Search

Predicting the clinical outcome prior to minimally invasive treatments for Benign Prostatic Hperlasia (BPH) cases would be very useful. However, clinical prediction has not been reliable in spite of multiple assessment parameters, such as symptom indices and flow rates. In our prior study, Artificial Intelligence (AI) algorithms were used to train computers to predict the surgical outcome in BPH patients treated by TURP or VLAP. Our aim was to investigate whether, based on eleven clinical biomarker features, AI can reproduce the clinical outcome of known cases and assist the urologist in predicting surgical outcomes. In this paper, the objective is to perform data analysis to investigate if specific features have a greater impact on predicting whether the patients had the desired outcome after a surgical procedure is done. Finally, how the number of significant features ought to be weighted to predict the outcome after surgery, is determined to create the most accurate prediction method. Here both the Decision Tree and Naive Bayse machine learning methods are used and compared.

In a study of the literature concerning the urea content of the spinal fluid, we have been struck by the amount of work done on this subject by French clinicians as contrasted with its apparent neglect by German, English and American clinicians. The normal quantity of urea in the spinal fluid, as indicated from a review of a considerable mass of material in the literature, varies between 0.01 per cent. and 0.05 per cent. Mollard and Froment,1in 1909, reviewed the literature up to that time and cited the works which follow in brief. Richet, in 1897, gave twenty-five analyses and stated "possibly urea." Deniges and Sabrazes, and Sabrazes and Binaud,2in 1895, reported two cases of tuberculous meningitis showing 0.015 per cent. and 0.035 per cent, of urea in the spinal fluid. Comba,3in 1899, reported two cases of acute uremia, in which there was an

The following case, while lacking autopsy confirmation, is of considerable interest when considered in conjunction with the case reported in this issue by Drs. Lamb and Paton. Like this, it suggests a form of infection probably overlooked not very infrequently. Case History. —Male, aged 43, American, widower; occupation, designer. Admitted to Presbyterian Hospital September 23, 1912. Family History —No bearing. Past History —Always notably well except for typhoid fever in 1895, and two attacks of malaria in 1911 and July, 1912, respectively, parasites having been found. Habits —Moderate user of alcohol, heavy user of tobacco. No genito-urinary history obtained. Present Illness. —Onset sudden on September 2, twenty-one days before admission, with severe nausea, vomiting and inability to retain any food or water. These symptoms continued for five days, at the end of which time the stomach was again apparently normal. On September 20, three days before admission, the

Meningococcus septicemia was first reported by Gwyn 1 in 1899. The case was one of epidemic meningitis complicated by acute arthritis. The meningococcus was isolated from the spinal fluid, synovial fluid, and the blood. Cochez and Lemaire 2 in 1901 were able to demonstrate the meningococcus in the blood of two meningitis patients. Jakobitz, 3 Martini and Rohde, 4 Lenhartz, 5 Marcovitch, 6 Robinson, 7 and Duval 8 have since made similar reports, the septicemia in all these cases being associated with meningitis. Elser, 9 examining the blood in forty-one cases of cerebrospinal meningitis, found the meningococcus in ten, or about 25 per cent. It has been observed that in most instances where the meningococcus has been found in the circulating blood, the disease has been fatal, and some form of extrameningeal lesion has been present. The endothelial-lined cavities, such as the joints, pleura, pericardium and endocardium have been the sites of these complicating