-
[show abstract]
[hide abstract]
ABSTRACT: To develop an artificial neural network (ANN) model to predict lymph node (LN) spread in men with clinically localized prostate cancer and to describe a clinically useful method for interpreting the ANN's output scores.
A simple, feed-forward ANN was trained and validated using clinical and pathologic data from two institutions (n = 6135 and n = 319). The clinical stage, biopsy Gleason sum, and prostate-specific antigen level were the input parameters and the presence or absence of LN spread was the output parameter. Patients with similar ANN outputs were grouped and assumed to be part of a cohort. The prevalence of LN spread for each of these patient cohorts was plotted against the range of ANN outputs to create a risk curve.
The area under the receiver operating characteristic curve for the first and second validation data sets was 0.81 and 0.77, respectively. At an ANN output cutoff of 0.3, the sensitivity achieved for each validation set was 63.8% and 44.4%; the specificity was 81.5% and 81.3%; the positive predictive value was 13.6% and 6.5%; and the negative predictive value was 98.0% and 98.1%, respectively. The risk curve showed a nearly linear increase (best fit R(2) = 0.972) in the prevalence of LN spread with increases in raw ANN output.
The ANN's performance on the two validation data sets suggests a role for ANNs in the accurate clinical staging of patients with prostate cancer. The risk curve provides a clinically useful tool that can be used to give patients a realistic assessment of their risk of LN spread.
Urology 04/2001; 57(3):481-5. · 2.43 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Prostate-specific antigen determinations for prostate cancer screening have led to a dramatic increase in the number of men who are diagnosed with organ-confined and therefore potentially curable prostate cancer. Advances in predicting outcomes with artificial neural networks may help to recommend one therapy over another. Less invasive forms of treatment, such as high-intensity focused ultrasound, may ultimately give patients additional options for treatment. Furthermore, attempts to better define the role of both neoadjuvant hormonal therapy and chemotherapy may give higher-risk patients better outcomes than with current treatments. These advances as well as continued research will likely lead to a day when more and more men with organ-confined disease will be cured.
Reviews in urology 02/2001; 3 Suppl 2:S39-48.
-
[show abstract]
[hide abstract]
ABSTRACT: This review describes two studies to evaluate artificial neural networks (ANNs) in prostate cancer staging. In the first study, an ANN was trained to identify prostate cancer patients at low risk of lymph node spread (LNS). The second study evaluated an ANN to predict capsular penetration (CP) in men with clinically localized prostate cancer. An accurate assessment of lymph node status will help identify those brachytherapy patients in whom lymphadenectomy can be avoided. The accurate prediction of CP can help determine the appropriateness of brachytherapy as a treatment option.
An ANN to predict LNS was trained and tested using a database from one institution (n = 4,133) and validated using two databases (n = 330 and n = 227) from different institutions. The clinical variables used were clinical stage (cTNM), Gleason sum, and prostate-specific antigen concentration (PSA). The ANN to predict CP was trained and validated with data from a single institution (n = 409). The variables used were age, race, PSA, PSA velocity, Gleason sum, and cTNM.
The LNS ANN was able classify 76%, 75%, and 30% of the patients in each database as being at low risk of LNS with 98% accuracy. The CP ANN correctly identified CP in 25 (84%) of patients and produced 5 (16%) false-negative predictions.
These preliminary results suggest that ANNs can be useful in staging prostate cancer. If sufficiently accurate ANNs can be developed and tested, they have the potential to increase the accuracy of clinical staging and thus improve treatment decisions.
Techniques in urology 07/2000; 6(2):60-3.
-
E D Crawford, J T Batuello,
P Snow,
E J Gamito,
D G McLeod,
A W Partin,
N Stone,
J Montie,
R Stock,
J Lynch,
J Brandt
[show abstract]
[hide abstract]
ABSTRACT: The current study assesses artificial intelligence methods to identify prostate carcinoma patients at low risk for lymph node spread. If patients can be assigned accurately to a low risk group, unnecessary lymph node dissections can be avoided, thereby reducing morbidity and costs.
A rule-derivation technology for simple decision-tree analysis was trained and validated using patient data from a large database (4,133 patients) to derive low risk cutoff values for Gleason sum and prostate specific antigen (PSA) level. An empiric analysis was used to derive a low risk cutoff value for clinical TNM stage. These cutoff values then were applied to 2 additional, smaller databases (227 and 330 patients, respectively) from separate institutions.
The decision-tree protocol derived cutoff values of < or = 6 for Gleason sum and < or = 10.6 ng/mL for PSA. The empiric analysis yielded a clinical TNM stage low risk cutoff value of < or = T2a. When these cutoff values were applied to the larger database, 44% of patients were classified as being at low risk for lymph node metastases (0.8% false-negative rate). When the same cutoff values were applied to the smaller databases, between 11 and 43% of patients were classified as low risk with a false-negative rate of between 0.0 and 0.7%.
The results of the current study indicate that a population of prostate carcinoma patients at low risk for lymph node metastases can be identified accurately using a simple decision algorithm that considers preoperative PSA, Gleason sum, and clinical TNM stage. The risk of lymph node metastases in these patients is < or = 1%; therefore, pelvic lymph node dissection may be avoided safely. The implications of these findings in surgical and nonsurgical treatment are significant.
Cancer 06/2000; 88(9):2105-9. · 4.77 Impact Factor
