer patients diagnosed 1992-2013. Hazard ratios (HR) and 95% confidence intervals (CI) were estimated using Cox regression models adjusted for age, sex and calendar year. Median follow-up was 3.1 (range 0-22) years. Overall, OTRs diagnosed with any cancer had a 35% higher rate of cancer death compared to nontransplanted cancer patients (HR: 1.35, 95% CI: 1.24-1.47). Specifically, higher rates of cancer-specific death were observed among OTRs diagnosed with Hodgkin lymphoma (HR: 15.0, 95% CI: 5.56-40.6), high-grade non-Hodgkin lymphoma (HR: 2.68, 95% CI: 1.90-3.77), malignant melanoma (HR: 2.80, 95% CI: 1.74-4.52) and urothelial (HR: 2.56, 95% CI: 1.65-3.97), breast (HR: 2.12, 95% CI: 1.38-3.25), head/neck (HR: 1.55, 95% CI: 1.02- 2.36) and colorectal (HR: 1.42, 95% CI: 1.07-1.88) cancer. The worse outcomes were not explained by differences in distribution of cancer stage or histologic subtypes. For other common cancer forms such as prostate, lung and kidney cancer, the prognosis was similar to that in nontransplanted cancer patients. In conclusion, several but not all types of posttransplantation cancer diagnoses are associated with worse outcomes than in the general population. Reasons for this should be further explored to optimize posttransplantation cancer management.

Kidney transplant recipients (KTRs) have an increased cancer risk compared to the general population, but absolute risks that better reflect the clinical impact of cancer are seldom estimated. All KTRs in Sweden, Norway, Denmark, and Finland, with a first transplantation between 1995 and 2011, were identified through national registries. Post-transplantation cancer occurrence was assessed through linkage with cancer registries. We estimated standardized incidence ratios (SIR), absolute excess risks (AER), and cumulative incidence of cancer in the presence of competing risks. Overall, 12 984 KTRs developed 2215 cancers. The incidence rate of cancer overall was threefold increased (SIR 3.3, 95% confidence interval [CI]: 3.2-3.4). The AER of any cancer was 1560 cases (95% CI: 1468-1656) per 100 000 person-years. The highest AERs were observed for nonmelanoma skin cancer (838, 95% CI: 778-901), non-Hodgkin lymphoma (145, 95% CI: 119-174), lung cancer (126, 95% CI: 98.2-149), and kidney cancer (122, 95% CI: 98.0-149). The five- and ten-year cumulative incidence of any cancer was 8.1% (95% CI: 7.6-8.6%) and 16.8% (95% CI: 16.0-17.6%), respectively. Excess cancer risks were observed among Nordic KTRs for a wide range of cancers. Overall, 1 in 6 patients developed cancer within ten years, supporting extensive post-transplantation cancer vigilance.

While Hodgkin lymphoma (HL) survival has improved, treatment-related complications remain a concern. As a measure of treatment-related diseases of the circulatory system (DCS) we report excess incidence of DCS and absolute risks among HL patients diagnosed in the modern treatment era. From the Swedish Cancer Register, we identified all HL patients diagnosed 1985 through 2013, at ages 18-80 years. Excess incidence rate ratios (EIRRs) with 95% confidence intervals (CIs) comparing excess DCS incidence between calendar periods were estimated overall, and at 5 and 10 years after diagnosis using flexible parametric models. Model-based predictions were used to obtain probabilities of being diagnosed with DCS, in the presence of competing risks. During follow-up, 726 (16%) of the 4,479 HL patients experienced DCS. Overall, the excess DCS incidence was lower during all calendar periods compared to the first (2009-2013 vs. 1985-1988: EIRR = 0.63, 95% CI: 0.42-0.95). The 5- and 10-year excess incidence of DCS decreased between 1985 and 1994 for 25-year-olds (5-year-EIRR1994 = 0.32, 95% CI: 0.12-0.92) and 60-year-olds (5-year-EIRR1994 = 0.45, 95% CI: 0.24-0.88), but remained stable thereafter. No improvements were observed among 75-year-olds. The probability of excess DCS remained the same throughout the study period. In 2009, the percentage of patients aged 25, 60 and 75 experiencing excess DCS within 5 years was 3.4, 15.0 and 17.0% (males) and 2.3, 10.8 and 12.6% (females). Treatment-related incidence of DCS has declined since the mid-1980s, but more recent improvements are absent and an excess risk remains. Continued efforts towards less toxic treatments are warranted, alongside primary prevention strategies.

Survival has improved among patients with diffuse large B-cell lymphoma (DLBCL) with the addition of anti-CD20 antibody therapy. We aimed to quantify trends and remaining loss in expectation of life (LEL) due to DLBCL at a national population-based level. Patients diagnosed with DLBCL 2000-2013 (N=7114) were identified through the Swedish Lymphoma Registry and classified according to the age-adjusted International Prognostic Index (aaIPI). The novel measure LEL is the difference between remaining life years among patients and the general population and was predicted using flexible parametric models from diagnosis and among 2-year survivors, by age and sex. Median age at DLBCL-diagnosis was 70 (18-105) years and 54.8% presented with stage III-IV disease. On average, LEL due to DLBCL decreased from 8.0 (95% CI: 7.7-8.3) to 4.6 (95% CI: 4.5-4.6) years over the study period. By risk group, LEL was most reduced among patients with aaIPI >= 2 aged 50-60 years. However, these patients were still estimated to lose >8 years in 2013 (eg, LELmales50years 8.6 years (95% CI: 5.0-12.3)). Among 2-year survivors, LEL was reduced from 6.1 years (95% CI: 5.6-6.5) (aaIPI >= 2) and 3.8 years (95% CI: 3.6-4.1) (aaIPI<2) to 1.1 (95% CI: 1.1-1.2) and 1.0 year (95% CI: 0.8-1.1), respectively. The reduction was observed across all ages. Results for females were similar. By using LEL we illustrate the improvement of DLBCL survival over time. Despite adequate immunochemotherapy, substantial LEL among patients with IPI >= 2 points to remaining unmet medical needs. We speculate that observed reduced losses among 2-year survivors indicate a reduction of late relapses.

Objective: Forty percent of Hodgkin lymphoma (HL) patients are older than 50years at diagnosis, a fact which is not commonly recognized. Older patients do significantly worse than younger patients and are rarely included in clinical trials. Methods: Using data from Swedish Cancer and Lymphoma Registries, we estimated relative survival ratios (RSRs) for 7997 HL patients (diagnosed 1973-2013; 45% 50years). Results: The 1-year RSRs (95% confidence interval; CI) for males aged 45-59, 60-69, 70-80, and 81years and over, diagnosed in 2013, were 0.95 (0.91-0.97), 0.88 (0.81-0.92), 0.74 (0.63-0.81), and 0.52 (0.35-0.67), respectively. The corresponding 1-year RSRs for females were 0.97 (0.94-0.98), 0.91 (0.85-0.95), 0.82 (0.73-0.88), and 0.66 (0.50-0.77). No improvements in 1-year of 5-year relative survival from 2000 to 2013 were observed for patients aged 45-59 or 60-69 but there were modest improvements for patients aged 70years and older. Importantly, we saw no changes in the distribution of disease or patient characteristics between 2000 and 2013. Conclusions: Elderly patients constitute a large group with clearly unmet medical needs. Our findings motivate a more active approach to including elderly patients in clinical trials. Our study provides a baseline for outcome comparison after the broader introduction of targeted drugs.

Objectives: This study aims to characterize the epidemiology of immunocompetent Primary central nervous system lymphoma (PCNSL) diagnosed 2000-2013 in Sweden. Methods: Cases were identified in the population-based Swedish Lymphoma Register. Incidence per 100000 person-years and 95% confidence intervals (CI) were calculated, and PCNSL-specific survival was estimated using relative survival. Tests for temporal trends were performed using Poisson regression. Population incidence of all brain tumors was retrieved for comparison. Results: With 359 identified PCNSL cases (median age 66years), overall incidence was 0.26 (95% CI: 0.24-0.29) and the average annual increase 4% (P=.002). The increasing trend was primarily observed among elderly individuals (70+years). Similarly, an increase in incidence of all brain tumors was noted only among the elderly. There was no significant improvement in relative survival across the study period although, among fit patients (with Eastern Cooperative Oncology Group, EGOC 0), survival plateaued 6years after diagnosis. Conclusion: The increasing PCNSL incidence in the elderly was consistent with an increasing incidence of brain tumors of any type and may in part be attributable to improved diagnostics and reporting in this group. New treatment options have not yet translated into general survival improvements in a population-based setting, although the presence of long-term survivors among fit patients is encouraging.

With today's excellent cure rates for Hodgkin lymphoma (HL), the number of long-term survivors is increasing. This study aims to provide a global assessment of late adverse effects for workingage HL survivors treated with contemporary protocols (combination chemotherapy and limited radiotherapy). From Swedish nationwide registers we identified 1017 HL survivors diagnosed in 2000-2009, aged 18-60 years (median 32) and surviving at least one year post-diagnosis, and 4031 age-,sex-, and calendar-year-matched population comparators. Incidence rate ratios (IRR) and 95% confidence intervals (95% CI) for outpatient visits and inpatient bed-days after the first year up to 14 years post-diagnosis (through 2013) were estimated across treatment subgroups, considering relapse-free time and using negative binomial regression. Scheduled outpatient visits for HL were excluded. The rate of outpatient visits was nearly double (IRR = 1.8, 95% CI: 1.6-2.0) that among comparators and higher rates persisted up to 10 years post-diagnosis. The rate of inpatient bed-days among relapse-free survivors was more than three-fold (IRR = 3.6, 95% CI: 2.74.7) that of comparators and the increase persisted up to four years post-diagnosis. Patients requiring 6-8 chemotherapy courses had higher rates of outpatient visits (IRR = 1.4, 95% CI: 1.11.7) and bed-days (IRR-4.7, 95% CI: 2.9-7.8) than patients treated with 2-4 courses+radiotherapy. Previously seldom reported reasons for the excess healthcare use included chest pain, keratitis, asthma, diabetes mellitus, and depression. Contemporary treatment, chemotherapy in particular, was associated with excess healthcare use among HL survivors during the first decade postdiagnosis. The reasons for healthcare visits reflected a wide range of disorders, indicating the need of broad individualized care in addition to specific screening programs.