Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions

Assessment and comparison of prognostic classification schemes for survival data

Prognostic classification schemes have often been used in medical applications, but rarely subjected to a rigorous examination of their adequacy. For survival data, the statistical methodology to assess such schemes consists mainly of a range of ad hoc approaches, and there is an alarming lack of commonly accepted standards in this field. We review these methods and develop measures of inaccuracy which may be calculated in a validation study in order to assess the usefulness of estimated patient-specific survival probabilities associated with a prognostic classification scheme. These measures are meaningful even when the estimated probabilities are misspecified, and asymptotically they are not affected by random censorship. In addition, they can be used to derive R(2)-type measures of explained residual variation. A breast cancer study will serve for illustration throughout the paper.

Neural network prediction of obstructive sleep apnea from clinical criteria

STUDY OBJECTIVES

Clinical prediction models for the diagnosis of obstructive sleep apnea (OSA) have lacked the accuracy necessary to confidently replace polysomnography (PSG). Artificial neural networks are computer programs that can be trained to predict outcomes based on experience. This study was conducted to test the hypothesis that a generalized regression neural network (GRNN) could accurately classify patients with OSA from clinical data.

STUDY DESIGN

Retrospective review.

SETTING

Regional sleep referral center.

PATIENTS

Randomly selected records of patients referred for possible OSA.

MEASUREMENTS

The neural network was trained using 23 clinical variables from 255 patients, and the predictive performance was evaluated using 150 other patients.

RESULTS

The prevalence of OSA in this series of 405 patients (293 men and 112 women) was 69%. The trained GRNN had an accuracy of 91.3% (95% confidence interval [CI], 86.8 to 95.8). The sensitivity was 98.9% for having OSA (95% CI, 96.7 to 100), and the specificity was 80% (95% CI, 70 to 90). The positive predictive value that the patient would have OSA was 88.1% (95% CI, 81.8 to 94.4), whereas the negative predictive value that the patient would not have OSA (if so classified) was 98% (95% CI, 94 to 100).

CONCLUSIONS

Appropriately trained GRNN has the ability to accurately rule in OSA from clinical data, and GRNN did not misclassify patients with moderate to severe OSA. In this study, use of the neural network could have reduced the number of PSG studies performed. Prospective validation of the neural network for the diagnosis of OSA is now required.

Prognostic factor research in oncology

The prognosis of solid tumors is predominantly influenced by the anatomic extent before and after initial treatment. It is defined by the TNM/pTNM system and the residual tumor (R) classification as internationally agreed on and published by the International Union Against Cancer (UICC). However, there are several independent factors effective in prognosis in addition to TNM and R. Their identification is the first objective in prognostic factor research. Correctly applied multivariate methods appropriate for the specific situation play a key role. Cooperation between clinical oncologists and experienced medical statisticians is indispensable. Putative new prognostic factors have to be carefully evaluated before they can be accepted for general use in clinical oncology. In the future, we have to focus on the development of prognostic systems. Such systems integrate multiple independent prognostic factors with present staging (TNM, R) to improve the assessment of prognosis.

An evaluation of intelligent prognostic systems for colorectal cancer

In this paper we describe attempts at building a robust model for predicting the length of survival of patients with colorectal cancer. The aim of the research, reported in this paper, is to study the effective utilisation of artificial intelligence techniques in the medical domain. We suggest that an important research objective of proponents of intelligent prognostic systems must be to evaluate the additionality that AI techniques can bring to an already well-established field of medical prognosis. Towards this end, we compare a number of different AI techniques that lend themselves to the task of predicting survival in colorectal cancer patients. We describe the pros and cons of each of these methods using the usual metrics of accuracy and perspicuity. We then present the notion of intelligent hybrid systems and evaluate the role that they may potentially play in developing robust prognostic models. In particular we evaluate a hybrid system that utilises the k Nearest Neighbour technique in conjunction with Genetic Algorithms. We describe a number of innovations used within this hybrid paradigm used to build the prognostic model. We discuss the issue of censored patients and how this issue can be tackled within the various models used. In keeping with our objective of studying the additionality that AI techniques bring to building prognostic models, we use Cox's regression as a standard and compare each AI technique with it, attempting to discover their capabilities in enhancing prognostic methods in medicine. In doing so we address two main questions--which model fits the data best?, and are the results obtained by the various AI techniques significantly different from those of Cox's regression? We conclude this paper by discussing future enhancements to the work presented and lessons learned from the study to date.

The effect of four interventions on the informational content of histopathology reports of resected colorectal carcinomas

AIM

To investigate the effect of different interventions on the inclusion of data items in the histopathology reports of resected colorectal carcinomas.

STUDY POPULATION

272 routine histopathology reports on colorectal carcinomas from the department of histopathology, Royal Hallamshire Hospital, Sheffield.

METHODS

The presence or absence of 10 specific data items was recorded for each report. The reports were divided into five audit periods. In the initial period reports were generated using free text with no agreed guidelines. In period 2, text guidelines had been issued; in period 3, flow diagram guidelines had been issued; and in periods 4 and 5, template proformas were attached to each specimen request form.

RESULTS

All interventions produced some increase in inclusion rate for some features, but only with the introduction of template proformas did these rates approach 100% for all data items. Inclusion rates were 100% for all items in all cases reported using a proforma. In the final audit period 96% of specimens were reported using proformas.

CONCLUSIONS

Template proformas produce a high rate of inclusion of data items in reports of colorectal carcinoma resection specimens.

Artificial neural network model of survival in patients treated with irradiation with and without concurrent chemotherapy for advanced carcinoma of the head and neck

PURPOSE

This study was performed to investigate the feasibility of predicting survival in squamous cell carcinoma of the head and neck (SCCHN) with an artificial neural network (ANN), and to compare ANN performance with conventional models.

METHODS AND MATERIALS

Data were analyzed from a Phase III trial in which patients with locally advanced SCCHN received hyperfractionated irradiation with or without concurrent cisplatin and 5-fluorouracil. Of the 116 randomized patients, 95 who had 2-year follow-up and all required data were evaluated. ANN and logistic regression (LR) models were constructed to predict 2-year total survival using round-robin cross-validation. A modified staging model was also examined.

RESULTS

The best LR model used tumor size, nodal stage, and race to predict survival. The best ANN used nodal stage, tumor size, stage, and resectability, and hemoglobin. Treatment type did not predict 2-year survival and was not included in either model. Using the respective best feature sets, the area under the receiver operating characteristic curve (Az) for the ANN was 0.78 +/- 0.05, showing more accurate overall performance than LR (Az = 0.67 +/- 0.05, p = 0.07). At 70% sensitivity, the ANN was 72% specific, while LR was 54% specific (p = 0.08). At 70% specificity, the ANN was 72% sensitive, while LR was 54% sensitive (p = 0.07). When both models used the five predictive variables best for an ANN, Az for LR decreased [Az = 0.61 +/- 0.06, p < 0.01 (ANN)]. The models performed equivalently when using the three variables best for LR. The best ANN also compared favorably with staging [Az = 0.60 +/- 0.07, p = 0.02 (ANN)].

CONCLUSIONS

An ANN modeled 2-year survival in this data set more accurately than LR or staging models and employed predictive variables that could not be used by LR. Further work is planned to confirm these results on larger patient samples, examining longer follow-up to incorporate treatment type into the model.