No abstract

No abstract

No abstract

This application made use of a Multiple Neural Network Learning System (MNNLS) to replicate the decisions made by mortgage insurance underwriters. The MNNLS was trained on previous underwriter judgements and learned to mimic their underwriting skills. The system reached a high degree of agreement with human underwriters when testing on previously unseen examples. Disagreements were examined using case studies, a single feature distribution analysis and a quality analysis. These studies indicate that human underwriters in many cases disagree with one another and are inconsistent in the use of their underwriting guidelines. It was found that when the MNNLS system and the underwriter disagree, the system's classifications are more consistent with the guidelines than the underwriter's judgement.

The present paper describes various kinds of surgery carried out with great success in 16 cases which included both severe and moderate haemophilia patients with modest amounts of factor concentrates and anti-fibrinolytic drugs. This is very important in developing countries where factor concentrates are not easily available. In one patient haemophilia was diagnosed only after surgery. None of the patients had inhibitor pre- or post-operatively. One patient who was HIV positive underwent orchidectomy successfully with only 6000 IU of factor VIII concentrate.