The prediction of risk of recurrence and time to recurrence of hepatocellular carcinoma after orthotopic liver transplantation: a pilot study.

Orthotopic liver transplantation (OLTx) in the presence of hepatocellular carcinoma (HCC) has been complicated by high recurrence rates. The ability to determine the risk and timing of HCC recurrence on an individual basis would greatly aid in the candidate selection process resulting in a more efficient use of donated organs and allow the individualization and better evaluation of adjuvant chemotherapy. The 214 patients who underwent OLTx in the presence of HCC were analyzed. From the 178 patients who survived more than 150 days, 71 (40%) have suffered HCC recurrence. Based on five risk factors, that is, gender, tumor number, lobar tumor distribution, tumor size, grade of vascular invasion, artificial neural network models predicting the likelihood of HCC recurrence within 1, 2, and 3 consecutive years after transplantation were developed. Based on model predictions, those combinations of risk factors that should/should not lead to recurrence were generated, allowing stratification of patients into the following three groups: 1) patients who should not suffer HCC recurrence and who should not need adjuvant therapy, 2) patients who will suffer recurrence and for whom postoperative chemotherapy significantly prolonged survival (but did not prevent recurrence), and 3) patients who may or may not suffer HCC recurrence and whose recurrence may be prevented by adjuvant chemotherapy. The outcome of OLTx for patients with HCC can be prognosticated based on a number of clinical variables. If verified through multicenter trials, these models could be made available to transplantation programs performing OLTx in the presence of HCC.

Multisolutional clustering and quantization algorithm (MCQ).

We have developed a novel clustering and quantization algorithm that allows the user to create multiple one-to-one correspondences between the actual data and its transformed (clustered and quantized) values, based on the user's hypothesis regarding the nature of the classification task. The types of problems for which the algorithm can be beneficial are discussed. We report experiments employing simulated and real data that suggest the proposed algorithm may be useful in neural network analysis of various phenomena in medicine and biology.

Performance of multi-layer feedforward neural networks to predict liver transplantation outcome.

A novel multisolutional clustering and quantization (MCQ) algorithm has been developed that provides a flexible way to preprocess data. It was tested whether it would impact the neural network's performance favorably and whether the employment of the proposed algorithm would enable neural networks to handle missing data. This was assessed by comparing the performance of neural networks using a well-documented data set to predict outcome following liver transplantation. This new approach to data preprocessing leads to a statistically significant improvement in network performance when compared to simple linear scaling. The obtained results also showed that coding missing data as zeroes in combination with the MCQ algorithm, leads to a significant improvement in neural network performance on a data set containing missing values in 59.4% of cases when compared to replacement of missing values with either series means or medians.

Comparative in vitro study of nonoxynol-9: effects on human, bull and boar spermatozoa.

Spermicidal activity of different dilutions of nonoxynol-9 (nonyl-phenoxy-polyethoxy-ethanol) on human, bull and boar spermatozoa was studied using the modified Sander-Cramer method. The results obtained showed that differences in spermatozoal resistance among the mentioned species to nonoxynol-9 were statistically very significant (P much less than 0.0005): bull greater than man greater than boar. The results obtained were compared to available literature results.