AI Concepts for System of Systems Dynamic Interoperability.

Interoperability is a central problem in digitization and System of Systems (SoS) engineering, which concerns the capacity of systems to exchange information and cooperate. The task to dynamically establish interoperability between heterogeneous cyber-physical systems (CPSs) at run-time is a challenging problem. Different aspects of the interoperability problem have been studied in fields such as SoS, neural translation, and agent-based systems, but there are no unifying solutions beyond domain-specific standardization efforts. The problem is complicated by the uncertain and variable relations between physical processes and human-centric symbols, which result from, e.g., latent physical degrees of freedom, maintenance, re-configurations, and software updates. Therefore, we surveyed the literature for concepts and methods needed to automatically establish SoSs with purposeful CPS communication, focusing on machine learning and connecting approaches that are not integrated in the present literature. Here, we summarize recent developments relevant to the dynamic interoperability problem, such as representation learning for ontology alignment and inference on heterogeneous linked data; neural networks for transcoding of text and code; concept learning-based reasoning; and emergent communication. We find that there has been a recent interest in deep learning approaches to establishing communication under different assumptions about the environment, language, and nature of the communicating entities. Furthermore, we present examples of architectures and discuss open problems associated with artificial intelligence (AI)-enabled solutions in relation to SoS interoperability requirements. Although these developments open new avenues for research, there are still no examples that bridge the concepts necessary to establish dynamic interoperability in complex SoSs, and realistic testbeds are needed.

Penile cancer: long-term infectious and thromboembolic complications following lymph node dissection - a population-based study (Sweden).

PURPOSE: To assess the long-term risks of infectious and thromboembolic events following inguinal (ILND) and pelvic (PLND) lymph node dissection in men with penile cancer. MATERIAL AND METHODS: A total of 364 men subjected to ILND with or without PLND for penile cancer between 2000 and 2012 were identified in the Swedish National Penile Cancer Register. Each patient was matched based on age and county of residence with six penile cancer-free men. The Swedish Cancer Register and other population-based registers were used to retrieve information on treatment and hospitalisation for selected infectious and thromboembolic events. Hazard ratios (HRs) with 95% confidence intervals (CIs) were estimated using Cox proportional hazard models with multiple imputation. RESULTS: The risk of infectious events remained increased for more than five years postoperatively in men with penile cancer compared with matched controls. The palpable nodal disease was the only predictor of these events, with risk increasing with the cN stage. The HR at one, three and five years and six months postoperatively was 8.60 (95% CI 5.16-14.34), 4.02 (95% CI 2.65-6.09) and 1.93 (95% CI 1.11-3.38), respectively. An increased risk of thromboembolic events persisted for three years postoperatively. The HR at one and three years postoperatively was 13.51 (95% CI 6.53-27.93) and 2.12 (95% CI 1.07-4.20). The results correspond well with the over-prescription of anticoagulants observed during this period. An association with bulky disease (cN3) was observed. CONCLUSIONS: Lymph node dissection for penile cancer is associated with an increased risk of infectious and thromboembolic events. The findings of this population-based study show that the risks of these events remain increased more than five years for infectious and three years for thromboembolic events. Improved awareness of long-term complications following ILND is of importance both among patients and care givers to ensure early detection and treatment.

Deep Ontology Alignment Using a Natural Language Processing Approach for Automatic M2M Translation in IIoT.

The technical capabilities of modern Industry 4.0 and Industry 5.0 are vast and growing exponentially daily. The present-day Industrial Internet of Things (IIoT) combines manifold underlying technologies that require real-time interconnection and communication among heterogeneous devices. Smart cities are established with sophisticated designs and control of seamless machine-to-machine (M2M) communication, to optimize resources, costs, performance, and energy distributions. All the sensory devices within a building interact to maintain a sustainable climate for residents and intuitively optimize the energy distribution to optimize energy production. However, this encompasses quite a few challenges for devices that lack a compatible and interoperable design. The conventional solutions are restricted to limited domains or rely on engineers designing and deploying translators for each pair of ontologies. This is a costly process in terms of engineering effort and computational resources. An issue persists that a new device with a different ontology must be integrated into an existing IoT network. We propose a self-learning model that can determine the taxonomy of devices given their ontological meta-data and structural information. The model finds matches between two distinct ontologies using a natural language processing (NLP) approach to learn linguistic contexts. Then, by visualizing the ontological network as a knowledge graph, it is possible to learn the structure of the meta-data and understand the device's message formulation. Finally, the model can align entities of ontological graphs that are similar in context and structure.Furthermore, the model performs dynamic M2M translation without requiring extra engineering or hardware resources.

Successful tyrosine kinase inhibitor discontinuation outside clinical trials - data from the population-based Swedish chronic myeloid leukaemia registry.

Clinical trials show that tyrosine kinase inhibitor (TKI) treatment can be discontinued in selected patients with chronic myeloid leukaemia (CML). Although updated CML guidelines support such procedure in clinical routine, data on TKI stopping outside clinical trials are limited. In this retrospective study utilising the Swedish CML registry, we examined TKI discontinuation in a population-based setting. Out of 584 patients diagnosed with chronic-phase CML (CML-CP) in 2007-2012, 548 had evaluable information on TKI discontinuation. With a median follow-up of nine years from diagnosis, 128 (23%) discontinued TKI therapy (≥1 month) due to achieving a DMR (deep molecular response) and 107 (20%) due to other causes (adverse events, allogeneic stem cell transplant, pregnancy, etc). Among those stopping in DMR, 49% re-initiated TKI treatment (median time to restart 4·8 months). In all, 38 patients stopped TKI within a clinical study and 90 outside a study. After 24 months 41·1% of patients discontinuing outside a study had re-initiated TKI treatment. TKI treatment duration pre-stop was longer and proportion treated with second-generation TKI slightly higher outside studies, conceivably affecting the clinical outcome. In summary we show that TKI discontinuation in CML in clinical practice is common and feasible and may be just as successful as when performed within a clinical trial.

Estimates of lung and pancreatic cancer survival in Sweden with and without inclusion of death certificate initiated (DCI) cases.

INTRODUCTION: International differences in cancer incidence and survival may partly reflect differences in cancer registration practices. As opposed to most other National Cancer Registries, Death Certificate Initiated (DCI) cases are not included in the Swedish Cancer Register. We characterized cases not reported to the Swedish Cancer Register and assessed the impact of inclusion of DCI cases on the completeness and estimates of one-year lung and pancreatic cancer survival. METHODS: We used information in the Swedish Cause of Death Register to identify individuals in two Health Care Regions (West and Uppsala Örebro) with lung or pancreatic cancer as cause of death in 2013. These records were cross-linked to the Cancer Register to identify individuals without a corresponding cancer registration, i.e. Death Certificate Notified (DCN) cases. DCN cases were cross-linked to the Patient Register to retrieve hospital discharge information to confirm the diagnosis. In a separate step, trace-back of DCN cases was performed to access medical records to validate the diagnosis. RESULTS: Following validity checks, an estimated 16% and 34% of individuals with a diagnosis of lung or pancreatic cancer, respectively, had not been reported to the SCR. Non-reported patients were older and had a considerable poorer survival than those included in the SCR. Inclusion of DCI cases decreased one-year lung cancer overall survival from 45% to 41%. The corresponding decrease for pancreatic cancer was five percentage points, from 29% to 24%. CONCLUSIONS: Lung and pancreatic cancers are underreported to the SCR yielding too low incidence rates and upward biased survival estimates. We conclude that implementation of systematic death certificate processing with trace-back is feasible also within the Swedish system with regionalized cancer reporting. Verifying registrability by use of information in the Patient Register provided a good approximation of "corrected" survival estimates based on chart review.

Clinical characteristics and survival in non-small cell lung cancer patients by smoking history: a population-based cohort study.

Introduction: Approximately, 10-15% of lung cancer patients have never smoked. Previous epidemiological studies on non-tobacco associated lung cancer have been hampered by selected data from a small number of hospitals or limited numbers of patients. By use of data from large population-based registers with national coverage, this study aims to compare characteristics and survival of patients with non-small cell lung cancer (NSCLC) with different smoking histories.Methods: Swedish national population-based registers were used to retrieve data on patients diagnosed with primary NSCLC between 2002 and 2016. The Kaplan-Meier method and Cox proportional hazard models were used to estimate overall survival and lung cancer-specific survival by smoking history.Results: In total, 41,262 patients with NSCLC were included. Of those, 4624 (11%) had never smoked. Never-smokers were more often women and older compared to ever smokers (current and former). Adenocarcinoma was proportionally more common in never-smokers (77%) compared to current (52%) and former smokers (57%). Stage IV disease was more common in never-smokers (57%) than in current (48%) and former smokers (48%). Epidermal growth factor receptor mutation was observed more in never-smokers (37%) compared to current (5%) and former smokers (9%). Both lung cancer-specific and overall survival were higher for never-smokers compared to current smokers.Conclusions: The observed differences in characteristics between never-smokers and smokers, and the higher survival in never-smokers compared to smokers from this large population-based study provide further evidence that lung cancer in never-smokers is clinically different to tobacco-associated lung cancer. The findings from this study emphasise the need for an improved understanding of genetics, pathogenesis, mechanisms and progression of non-tobacco associated lung cancer that may help prevent lung cancer or identify individually targeted treatments.

U-CAN: a prospective longitudinal collection of biomaterials and clinical information from adult cancer patients in Sweden.

BACKGROUND: Progress in cancer biomarker discovery is dependent on access to high-quality biological materials and high-resolution clinical data from the same cases. To overcome current limitations, a systematic prospective longitudinal sampling of multidisciplinary clinical data, blood and tissue from cancer patients was therefore initiated in 2010 by Uppsala and Umeå Universities and involving their corresponding University Hospitals, which are referral centers for one third of the Swedish population. MATERIAL AND METHODS: Patients with cancer of selected types who are treated at one of the participating hospitals are eligible for inclusion. The healthcare-integrated sampling scheme encompasses clinical data, questionnaires, blood, fresh frozen and formalin-fixed paraffin-embedded tissue specimens, diagnostic slides and radiology bioimaging data. RESULTS: In this ongoing effort, 12,265 patients with brain tumors, breast cancers, colorectal cancers, gynecological cancers, hematological malignancies, lung cancers, neuroendocrine tumors or prostate cancers have been included until the end of 2016. From the 6914 patients included during the first five years, 98% were sampled for blood at diagnosis, 83% had paraffin-embedded and 58% had fresh frozen tissues collected. For Uppsala County, 55% of all cancer patients were included in the cohort. CONCLUSIONS: Close collaboration between participating hospitals and universities enabled prospective, longitudinal biobanking of blood and tissues and collection of multidisciplinary clinical data from cancer patients in the U-CAN cohort. Here, we summarize the first five years of operations, present U-CAN as a highly valuable cohort that will contribute to enhanced cancer research and describe the procedures to access samples and data.

The impact of socio-economic factors on treatment choice and mortality in chronic myeloid leukaemia.

PURPOSE: To evaluate the influence of socio-economic variables on treatment selection and survival of patients with chronic myeloid leukaemia (CML). METHODS: Using information available in population-based Swedish registries, we evaluated indices of health, education and economy from the 980 patients in the Swedish CML register diagnosed between 2002 and 2012. Apart from internal comparisons, five age-, gender- and region-matched control subjects per patient served as control cohort. Median follow-up time from CML diagnosis was 4.8 years. RESULTS: Among patients with CML, low personal or household income, short education, living alone, poor performance status and high age (>60 years) were significantly associated with an inferior survival (in univariate analyses). However, similar findings were noted also in the matched control group, and in comparisons adjusted for calendar year, age and performance status, socio-economic variables were not significantly associated with CML survival. Meanwhile, both education and income were independently linked to TKI treatment overall and to upfront treatment with second-generation TKIs. CONCLUSIONS: In conclusion, socio-economic conditions were associated with survival in the studied CML cohort but these associations could be explained by differences at baseline. Meanwhile, socio-economic conditions appeared to influence treatment choice.

Advanced phase chronic myeloid leukaemia (CML) in the tyrosine kinase inhibitor era - a report from the Swedish CML register.

OBJECTIVES: The primary goal in management of chronic phase (CP) chronic myeloid leukaemia (CML) is to prevent disease progression to accelerated phase (AP) or blast crisis (BC). We have evaluated progression rates in a decentralised healthcare setting and characterised patients progressing to AP/BC on TKI treatment. METHODS: Using data from the Swedish CML register, we identified CP-CML patients diagnosed 2007-2011 who progressed to AP/BC within 2 yrs from diagnosis (n = 18) as well as patients diagnosed in advanced phase during 2007-2012 (n = 36) from a total of 544 newly diagnosed CML cases. We evaluated baseline characteristics, progression rates, outcome and adherence to guidelines for monitoring and treatment. RESULTS: The cumulative progression rate at 2 yrs was 4.3%. All 18 progression cases had been treated with imatinib, and six progressed within 6 months. High-risk EUTOS score was associated to a higher risk of progression. Insufficient cytogenetic and/or molecular monitoring was found in 33%. Median survival after transformation during TKI treatment was 1.4 yrs. In those presenting with BC and AP, median survival was 1.6 yrs and not reached, respectively. CONCLUSION: In this population-based setting, progression rates appear comparable to that reported from clinical trials, with similar dismal patient outcome. Improved adherence to CML guidelines may minimise the risk of disease progression.

Cardiovascular Events Associated With Use of Tyrosine Kinase Inhibitors in Chronic Myeloid Leukemia: A Population-Based Cohort Study.

BACKGROUND: Tyrosine kinase inhibitors (TKIs) have increased survival dramatically for patients with chronic myeloid leukemia (CML), but continuous administration of these drugs may elicit long-term toxicity. OBJECTIVE: To investigate the incidence of vascular events in patients with CML treated with first- and second-generation TKIs. DESIGN: Retrospective cohort study using nationwide population-based registries. SETTING: Sweden. PATIENTS: All patients diagnosed with chronic-phase CML in Sweden from 2002 to 2012 and treated with a TKI, and 5 age- and sex-matched control individuals per patient. MEASUREMENTS: Relative risks, expressed as incidence rate ratios comparing patients with control individuals, were calculated. Events per 1000 person-years were assessed in interdrug comparisons. RESULTS: 896 patients, 94.4% with documented TKI treatment, were followed for a median of 4.2 years. There were 54 arterial and 20 venous events in the CML cohort, corresponding to relative risks of 1.5 (95% CI, 1.1 to 2.1) and 2.0 (CI, 1.2 to 3.3), respectively. The event rate for myocardial infarction was higher in patients treated with nilotinib or dasatinib (29 and 19 per 1000 person-years, respectively) than in those receiving imatinib (8 per 1000 person-years), although data are limited and the CIs were wide and overlapped. Among 31 patients treated with a TKI who had myocardial infarction, 26 (84%) had at least 1 major cardiac risk factor diagnosed before the event occurred. LIMITATIONS: Patients may have been exposed to multiple TKIs. Data on second- and third-generation TKIs were limited. CONCLUSION: An increased risk for arterial and venous vascular events was seen in patients with CML treated with a TKI. Further study is needed to determine whether the risk for myocardial infarction increases with second-generation drugs. PRIMARY FUNDING SOURCE: No external funding.

Population-based assessment of chronic myeloid leukemia in Sweden: striking increase in survival and prevalence.

The clinical outcome for patients with chronic myeloid leukemia (CML) has improved dramatically following the introduction of tyrosine kinase inhibitors. An improved survival, combined with a constant incidence, is expected to increase the prevalence of CML. However, data on the prevalence of CML remain scarce. We examined the overall and relative (age and gender matched) survival and assessed the past, present, and projected future prevalence of CML in Sweden. Data on all patients diagnosed with CML between 1970 and 2012 were retrieved from the Swedish Cancer Register and the Swedish Cause of Death Register. The 5-year overall survival increased from 0.18 to 0.82, during the observed time period. Between 2006 and 2012, the 5-year relative survival was close to normal for 40-year-old, but considerably lower for 80-year-old CML patients. The observed prevalence tripled from 1985 to 2012, from 3.9 to 11.9 per 100 000 inhabitants. Assuming no further improvements in relative survival, the prevalence is projected to further increase by 2060 to 22.0 per 100 000 inhabitants (2587 persons in Sweden). The projected dramatic increase in CML prevalence has major medical and health economic implications and needs to be considered in planning how to organize future care of CML patients.

Second malignancies following treatment of chronic myeloid leukaemia in the tyrosine kinase inhibitor era.

Given that tyrosine kinase inhibitors (TKIs) have dramatically improved the survival of patients with chronic myeloid leukaemia (CML), we were interested in examining the possible risk of long-term adverse events, such as the emergence of other neoplasms. Therefore, we studied the development of second malignancies in 868 patients diagnosed with CML between 2002 and 2011 using the Swedish CML register, cross-linked to the Swedish Cancer register. With a median follow-up of 3·7 (range 0-9·9) years, 65 (7·5%) patients developed 75 second malignancies (non-haematological), 52 of which were of the invasive type. Compared to expected rates in the background population, the risk of second malignancies was higher in the CML cohort, with a standardized incidence ratio (SIR) of 1·52 (95% CI 1·13-1·99). The SIR before and after the second year following diagnosis of CML was 1·58 and 1·47, respectively. Among specific cancer types, gastrointestinal and nose and throat cancer were significantly increased. Founded on a population-based material, our results indicate that CML patients treated in the TKI era are at an increased risk of developing a second malignancy, with indications that this risk may more likely be linked to CML itself rather than to the TKI treatment.

The Risk of Distant Metastases and Cancer Specific Survival in Men with Serum Prostate Specific Antigen Values above 100 ng/ml.

PURPOSE: Current EAU (European Association of Urology) guidelines state that prostate specific antigen 100 ng/ml or greater at diagnosis indicates metastatic disease. We examined the association of prostate specific antigen 100 ng/ml or greater at diagnosis with distant metastasis and prostate cancer specific survival. MATERIAL AND METHODS: A total of 15,635 men with prostate cancer diagnosed between 1998 and 2009 who were identified in PCBaSe (Prostate Cancer Data Base Sweden 2.0) were included in a population based registry study. Prostate cancer specific survival was compared among 3 groups, including 1,879 men with prostate specific antigen 100 ng/ml or greater and negative imaging (M0), 5,642 with distant metastases on imaging (M1) and prostate specific antigen 100 ng/ml or greater, and 3,828 with M1 and prostate specific antigen less than 100 ng/ml. A fourth group consisted of 4,286 men with prostate specific antigen 100 ng/ml or greater who had not undergone imaging (Mx). The latter men were not included in the assessment of survival. RESULTS: Of 7,521 men with prostate specific antigen 100 ng/ml or greater who underwent imaging for staging 75% were classified with M1 disease. Only 59% of 3,527 men with prostate specific antigen 100 to 300 mg/ml had distant metastases on imaging. Five-year prostate cancer specific survival was 72% (95% CI 70-74) in men with prostate specific antigen 100 ng/ml or greater and M0, 24% (95% CI 23-25) in men with prostate specific antigen 100 ng/ml or greater and M1, and 39% (95% CI 37-40) in men with prostate specific antigen less than 100 ng/ml and M1. CONCLUSIONS: A fourth of men with prostate specific antigen 100 ng/ml or greater did not have distant metastases. They had twofold to threefold higher 5-year survival than men with distant metastases on imaging. Our findings strongly suggest that using prostate specific antigen 100 ng/ml or greater as an indicator of metastatic disease should be reconsidered.

Tyrosine kinase inhibitor usage, treatment outcome, and prognostic scores in CML: report from the population-based Swedish CML registry.

Clinical management guidelines on malignant disorders are generally based on data from clinical trials with selected patient cohorts. In Sweden, more than 95% of all patients diagnosed with chronic myeloid leukemia (CML) are reported to the national CML registry, providing unique possibilities to compile population-based information. This report is based on registry data from 2002 to 2010, when a total of 779 patients (425 men, 354 women; median age, 60 years) were diagnosed with CML (93% chronic, 5% accelerated, and 2% blastic phase) corresponding to an annual incidence of 0.9/100,000. In 2002, approximately half of the patients received a tyrosine kinase inhibitor as initial therapy, a proportion that increased to 94% for younger (<70 years) and 79% for older (>80 years) patients during 2007-2009. With a median follow-up of 61 months, the relative survival at 5 years was close to 1.0 for patients younger than 60 years and 0.9 for those aged 60 to 80 years, but only 0.6 for those older than 80 years. At 12 months, 3% had progressed to accelerated or blastic phase. Sokal, but not European Treatment and Outcome Study, high-risk scores were significantly linked to inferior overall and relative survival. Patients living in university vs nonuniversity catchment areas more often received tyrosine kinase inhibitors up front but showed comparable survival.

Epidemiology of chronic myeloid leukaemia: an update.

National and regional population-based registries are, provided diagnostic accuracy and full coverage of the target population, indispensible tools for epidemiological research. Chronic myeloid leukaemia (CML) registries with more comprehensive reporting may also provide complementary data on treatment outcome to those obtained from clinical trials. Reports from several European CML registries consistently show a crude annual incidence of 0.7-1.0/100,000, a median age at diagnosis of 57-60 years and a male/female ratio of 1.2-1.7. The incidence of CML has been stable over time. Worldwide, variations in the reported incidence of CML may be due to methodological issues, but a true difference between different geographical areas and/or ethnical subgroups cannot be excluded. The prevalence of CML is not well known but has been estimated to be 10-12/100,000 inhabitants with a steady increase due to the dramatic improvement in survival of these patients. In recent population-based studies, CML patients have an overall survival that is comparable to that shown in large clinical trials, though relative survival in patients >70 years is still decreased. The importance of socio-economic factors and health-care setting for outcome and the possible increased risk of secondary cancer in CML are areas of ongoing research.

Combination of pegylated IFN-α2b with imatinib increases molecular response rates in patients with low- or intermediate-risk chronic myeloid leukemia.

Biologic and clinical observations suggest that combining imatinib with IFN-α may improve treatment outcome in chronic myeloid leukemia (CML). We randomized newly diagnosed chronic-phase CML patients with a low or intermediate Sokal risk score and in imatinib-induced complete hematologic remission either to receive a combination of pegylated IFN-α2b (Peg-IFN-α2b) 50 µg weekly and imatinib 400 mg daily (n = 56) or to receive imatinib 400 mg daily monotherapy (n = 56). The primary endpoint was the major molecular response (MMR) rate at 12 months after randomization. In both arms, 4 patients (7%) discontinued imatinib treatment (1 because of blastic transformation in imatinib arm). In addition, in the combination arm, 34 patients (61%) discontinued Peg-IFN-α2b, most because of toxicity. The MMR rate at 12 months was significantly higher in the imatinib plus Peg-IFN-α2b arm (82%) compared with the imatinib monotherapy arm (54%; intention-to-treat, P = .002). The MMR rate increased with the duration of Peg-IFN-α2b treatment (< 12-week MMR rate 67%, > 12-week MMR rate 91%). Thus, the addition of even relatively short periods of Peg-IFN-α2b to imatinib markedly increased the MMR rate at 12 months of therapy. Lower doses of Peg-IFN-α2b may enhance tolerability while retaining efficacy and could be considered in future protocols with curative intent.

Integration of neuromorphic AI in event-driven distributed digitized systems: Concepts and research directions.

Increasing complexity and data-generation rates in cyber-physical systems and the industrial Internet of things are calling for a corresponding increase in AI capabilities at the resource-constrained edges of the Internet. Meanwhile, the resource requirements of digital computing and deep learning are growing exponentially, in an unsustainable manner. One possible way to bridge this gap is the adoption of resource-efficient brain-inspired "neuromorphic" processing and sensing devices, which use event-driven, asynchronous, dynamic neurosynaptic elements with colocated memory for distributed processing and machine learning. However, since neuromorphic systems are fundamentally different from conventional von Neumann computers and clock-driven sensor systems, several challenges are posed to large-scale adoption and integration of neuromorphic devices into the existing distributed digital-computational infrastructure. Here, we describe the current landscape of neuromorphic computing, focusing on characteristics that pose integration challenges. Based on this analysis, we propose a microservice-based conceptual framework for neuromorphic systems integration, consisting of a neuromorphic-system proxy, which would provide virtualization and communication capabilities required in distributed systems of systems, in combination with a declarative programming approach offering engineering-process abstraction. We also present concepts that could serve as a basis for the realization of this framework, and identify directions for further research required to enable large-scale system integration of neuromorphic devices.