Genetic adaptive neural network to predict biochemical failure after radical prostatectomy: a multi-institutional study

BACKGROUND AND PURPOSE

Despite many new procedures, radical prostatectomy remains one of the commonest methods of treating clinically localized prostate cancer. Both from the physician's and the patient's point of view, it is important to have objective estimation of the likelihood of recurrence, which forms the foundation for treatment selection for an individual patient. Currently, it is difficult to predict the probability of biochemical recurrence (rising serum prostate specific antigen [PSA] concentration) in an individual patient, and approximately 30% of the patients do experience recurrence. Tools predicting the recurrence will be of immense practical utility in the treatment selection and planning follow up. We have utilized preoperative parameters through a computer based genetic adaptive neural network model to predict recurrence in such patients, which can help primary care physicians and urologists in making management recommendations.

PATIENTS AND METHODS

Fourteen hundred patients who underwent radical prostatectomy at participating institutions form the subjects of this study. Demographic data such as age, race, preoperative PSA, systemic biopsy based staging and Gleason scores were used to construct a neural network model. This model simulated the functioning of a trained human mind and learned from the database. Once trained, it was used to predict the outcomes in new patients.

RESULTS

The patients in this comprehensive database were representative of the average prostate cancer patients as seen in USA. Their mean age was 68.4 years, the mean PSA concentration before surgery was 11.6 ng/mL, and 67% patients had a Gleason sum of 5 to 7. The mean length of follow-up was 41.5 months. Eighty percent of the cancers were clinical stage T2 and 5% T3. In our series, 64% of patients had pathologically organ-confined cancer, 33% positive margins, and 14% had seminal vesicle invasion. Lymph node positive patients were not included in this series. Progression as judged by serum PSA was noted in 30.6%. With entry of a few routinely used parameters, the model could correctly predict recurrence in 76% of the patients in the validation set. The area under the curve was 0.831. The sensitivity was 85%, the specificity 74%, the positive predictive value 77%, and the negative predictive value of 83%.

CONCLUSION

It was possible to predict PSA recurrence with a high accuracy (76%). Physicians desiring objective treatment counseling can use this model, and significant cost savings are anticipated because of appropriate treatment selection and patient-specific follow-up protocols. This technology can be extended to other treatments such as watchful waiting, external-beam radiation, and brachytherapy.

Long-term efficacy of sildenafil and tachyphylaxis effect

PURPOSE

We observed that patients who initially responded to sildenafil frequently became resistant to it with time. We evaluated the long-term efficacy of sildenafil.

MATERIALS AND METHODS

A telephone survey was conducted of patients during the first year of sildenafil usage, and another one was completed 2 years later of the same group.

RESULTS

During the first survey, the etiology of impotence included post radical prostatectomy in 25, arterial insufficiency in 26, diabetes in 19, neurogenic impotence in 12, suspected venous leak in 9, proved venous leak in 7, Peyronie's disease in 6 and unspecified in 47 patients. The overall improvement rate, which was defined as the ability to initiate and maintain erections for successful intercourse, was 74%. The dose necessary to achieve this response was 100 mg. sildenafil in 15% of patients, 50 mg. in 83% and 25 mg. in 2%. During the second survey, information was collected on 82 patients and only 43 (52%) had continued treatment. Of the 69 patients who reported an initial good response 41 (59%) were still using sildenafil, and of the 43 who were still using it 16 (37%) had to increase the dose by 50 mg. to achieve an adequate result. There was no significant relationship between the need to increase the dose and frequency of treatment per month. Reduction in efficacy ranged from 15% to 50% (mean 36 +/- 12%) and the time to loss of efficacy ranged from 1 to 18 months (mean 11 +/- 5). Of the 82 patients in the second surgery, 39 (48%) stopped using sildenafil. A total of 28 (74%) patients reported a good initial response on the first survey, and 6 had spontaneous erections and no longer needed treatment. However, 14 (50%) patients discontinued sildenafil because of the loss of efficacy. In this group 10 patients had side effects, mainly headache and flushing of the face and nose, and only 2 discontinued treatment because of them.

CONCLUSIONS

Our data suggest that there is a possible tachyphylaxis effect with sildenafil. Of the patients who were followed for 2 years 20% had to increase the sildenafil dose to have the same effect and 17% discontinued use due to loss of efficacy.

Poor prognosis associated with thrombocytosis in patients with renal cell carcinoma

OBJECTIVES

To better define the relationship between platelet count and survival using a retrospective analysis in patients with thrombocytosis and metastatic renal cell carcinoma (RCC), some of whom had a shorter life expectancy than those with a normal platelet count.

PATIENTS AND METHODS

The records were reviewed of patients with stage IV RCC who had undergone a variety of adjuvant therapies after nephrectomy between 1972 and 1992. Entry criteria included a tissue diagnosis of RCC, at least one platelet count and a complete follow-up until the time of death. Of 350 patients available for review, 259 met the entry criteria. Patients were divided into two groups: group 1 included 112 patients whose platelet counts remained at < 4 x 105/microL between the time of nephrectomy and the time of death; group 2 included 147 patients with at least one platelet count of > 4 x 105/microL (mean age in each group 57 years).

RESULTS

The mean (SD) survival for group 1 was 151 (34) months, compared with 92 (18) months for those in group 2. Using the log-rank chi-square test the difference in survival between the groups was significant (P = 0.005). Controlling for established prognostic indicators of pathological stage, nuclear grade and cell type, using Cox's regression technique, the difference in survival between the groups remained significant (P = 0.015).

CONCLUSIONS

These results suggest that patients with metastatic RCC who receive adjuvant therapy and have a persistently normal platelet count have a 64% longer life expectancy than those with thrombocytosis. The difference is highly statistically significant when controlled for nuclear grade, cell type and pathological stage.

Analgesia during extracorporeal shock wave lithotripsy using the Medstone STS lithotriptor: a randomized prospective study

OBJECTIVES

To investigate and compare the effectiveness of three analgesic protocols for pain management during extracorporeal shock wave lithotripsy (ESWL) in a prospective, randomized clinical trial.

METHODS

Seventy-four patients were randomized into three groups before ESWL; group A (n = 23) received 10 mg morphine sulfate (MS), group B (n = 25) 60 mg ketorolac tromethamine (KT), and group C (n = 26) topical 2.5% lidocaine/prilocaine gel (Emla). Each method of pain management during ESWL was assessed using a standard 10-point linear pain scale and by the requirement for supplemental analgesia during treatment. Supplemental analgesia was administered intravenously using a patient-controlled analgesic pump. The results were compared between the three groups, as were such parameters as body habitus, stone burden, stone location, number of shock waves, and the presence of ureteral stents.

RESULTS

Pain severity averaged 4.6 points on the pain scale for the three groups combined. Pain tended to be more severe in group C (5.4) than in group A (4.3) or group B (4.1); however, the differences were not statistically significant (P>0.05). The amount of supplemental analgesia was similar in all three groups. Stone burden, stone location, and number of shock waves did not influence the severity of pain or analgesic requirement during ESWL. The analgesic requirement was significantly less in patients with ureteral stents (n = 32) than in patients without (n = 42), averaging 10 mg versus 24 mg MS, respectively (P = 0.01). KT was not associated with adverse events such as bleeding. MS was more likely to cause oversedation and nausea or vomiting, necessitating naloxone and antiemetic therapy, respectively.

CONCLUSIONS

The use of KT was safe and effective for premedication before ESWL; patients receiving KT before ESWL reported lower pain scores and required less supplemental analgesia requirement than those who received MS or Emla; however, the differences were not statistically significant. Patients receiving Emla recorded the highest pain scores. Patients with ureteral stents had lower pain scores and required less supplemental analgesia.

Factors predicting cancer detection in biopsy of the prostatic fossa after radical prostatectomy

OBJECTIVES

To determine whether the results of anastomotic biopsy for prostate-specific antigen (PSA) recurrence after radical prostatectomy could be predicted by either PSA, PSA velocity, digital rectal examination (DRE), transrectal ultrasound (TRUS), or the interval from prostatectomy to biopsy.

METHODS

TRUS with biopsy of the anastomosis was performed for 91 postprostatectomy patients who had either an abnormal DRE or detectable PSA (greater than 0.2 ng/mL). The biopsy results were correlated with the findings of DRE, TRUS, PSA, PSA velocity, interval to PSA recurrence, and with the pathologic stage.

RESULTS

Of 131 examinations, there were 50 positive biopsy specimens for a detection rate of 38%. Of 34 patients with PSA 1.0 ng/mL or less, 8 (24%) had positive biopsy (P = 0.02). A negative DRE lowered (but did not eliminate) the probability of a positive biopsy. Of 100 patients with normal DRE, 28 (28%) had positive biopsy. None of the 11 patients with a negative DRE and a PSA of 0.5 ng/mL or less had a positive biopsy (P = 0.02). The mean interval between prostatectomy and biopsy was significantly greater in patients who had a positive biopsy (45 +/- 39) than in patients with a negative biopsy (27 +/- 21) (P = 0.001). The pathologic stage, Gleason score, and PSA velocity were not helpful in predicting the results of biopsy.

CONCLUSIONS

Although patients with a negative DRE can have a positive biopsy and patients with a PSA of 1.0 ng/mL or less can have a positive biopsy, no patient with a negative DRE and a PSA of 0.5 ng/mL or less has a positive biopsy.