Invited Article

The purpose of this review is to assess the evidence of healthcare bene®ts involving the application of arti®cial neural networks to the clinical functions of diagnosis, prognosis and survival analysis, in the medical domains of oncology, critical care and cardiovascular medicine. The primary source of publications is PUBMED listings under Randomised Controlled Trials and Clinical Trials. The ro Ãle of neural networks is introduced within the context of advances in medical decision support arising from parallel developments in statistics and arti®cial intelligence. This is followed by a survey of published Randomised Controlled Trials and Clinical Trials, leading to recommendations for good practice in the design and evaluation of neural networks for use in medical intervention. q 2002 Elsevier Science Ltd. All rights reserved.

[1]  Patrick van der Smagt,et al.  An introduction to neural networks , 2018 .

[2]  D. Collet.  Modelling Survival Data in Medical Research , 2004 .

[3]  Paulo J. G. Lisboa,et al.  Are neural networks best used to help logistic regression? An example from breast cancer survival analysis , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[4]  T. Stamey,et al.  Comparison of a Neural Network with High Sensitivity and Specificity to Free/total Serum PSA for Diagnosing Prostate Cancer in Men with a PSA < 4.0 ng/mL , 2001 .

[5]  R. Lordo.  Learning from Data: Concepts, Theory, and Methods , 2001, Technometrics.

[6]  D. Altman.  Statistics in medical journals: some recent trends. , 2000, Statistics in medicine.

[7]  T. Stephenson,et al.  Validation of a decision support system for the cytodiagnosis of fine needle aspirates of the breast using a prospectively collected dataset from multiple observers in a working clinical environment , 2000, Cytopathology : official journal of the British Society for Clinical Cytology.

[8]  J P Shepherd,et al.  treatment planning: A controlled trial of three referral methods for patients with third molars. , 2000, British Dental Journal.

[9]  Yves D'Asseler,et al.  Automatic quantification of defect size using normal templates: a comparative clinical study of three commercially available algorithms , 2000, European Journal of Nuclear Medicine.

[10]  Paulo J. G. Lisboa,et al.  Robust methodology for the discrimination of brain tumours from in vivo magnetic resonance spectra , 2000 .

[11]  Andrew Thomas,et al.  WinBUGS - A Bayesian modelling framework: Concepts, structure, and extensibility , 2000, Stat. Comput..

[12]  P. Sandercock,et al.  Framework for design and evaluation of complex interventions to improve health , 2000, BMJ : British Medical Journal.

[13]  F M Debruyne,et al.  Neural network‐based digitized cell image diagnosis of bladder wash cytology , 2000, Diagnostic cytopathology.

[14]  A F Taktak,et al.  Neural network analysis of oxygenation signals in infants during sleep , 2000, Physiological measurement.

[15]  Jae K. Lee,et al.  Mining and Visualizing Large Anticancer Drug Discovery Databases , 2000, J. Chem. Inf. Comput. Sci..

[16]  G. Murray,et al.  Disability in young people and adults one year after head injury: prospective cohort study , 2000, BMJ : British Medical Journal.

[17]  Gamito Ej,et al.  Use of artificial neural networks in the clinical staging of prostate cancer: implications for prostate brachytherapy. , 2000, Techniques in urology.

[18]  Paulo J. G. Lisboa,et al.  Bias reduction in skewed binary classification with Bayesian neural networks , 2000, Neural Networks.

[19]  E. Pifer,et al.  Computerized decision support and the quality of care. , 2000, Managed care.

[20]  J A Espinosa,et al.  Reducing errors made by emergency physicians in interpreting radiographs: longitudinal study , 2000, BMJ : British Medical Journal.

[21]  R. Gibberd,et al.  Epidemiology of medical error , 2000, BMJ : British Medical Journal.

[22]  P. Barach,et al.  Reporting and preventing medical mishaps: lessons from non-medical near miss reporting systems , 2000, BMJ : British Medical Journal.

[23]  Paulo J. G. Lisboa,et al.  Artificial Neural Networks in Biomedicine , 2000, Perspectives in Neural Computing.

[24]  J Riess,et al.  Adaptive neural network control of cyclic movements using functional neuromuscular stimulation. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[25]  Richard W. McCallum,et al.  Noninvasive feature-based detection of delayed gastric emptying in humans using neural networks , 2000, IEEE Transactions on Biomedical Engineering.

[26]  D G Altman,et al.  What do we mean by validating a prognostic model? , 2000, Statistics in medicine.

[27]  Jørgen Hilden.  Prevalence-free utility-respecting summary indices of diagnostic power do not exist. , 2000, Statistics in Medicine.

[28]  W L Wu,et al.  Potential of the back propagation neural network in the assessment of gait patterns in ankle arthrodesis. , 2000, Clinical biomechanics.

[29]  R Chang,et al.  An automated form of video image analysis applied to classification of movement disorders , 2000, Disability and rehabilitation.

[30]  J D Habbema,et al.  The diagnostic value of computer-assisted primary cervical smear screening: a longitudinal cohort study. , 1999, Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc.

[31]  Hans H.C.M. Savelberg,et al.  Assessment of the horizontal, fore-aft component of the ground reaction force from insole pressure patterns by using artificial neural networks , 1999 .

[32]  Gilbert Reibnegger,et al.  The determination of three subcutaneous adipose tissue compartments in non-insulin-dependent diabetes mellitus women with artificial neural networks and factor analysis , 1999, Artif. Intell. Medicine.

[33]  L Tarassenko,et al.  Second by second patterns in cortical electroencephalograph and systolic blood pressure during Cheyne-Stokes. , 1999, The European respiratory journal.

[34]  J Cuzick,et al.  Cervical screening in the United Kingdom. , 1999, Hong Kong medical journal = Xianggang yi xue za zhi.

[35]  David R. Jones,et al.  An introduction to bayesian methods in health technology assessment , 1999, BMJ.

[36]  Kjell Arne Kvistad,et al.  Applications of neural network analyses to in vivo 1H magnetic resonance spectroscopy of epilepsy patients , 1999, Epilepsy Research.

[37]  L. Ohno-Machado,et al.  Neural network applications in physical medicine and rehabilitation. , 1999, American journal of physical medicine & rehabilitation.

[38]  H. Heinrich,et al.  Single-sweep analysis of event-related potentials by wavelet networks-methodological basis and clinical application , 1999, IEEE Transactions on Biomedical Engineering.

[39]  William D. Penny,et al.  An empirical evaluation of Bayesian sampling with hybrid Monte Carlo for training neural network classifiers , 1999, Neural Networks.

[40]  N Bosanquet,et al.  Assessment of automated primary screening on PAPNET of cervical smears in the PRISMATIC trial , 1999, The Lancet.

[41]  E B Ringelstein,et al.  Automatic embolus detection by a neural network. , 1999, Stroke.

[42]  Richards,et al.  A COMPARISON OF COX REGRESSION AND NEURAL NETWORKS FOR RISK STRATIFICATION IN CASES OF ACUTE LYMPHOBLASTIC LEUKAEMIA IN CHILDREN , 1999 .

[43]  R. Cantu,et al.  The prediction of common bile duct stones using a neural network. , 1998, Journal of the American College of Surgeons.

[44]  Geoffrey E. Hinton,et al.  A comparison of statistical learning methods on the Gusto database. , 1998, Statistics in medicine.

[45]  W E Reddick,et al.  Hybrid artificial neural network segmentation and classification of dynamic contrast-enhanced MR imaging (DEMRI) of osteosarcoma. , 1998, Magnetic resonance imaging.

[46]  M E Brier,et al.  Prediction of anticoagulation during hemodialysis by population kinetics and an artificial neural network. , 1998, Artificial organs.

[47]  L S Wong,et al.  A comparison of ICU mortality prediction using the APACHE II scoring system and artificial neural networks , 1998, Anaesthesia.

[48]  N. Olsen,et al.  Analysis of 31P MR spectroscopy data using artificial neural networks for longitudinal evaluation of musclediseases: dermatomyositis , 1998, NMR in biomedicine.

[49]  E. Biganzoli,et al.  Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. , 1998, Statistics in medicine.

[50]  M. Gaetz,et al.  Neural network classifications and correlation analysis of EEG and MEG activity accompanying spontaneous reversals of the Necker cube , 1998 .

[51]  C.W. Anderson,et al.  Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks , 1998, IEEE Transactions on Biomedical Engineering.

[52]  J Röschke,et al.  Effects of Lorazepam on the Automatic Online Evaluation of Sleep EEG Data in Healthy Volunteers , 1998, Pharmacopsychiatry.

[53]  R. Golden,et al.  Use of a neural network to predict stone growth after shock wave lithotripsy. , 1998, Urology.

[54]  A R Jadad,et al.  The randomized controlled trial gets a middle-aged checkup. , 1998, JAMA.

[55]  T J O'Leary,et al.  PAPNET-assisted rescreening of cervical smears: cost and accuracy compared with a 100% manual rescreening strategy. , 1998, JAMA.

[56]  A. Heinz,et al.  Analysis of Quantitative EEG with Artificial Neural Networks and Discriminant Analysis – A Methodological Comparison , 1997, Neuropsychobiology.

[57]  Hualou Liang,et al.  Application of combined genetic algorithms with cascade correlation to diagnosis of delayed gastric emptying from electrogastrograms , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[58]  K Schreiber,et al.  Significant reduction in the rate of false-negative cervical smears with neural network-based technology (PAPNET Testing System). , 1997, Human pathology.

[59]  M A Leon,et al.  Ventilation mode recognition using artificial neural networks. , 1997, Computers and biomedical research, an international journal.

[60]  C J Snijders,et al.  Computerized analysis of daily life motor activity for ambulatory monitoring. , 1997, Technology and health care : official journal of the European Society for Engineering and Medicine.

[61]  D. Josefson.  Computers beat doctors in interpreting ECGs , 1997 .

[62]  B. Zernikow,et al.  Predicting length-of-stay in preterm neonates , 1997, European Journal of Pediatrics.

[63]  L.C. Goodenday,et al.  Identifying coronary stenosis using an image-recognition neural network , 1997, IEEE Engineering in Medicine and Biology Magazine.

[64]  William Moran,et al.  On the use of artificial neural networks for the analysis of survival data , 1997, IEEE Trans. Neural Networks.

[65]  Peter J. F. Lucas,et al.  Model-based diagnosis in medicine , 1997, Artif. Intell. Medicine.

[66]  L. Mango,et al.  Evaluation of PAPNET testing as an ancillary tool to clarify the status of the "atypical" cervical smear. , 1997, Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc.

[67]  R. Tibshirani,et al.  Improvements on Cross-Validation: The 632+ Bootstrap Method , 1997 .

[68]  F T de Dombal,et al.  Measuring surgical performance in acute abdominal pain: some reflections from international studies. , 1997, The European journal of surgery = Acta chirurgica.

[69]  T S Kuo,et al.  A neuro-control system for the knee joint position control with quadriceps stimulation. , 1997, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[70]  M Schumacher,et al.  Effects of covariate omission and categorization when analysing randomized trials with the Cox model. , 1997, Statistics in medicine.

[71]  F. Harrell,et al.  Artificial neural networks improve the accuracy of cancer survival prediction , 1997, Cancer.

[72]  H S Fraser,et al.  An artificial neural network system for diagnosis of acute myocardial infarction (AMI) in the accident and emergency department: evaluation and comparison with serum myoglobin measurements. , 1997, Computer methods and programs in biomedicine.

[73]  B Angus,et al.  The detection of nodal metastasis in breast cancer using neural network techniques , 1996, Physiological measurement.

[74]  T. Balachander,et al.  Neural network analysis of flow cytometry immunophenotype data , 1996, IEEE Transactions on Biomedical Engineering.

[75]  C B Schechter,et al.  Cost-effectiveness of rescreening conventionally prepared cervical smears by PAPNET testing. , 1996, Acta cytologica.

[76]  Konrad Lang,et al.  Evaluation of automatic knowledge acquisition techniques in the diagnosis of acute abdominal pain - Acute Abdominal Pain Study Group , 1996, Artif. Intell. Medicine.

[77]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[78]  J V Haxby,et al.  Network analysis of PET-mapped visual pathways in Alzheimer type dementia. , 1995, Neuroreport.

[79]  R. Dybowski,et al.  Artificial neural networks in pathology and medical laboratories , 1995, The Lancet.

[80]  G. Dombi,et al.  Prediction of rib fracture injury outcome by an artificial neural network. , 1995, The Journal of trauma.

[81]  R. D'Agostino,et al.  A comparison of performance of mathematical predictive methods for medical diagnosis: identifying acute cardiac ischemia among emergency department patients. , 1995, Journal of investigative medicine : the official publication of the American Federation for Clinical Research.

[82]  F. Gürgen,et al.  The assessment of LH surge for predicting ovulation time using clinical, hormonal, and ultrasonic indices in infertile women with an ensemble of neural networks. , 1995, Computers in Biology and Medicine.

[83]  O. Shmueli,et al.  Interpretation of nonstress tests by an artificial neural network. , 1995, American Journal of Obstetrics and Gynecology.

[84]  Zhi-Li Zhang,et al.  Evaluation of a new biochemical index for the estimation of bone demineralization using artificial intelligence. , 1995, Contemporary orthopaedics.

[85]  M Kaps,et al.  Variability of Doppler microembolic signal counts in patients with prosthetic cardiac valves. , 1995, Stroke.

[86]  S. Lemeshow,et al.  Modeling the severity of illness of ICU patients. A systems update. , 1994, JAMA.

[87]  Norberto F. Ezquerra,et al.  Neural computing in medicine , 1994, Artif. Intell. Medicine.

[88]  M S Rogers,et al.  Use of the neural network for hypothesis generation in fetal surveillance. , 1994, Bailliere's clinical obstetrics and gynaecology.

[89]  J H Kerr,et al.  Intensive Care Society's Acute Physiology and Chronic Health Evaluation (APACHE II) study in Britain and Ireland: A prospective, multicenter, cohort study comparing two methods for predicting outcome for adult intensive care patients , 1994, Critical care medicine.

[90]  W. Baxt.  A Neural Network Trained to Identify the Presence of Myocardial Infarction Bases Some Decisions on Clinical Associations That Differ from Accepted Clinical Teaching , 1994, Medical decision making : an international journal of the Society for Medical Decision Making.

[91]  D G Altman,et al.  Transfer of technology from statistical journals to the biomedical literature. Past trends and future predictions. , 1994, JAMA.

[92]  K. Liestøl,et al.  Survival analysis and neural nets. , 1994, Statistics in medicine.

[93]  J P Kassirer,et al.  A report card on computer-assisted diagnosis--the grade: C. , 1994, The New England journal of medicine.

[94]  M De Laurentiis,et al.  A technique for using neural network analysis to perform survival analysis of censored data. , 1994, Cancer letters.

[95]  F. Mandelli,et al.  Classification of patients affected by multiple myeloma using a neural network software , 1994, European journal of haematology.

[96]  J J Abbas,et al.  Experimental evaluation of an adaptive feedforward controller for use in functional neuromuscular stimulation systems. , 1993, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[97]  M L Astion,et al.  Overtraining in neural networks that interpret clinical data. , 1993, Clinical chemistry.

[98]  M. Boon,et al.  Neural network processing can provide means to catch errors that slip through human screening of pap smears , 1993, Diagnostic cytopathology.

[99]  L. S. Murray,et al.  Does prediction of outcome alter patient management? , 1993, The Lancet.

[100]  Edward H. Shortliffe,et al.  The adolescence of AI in medicine: will the field come of age in the '90s? , 1993, Artif. Intell. Medicine.

[101]  James A. Reggia,et al.  Neural computation in medicine , 1993, Artif. Intell. Medicine.

[102]  J. Concato,et al.  The Risk of Determining Risk with Multivariable Models , 1993, Annals of Internal Medicine.

[103]  William G. Baxt,et al.  Improving the Accuracy of an Artificial Neural Network Using Multiple Differently Trained Networks , 1992, Neural Computation.

[104]  O. Kirton,et al.  Further appraisal of APACHE II limitations and potential. , 1992, Surgery, gynecology & obstetrics.

[105]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[106]  R. Ledley,et al.  Reasoning foundations of medical diagnosis. , 1991, M.D. computing : computers in medical practice.

[107]  David G. Bounds,et al.  A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders , 1990, Neural Networks.

[108]  J. Civetta,et al.  Evaluation of APACHE II for Cost Containment and Quality Assurance , 1990, Annals of surgery.

[109]  G. Giles,et al.  Cervical cancers diagnosed after negative results on cervical cytology: perspective in the 1980s. , 1990, BMJ.

[110]  Jeremy Wyatt,et al.  Decision Aids and the Law , 1989, The Lancet.

[111]  L. Koss.  The Papanicolaou test for cervical cancer detection. A triumph and a tragedy. , 1989, JAMA.

[112]  B. Efron.  Logistic Regression, Survival Analysis, and the Kaplan-Meier Curve , 1988 .

[113]  E F Cook,et al.  A computer protocol to predict myocardial infarction in emergency department patients with chest pain. , 1988, The New England journal of medicine.

[114]  I. Adams,et al.  Computer aided diagnosis of acute abdominal pain: a multicentre study. , 1986, British medical journal.

[115]  Hubert L. Dreyfus,et al.  Why Expert Systems Do Not Exhibit Expertise , 1986, IEEE Expert.

[116]  E H Shortliffe,et al.  PUFF: an expert system for interpretation of pulmonary function data. , 1982, Computers and biomedical research, an international journal.

[117]  F. T. de Dombal,et al.  Human and Computer-aided Diagnosis of Abdominal Pain: Further Report with Emphasis on Performance of Clinicians , 1974, British medical journal.

[118]  William B. Schwartz,et al.  Medicine and the Computer. The Promise and Problems of Change , 1970 .

[119]  Paulo J G Lisboa.  Industrial use of safety-related artificial neural networks , 2001 .

[120]  William R. Hendee,et al.  To Err is Human: Building a Safer Health System , 2001 .

[121]  Leopold G. Koss,et al.  The Application of PAPNET to Diagnostic Cytology , 2000, Artificial Neural Networks in Biomedicine.

[122]  J J de la Rosette,et al.  Prediction of bladder outlet obstruction in men with lower urinary tract symptoms using artificial neural networks. , 2000, The Journal of urology.

[123]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[124]  Y. Hayashi,et al.  A comparison between two neural network rule extraction techniques of hepatobiliary disorders , 2000 .

[125]  W. Vach,et al.  On the misuses of arti"cial neural networks for prognostic and diagnostic classi"cation in oncology , 2000 .

[126]  J. Wei,et al.  Artificial neural networks for prostate carcinoma risk assessment: An overview. , 2000, Cancer.

[127]  J. Reason.  Human error: models and management. , 2000, BMJ.

[128]  Lucila Ohno-Machado,et al.  Evaluating variable selection methods for diagnosis of myocardial infarction , 1999, AMIA.

[129]  Jon Rogers,et al.  Evaluation of an implementation of PRODIGY phase two , 1999, AMIA.

[130]  R. Tibshirani,et al.  The Covariance Inflation Criterion for Adaptive Model Selection , 1999 .

[131]  F. Grus,et al.  Analysis of tear protein patterns by a neural network as a diagnostical tool for the detection of dry eyes , 1999, Electrophoresis.

[132]  D. Bates,et al.  Clinical Decision Support Systems , 1999, Health Informatics.

[133]  R. Haynes,et al.  Effects of Computer-Based Clinical Decision Support Systems on Physician Performance and Patient Outcomes , 1998 .

[134]  P Patterson,et al.  A neural net representation of experienced and nonexperienced users during manual wheelchair propulsion. , 1998, Journal of rehabilitation research and development.

[135]  L. Mango,et al.  Interactive neural-network-assisted screening. An economic assessment. , 1998, Acta cytologica.

[136]  G. Apolone,et al.  Evaluation of the uniformity of fit of general outcome prediction models , 1998, Intensive Care Medicine.

[137]  Christopher M. Bishop,et al.  GTM: The Generative Topographic Mapping , 1998, Neural Computation.

[138]  K. I. Jantunen,et al.  Guide to Medical Informatics, the Internet, and Telemedicine , 1998 .

[139]  E Pesonen,et al.  Is neural network better than statistical methods in diagnosis of acute appendicitis? , 1997, Studies in health technology and informatics.

[140]  L. Mango,et al.  Clinical validation of interactive cytologic screening. Automating the search, not the interpretation. , 1997, Acta cytologica.

[141]  D. Faraggi,et al.  Bayesian Neural Network Models for Censored Data , 1997 .

[142]  T Groth,et al.  Neural network analysis of biochemical markers for early assessment of acute myocardial infarction. , 1997, Studies in health technology and informatics.

[143]  P M Rautaharju,et al.  Using automated analysis of the resting twelve-lead ECG to identify patients at risk of developing transient myocardial ischaemia - an application of an adaptive logic network , 1997 .

[144]  Robert Tibshirani,et al.  A Comparison of Some Error Estimates for Neural Network Models , 1996, Neural Computation.

[145]  Radford M. Neal.  Bayesian learning for neural networks , 1995 .

[146]  David Mackay,et al.  Probable networks and plausible predictions - a review of practical Bayesian methods for supervised neural networks , 1995 .

[147]  Christopher M. Bishop,et al.  Neural Network for Pattern Recognition , 1995 .

[148]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[149]  E. Carson,et al.  A probabilistic approach to glucose prediction and insulin dose adjustment: description of metabolic model and pilot evaluation study. , 1994, Computer methods and programs in biomedicine.

[150]  F T de Dombal,et al.  Computer-assisted diagnosis in Europe. , 1994, New England Journal of Medicine.

[151]  J. Wiles,et al.  Connectionist, rule-based and Bayesian decision aids: an empirical comparison , 1993 .

[152]  J. E. W. Beneken,et al.  Advances in biomedical engineering : results of the 4th EC Medical and Health Research Programme , 1993 .

[153]  P M Ravdin,et al.  Treatment decisions in axillary node-negative breast cancer patients. , 1992, Journal of the National Cancer Institute. Monographs.

[154]  C.A. Kulikowski,et al.  Artificial intelligence in medical consultation systems: a review , 1988, IEEE Engineering in Medicine and Biology Magazine.

[155]  F T de Dombal,et al.  Computer based assistance for medical decision making. , 1984, Gastroentérologie Clinique et Biologique.

[156]  H. E. Pople,et al.  Internist-1, an experimental computer-based diagnostic consultant for general internal medicine. , 1982, The New England journal of medicine.

[157]  Edward H. Shortliffe,et al.  Computer-based medical consultations, MYCIN , 1976 .