Federated Learning Survival Model and Potential Radiotherapy Decision Support Impact Assessment for Non-small Cell Lung Cancer Using Real-World Data.

AIMS: The objective of this study was to develop a two-year overall survival model for inoperable stage I-III non-small cell lung cancer (NSCLC) patients using routine radiation oncology data over a federated (distributed) learning network and evaluate the potential of decision support for curative versus palliative radiotherapy. METHODS: A federated infrastructure of data extraction, de-identification, standardisation, image analysis, and modelling was installed for seven clinics to obtain clinical and imaging features and survival information for patients treated in 2011-2019. A logistic regression model was trained for the 2011-2016 curative patient cohort and validated for the 2017-2019 cohort. Features were selected with univariate and model-based analysis and optimised using bootstrapping. System performance was assessed by the receiver operating characteristic (ROC) and corresponding area under curve (AUC), C-index, calibration metrics and Kaplan-Meier survival curves, with risk groups defined by model probability quartiles. Decision support was evaluated using a case-control analysis using propensity matching between treatment groups. RESULTS: 1655 patient datasets were included. The overall model AUC was 0.68. Fifty-eight percent of patients treated with palliative radiotherapy had a low-to-moderate risk prediction according to the model, with survival times not significantly different (p = 0.87 and 0.061) from patients treated with curative radiotherapy classified as high-risk by the model. When survival was simulated by risk group and model-indicated treatment, there was an estimated 11% increase in survival rate at two years (p < 0.01). CONCLUSION: Federated learning over multiple institution data can be used to develop and validate decision support systems for lung cancer while quantifying the potential impact of their use in practice. This paves the way for personalised medicine, where decisions can be based more closely on individual patient details from routine care.

An Overview of the Role of Radiotherapy in the Treatment of Small Cell Lung Cancer - A Mainstay of Treatment or a Modality in Decline?

AIMS: Small cell lung cancer (SCLC) accounts for about 15% of all lung cancers. Chemotherapy, immunotherapy and radiotherapy all play important roles in the management of SCLC. The aim of this study was to provide a comprehensive overview of the role and evidence of radiotherapy in the cure and palliation of SCLC. MATERIALS AND METHODS: The search strategy included a search of the PubMed database, hand searches, reference lists of relevant review articles and relevant published abstracts. CLINICALTRIALS: gov was also queried for relevant trials. RESULTS: Thoracic radiotherapy improves overall survival in limited stage SCLC, but the timing and dose remain controversial. The role of thoracic radiotherapy in extensive stage SCLC with immunotherapy is the subject of several ongoing trials. Current evidence supports the use of prophylactic cranial irradiation (PCI) for limited stage SCLC but the evidence is equivocal in extensive stage SCLC. Whole brain radiotherapy is well established for the treatment of brain metastases but evidence is rapidly accumulating for the use of stereotactic radiosurgery. Further studies will define the role of PCI, whole brain radiotherapy and hippocampal avoidant PCI in the immunotherapy era. CONCLUSION: Radiotherapy is an essential component in the multimodality management of SCLC. Technological advances have allowed safer delivery of radiotherapy with reduced toxicities. Discussion at multidisciplinary team meetings is important to ensure radiotherapy is considered and offered in appropriate patients.

A systematic review and meta-analysis of treatment-related toxicities of curative and palliative radiation therapy in non-small cell lung cancer.

Treatment-related toxicity is an important component in non-small cell lung cancer (NSCLC) management decision-making. Our aim was to evaluate and compare the toxicity rates of curative and palliative radiotherapy with and without chemotherapy. This meta-analysis provides better quantitative estimates of the toxicities compared to individual trials. A systematic review of randomised trials with > 50 unresectable NSCLC patients, treated with curative or palliative conventional radiotherapy (RT) with or without chemotherapy. Data was extracted for oesophagitis, pneumonitis, cardiac events, pulmonary fibrosis, myelopathy and neutropenia by any grade, grade ≥ 3 and treatment-related deaths. Mantel-Haenszel fixed-effect method was used to obtain pooled risk ratio. Forty-nine trials with 8609 evaluable patients were included. There was significantly less grade ≥ 3 acute oesophagitis (6.4 vs 22.2%, p < 0.0001) and any grade oesophagitis (70.4 vs 79.0%, p = 0.04) for sequential CRT compared to concurrent CRT, with no difference in pneumonitis (grade ≥ 3 or any grade), neutropenia (grade ≥ 3), cardiac events (grade ≥ 3) or treatment-related deaths. Although the rate of toxicity increased with intensification of treatment with RT, the only significant difference between treatment regimens was the rate of oesophagitis between the use of concurrent and sequential CRT. This can aid clinicians in radiotherapy decision making for NSCLC.

[Oesophageal bullous detachment with massive haemorrhage revealing acquired haemophilia A in autoimmune bullous dermatosis]. / Décollement bulleux de l'œsophage responsable d'une hémorragie massive révélant une hémophilie A acquise au cours d'une dermatose bulleuse auto-immune.

INTRODUCTION: Acquired haemophilia A (AHA) is a rare coagulopathy caused by the development of factor VIII antibodies. Various aetiologies have been established but a number of cases have been reported in association with autoimmune bullous dermatosis (AIBD). We report a new case of this type of association revealed by oesophageal involvement of AIBD. PATIENTS AND METHODS: A male patient was treated for AIBD. Due to the inefficacy of local steroids and the emergence of oral and laryngeal blisters, the patient was treated with systemic steroids. He developed a gastrointestinal haemorrhage complicated by haemorrhagic shock. Endoscopy revealed complete peeling of the oesophagus. Laboratory tests showed lengthening of ACT, reduced factor VIII levels, and the presence of anti-factor VIII antibodies. A diagnosis was made of AHA associated with AIBD. Prolongation of systemic corticosteroids and initiation of rituximab resulted in normalisation of haemostasis. DISCUSSION: AIBD and AHA frequently develop concomitantly, as was the case with our patient. The haemorrhagic complications were severe. The aim of AHA treatment is to stop acute bleeding and eliminate antibodies, and for this reason rituximab was chosen. CONCLUSION: Oesophageal bullous detachment is rare in AIBD but, as seen here, it may be responsible for massive haemorrhage, especially in the event of associated AHA. This feature underscores the need for evaluation of haemostasis in the early stages and during relapses for all patients with AIBD.

Calmodulin affinity for brain coated vesicle proteins.

A systematic characterization of the affinity of calmodulin for brain coated vesicles was undertaken. Binding of 125I-labeled calmodulin to coated vesicles was saturable and competed with unlabeled calmodulin, but not with troponin-C. Scatchard analysis revealed one high-affinity, low-capacity binding site, KD = 3.9 +/- 0.6 nM, Bmax = 16.3 +/- 2.4 pmol/mg, and one low-affinity, high-capacity binding site, KD = 102 +/- 15.0 nM, Bmax = 151 +/- 23.0 pmol/mg. Radioimmunoassay revealed that coated vesicles contain 1.05 microgram calmodulin/mg protein. Because this value remained constant even after removal of clathrin, the major coat protein, from the coated vesicle, it is apparent that calmodulin is associated with the vesicle per se rather than with its clathrin lattice. When a Triton X-100-treated extract of coated vesicles was passed through a Sepharose 4B-calmodulin affinity column, polypeptides with Mrs (molecular weights) of 100,000, 55,000, and 30,000 bound in a Ca2+-dependent manner. A 30,000 Mr protein doublet purified from coated vesicles was completely eluted by EGTA from the calmodulin affinity column, confirming that this protein doublet represents one of the coated vesicle calmodulin binding sites. Because calmodulin stimulated [Ca2+-Mg2+]-ATPase activity as well as Ca2+ uptake in coated vesicles, it is postulated that the 100,000 and 55,000 Mr calmodulin binding proteins represent the [Ca2+-Mg2+]-ATPase complex, the other coated vesicle calmodulin binding site.