Four out of twenty-three acromegalic patients selected for treatment with external megavoltage pituitary irradiation between 1961 and 1975 developed progressive visual failure. They had received megavoltage external irradiation through multiple portals from a cobalt-60 unit over a period of 3 weeks. Visual deterioration began 2 months to 6 years after irradiation. In two patients the optic nerves were explored. In both, post-mortem later confirmed radiation damage to the optic nerves and hypothalamus. In one case there was also necrosis of the right frontal lobe with necrosis and inflammation of the bone surrounding the pituitary fossa. In the two other patients, extensive clinical and neuroradiological investigation excluded the presence of a suprasellar mass as a cause for this visual failure and a clinical diagnosis of radiation necrosis was made.

Eighty‐one patients with cancer of the male breast were studied. The majority (79) presented with a mass in the breast and in 8 patients the tumor was found by chance. Two patients presented with serosanguinous discharge. Average duration of symptoms was 11.9 months. Thirty patients had Stage I, 25 had Stage II, 16 had Stage III, and 8 had Stage IV disease. Fifty‐three patients had simple mastectomy, nine had lumpectomy, six had radical mastectomy, and five had biopsy only. Eight had no local surgery. Overall 5‐and 10‐year survival allowing for all causes of death was 38% and 17%, respectively. Cox's (1972) proportional hazard regression model was used to assess the contribution of various factors to survival. Age at presentation, postoperative hormone therapy, postoperative radiotherapy, site of the primary tumor within the breast, and type of local surgery did not contribute to survival. Only the stage of disease contributed to survival and did so in the expected direction.

No abstract

No abstract

Aim We aim to compare machine learning with neural network performance in predicting R0 resection (R0), length of stay > 14 days (LOS), major complication rates at 30 days postoperatively (COMP) and survival greater than 1 year (SURV) for patients having pelvic exenteration for locally advanced and recurrent rectal cancer. Method A deep learning computer was built and the programming environment was established. The PelvEx Collaborative database was used which contains anonymized data on patients who underwent pelvic exenteration for locally advanced or locally recurrent colorectal cancer between 2004 and 2014. Logistic regression, a support vector machine and an artificial neural network (ANN) were trained. Twenty per cent of the data were used as a test set for calculating prediction accuracy for R0, LOS, COMP and SURV. Model performance was measured by plotting receiver operating characteristic (ROC) curves and calculating the area under the ROC curve (AUROC). Results Machine learning models and ANNs were trained on 1147 cases. The AUROC for all outcome predictions ranged from 0.608 to 0.793 indicating modest to moderate predictive ability. The models performed best at predicting LOS > 14 days with an AUROC of 0.793 using preoperative and operative data. Visualized logistic regression model weights indicate a varying impact of variables on the outcome in question. Conclusion This paper highlights the potential for predictive modelling of large international databases. Current data allow moderate predictive ability of both complex ANNs and more classic methods.