Mathematical and computer-assisted procedures in the diagnosis of liver and biliary tract disorders

Computer-assisted diagnosis in gastroenterology

During the last 20 years, Danish gastroenterologists and biostatisticians have been involved in practical and theoretical research aimed at providing computer-assisted decision support in clinical practice. On the practical side, we summarize two clinical applications, one in the acute abdomen, the other in jaundice. The former project is part of a worldwide effort which appears able to reduce considerably the perforated appendix rate and the negative laparotomy rate. In the latter project, also entwined in international activities, three methods of early statistical discrimination of jaundice causes have been tested, and it has been shown how ultrasonographic data can be incorporated into the diagnostic assessment. On the theoretical side, a Dutch-Danish group has been looking into how one best designs a trial and analyses its data in the context of measuring the quality and impact of machine-made diagnostic advice. Having pointed out the international ramifications of these activities, we outline what may lie ahead: Gastroenterologists must be prepared to join large-scale field trials of clinical advice-giving software. In the future, however, such software will often become embedded in general hospital recordkeeping systems.

The intelligent decision mapping patient record (IDMR)

IDMR explored in a representative group of diseases, the design of a European patient record, structured on the decisions made by the doctors in caring for patients throughout their hospitalisation in each country of the European Community. Over 350 patients involving 6000 decisions were entered in the database. Working programs in FoxPro and Windows, a demo Apple program and an expert system in Prolog were delivered. The approach worked well. The catalogue of decisions and costs was illuminating. The complexity of a telematics patient record and the clinical work needed to produce it may be underestimated.

A prospective study of serum tumour markers carcinoembryonic antigen, carbohydrate antigens 50 and 242, tissue polypeptide antigen and tissue polypeptide specific antigen in the diagnosis of pancreatic cancer with special reference to multivariate diagnostic score

The aim of this study was to assess by a stepwise multivariate discriminant analysis the value of four current serum tumour markers - carcinoembryonic antigen (CEA), carbohydrate antigen (CA) 50 and CA 242 and tissue polypeptide antigen (TPA) - and a new serum tumour marker, tissue polypeptide specific antigen (TPS), in the diagnosis of pancreatic cancer. The serum values were measured in a prospective series of patients with jaundice, with unjaundiced cholestasis and with a suspicion of chronic pancreatitis or a pancreatic tumour (n = 193). There were 24 patients with a cancer of the pancreas and two patients with a cancer of the papilla of Vater in this series. Our results showed that CA 50 (P < 0.001) and TPA (P < 0.01) were the best marker tests in predicting pancreatic malignancy. Also, the TPS (P = 0.07) and CA 242 (P = 0.08) tests showed marginally significant independent discriminating power, while the CEA test did not (P = 0.12). In order to sum up the contributions of different markers, a diagnostic score (DSI) was developed. The discrimination function was: DS1 = CA 50 x 1.75 + TPA x 0.62 + TPS x (-0.37) + CA 242 x (-1.21). The sensitivity of DS1 in detecting pancreatic cancer was 36% with a specificity of 90% and an efficiency of 82%. When the combination of CA 50 and TPA was used as a test, the discrimination function (DS2) was: DS2 = CA 50 x 0.69 + TPA x 0.67. The sensitivity of DS2 was 44% with a 88% specificity and an efficiency of 82%. According to this analysis, the further advantage gained by a computer-aided scoring system seems to be limited, since despite the considerably high specificity and efficiency its sensitivity remained low. In the present analysis the best combination in diagnosing pancreatic cancer was the combination of CA 50 and TPA.

Evaluation of a computer-based diagnostic score system in the diagnosis of jaundice and cholestasis

A prospective series of 220 patients with jaundice and/or cholestasis was analysed by means of discriminant analysis to evaluate the diagnostic value of various symptoms and signs and basic hepatopancreatobiliary laboratory tests in the differential diagnosis of these patients. In addition, a computer-based diagnostic score (DS) system was developed and compared with the diagnostic value of clinical evaluation (CE), ultrasound (US), computed tomography (CT), and endoscopic retrograde cholangiopancreatography (ERCP). A multivariate stepwise discriminant analysis showed five independent diagnostic factors in distinguishing extrahepatic and intrahepatic diseases: duration of jaundice (p = 0.002), serum protein concentrations (p = 0.002), Normotest (p = 0.04), fever during the past 3 months (p = 0.54), and age (p = 0.58). To sum up the contributions of independent factors, a DS was developed. The discrimination function was as follows: duration of jaundice x 0.97 + age x -0.40 + fever during the past 3 months x 0.33 + serum protein concentration x 0.35 + Normotest x -0.27. The diagnostic sensitivity of DS in the detection of extrahepatic disease was 96%, with a specificity of 80% and an efficiency of 93%. The sensitivities of the imaging methods (62-85%) were inferior to that of DS, whereas the specificities were better (94-98%). The sensitivity of CE was only slightly lower (86%) than that of DS, but the specificity was lowest (57%). In conclusion, relatively few (5 of 40) of the classical symptoms, signs, and biochemical tests proved to be independent diagnostic factors in distinguishing extrahepatic and intrahepatic diseases.(ABSTRACT TRUNCATED AT 250 WORDS)

Second evaluation of HEPAR, an expert system for the diagnosis of disorders of the liver and biliary tract

HEPAR is an expert system which can be used as a supportive tool in the diagnosis of disorders of the liver and biliary tract. When consulted for a particular patient, the system assesses the patient's disorder in two stages. In the first stage, data of medical history, physical examination and routine laboratory tests are used to determine whether the disorder is hepatocellular or biliary obstructive, and whether benign or malignant features are present. In the second stage, the system produces a differential diagnosis out of a set of 80 disease categories, using the conclusions of the first stage of the assessment and the results of a restricted number of supplementary investigations, i.e. serological tests and ultrasonography. The conclusions of the two stages are ordered by the amount of evidence computed by HEPAR. The system is not yet suitable for clinical use. The system has been evaluated using data of 181 patients selected from a population of 214 consecutively admitted patients with jaundice. The patients were classified by the system as having a hepatocellular or biliary obstructive, and a benign or malignant disorder in 96% and 100% of the cases, respectively. When comparing the conclusions with strongest evidence with the final clinical diagnoses, the patients were classified correctly in 86% and 83% of the classified cases, respectively. A differential diagnosis was produced in 87% of the patients. A correspondence between the diagnosis with strongest evidence and the final clinical diagnosis was found in 78% of the classified patients.

A performance evaluation of the expert system 'Jaundice' in comparison with that of three hepatologists

The diagnostic performance of an Expert System (Jaundice) designed to discriminate between different causes of jaundice was evaluated in a test sample of 200 consecutive in-patients with serum bilirubin greater than or equal to 51 mumol/l. The average probability assigned to true diagnosis, the non-error rate and the overall accuracy were, respectively, 55%, 77% and 70%. The Expert System's discriminatory ability in probabilistic prediction, assessed by a method based on continuous functions of the diagnostic probabilities (Brier score) was good. We also compared the ability of our Expert System to that of three experienced hepatologists, who were required to give a diagnosis in 20 cases following the same protocol used by computer (i.e., by asking only clinical and laboratory items). Both the hepatologists and Jaundice achieved a correct diagnosis in 70% of 20 cases, but the Expert System asked a significantly higher average number of questions during each consultation. Analysis of the reasoning pathway made by an external referee showed a high agreement between the diagnostic strategies of the Expert System and the physicians. We conclude that Jaundice can be a useful tool to support a physician with insufficient clinical experience in this field to generate correct diagnostic hypotheses.

Development and validation of HEPAR, an expert system for the diagnosis of disorders of the liver and biliary tract

HEPAR is an expert system in the field of hepatology which can be used as a supportive tool in the diagnosis of disorders of the liver and biliary tract. The representation language employed in HEPAR consists of production rules with object-attribute-value triples. In the system, medical diagnosis is modelled according to the strategy which is clinically used in this field. The patient's disorder is assessed in two stages. In the first stage, available data from medical interview, physical examination and simple laboratory tests are used to determine whether the disorder is hepatocellular or biliary obstructive in nature, and whether benign or malignant features are present. In the second stage the system produces a subset of possible diagnoses out of a set of more than 80 disease categories, using additional data from supplementary tests. The results of the first stage classification cause considerable pruning of the search space. In this paper the structure, development process and approach followed in the validation of the HEPAR system are described. The results of a recent performance validation study using data from 181 consecutive patient cases are discussed.

Expert systems and the pancreatic cancer problem: decision support in the pre-operative diagnosis

In this paper, after reviewing the main issue in artificial intelligence, decision support systems, medical decision-making, expert systems and some of their applications in medicine, we focus on the diagnostic aspect of pancreatic cancer. We briefly examine the most significant applications both from the oncological and from the diagnostic point of view. We discuss the medical problems mentioning incidence and mortality, aetiological factors and diagnosis, considering the roles of surgery and adjuvant therapies. Finally we justify the decision to develop an expert system in such a medical domain and discuss the SPES (Surgical Pancreatic Expert System) project, its parts dealing with the different medical phases of pancreatic cancer diagnosis and therapy: pre-operative, intra-operative and adjuvant therapies. In particular we discuss diagnostic aspects of pancreatic cancer disease, pointing out the aims of the project, methodologies, tools used and future developments.

Use of computers in diagnosis of jaundice

The development of computer-assisted diagnostic systems for the differential diagnosis of jaundice has been attempted in several studies during the last 25-30 years. All working systems have depended on numerical methods whereas expert systems have not yet become operational. The first step in the construction of a system is the collection of a data base from a series of jaundiced patients of clinical information (indicants) i.e. symptoms, signs, and the results from laboratory tests. The best discriminating indicants are selected and processed into a mathematical rule. The performance of this rule must be tested on an independent test sample of relevant patients. The performance may also be compared to that of clinicians. So far the computerized diagnoses have not been more accurate than those of clinicians. However, computer-assisted diagnostics may form an important first step in clinical decision making regarding the selection of a confirmatory diagnostic test (direct cholangiography, ultrasonography, liver biopsy, etc.) in the evaluation of the jaundiced patient.

Differential diagnosis of jaundice: applicability of the Copenhagen Pocket Chart proved in Stockholm patients

This paper shows that an algorithm for differential diagnosis of jaundice developed in Denmark has been successfully transferred for use in a Swedish hospital. The algorithm, which is based on data from nearly 1000 patients, utilises 21 items of information from the medical history, physical examination and blood chemistry. The algorithm recognises four diagnostic groups: benign obstructive jaundice, malignant obstructive jaundice, acute non-obstructive jaundice, and chronic non-obstructive jaundice. To each item of information, a score is attached reflecting its weight of evidence. Summing the scores for the symptoms and signs that are present leads to a probabilistic statement about the diagnosis. Because of missing data in the Swedish patient material, three of the items were excluded from the original algorithm. Corrections were made for differences in the distribution of diseases. In reclassification of 985 Danish patients the modified algorithm's "best bid", i.e. the diagnosis given the highest probability, was correct in 78% of cases. More important, 93% of the cases given a "confident" diagnosis (probability greater than 0.80) were correct. The corresponding figures when the algorithm was applied to Swedish patients were 76% and 93%, respectively. In both series the predicted probabilities were matched by a corresponding proportion of actual diagnostic hits. It is concluded that the algorithm leads to reliable estimates of diagnostic probabilities in jaundice and that the algorithm seems to work well in Sweden also.

Computer diagnosis in jaundice. Bayes' rule founded on 1002 consecutive cases

Extensive clinical and clinical chemical information was collected from 1002 consecutive jaundiced patients. Initial selection of variables based on Chi 2-tests or Mann-Whitney U-test allowed the removal of 64 of the 107 variables originally collected. A further selection of variables was carried out using a modified version of Bayes' rule thus reducing the number of variables from 43 to 22. Of the 982 patients with a final diagnosis 743 patients (76%) could be classified correctly into one of 13 diagnostic categories. The Bayes' rule was also applied to a test group of a further 110 jaundiced patients and found to perform equally well: of 108 patients with a final diagnosis 81 (75%) were correctly classified. A comparison between the clinician's diagnosis and the computer-aided diagnosis according to Bayes' rule demonstrated agreement with regard to one of the 13 diagnostic alternatives in 734 patients (75%), of whom 81 patients were wrongly diagnosed. In the test group agreement upon diagnosis was found in 80 patients (74%). By plausibly combining the computer-aided and the clinician's preliminary diagnoses, more correct classifications were obtained than with either method alone. Many diagnostic modalities such as ultrasound examination, CT-scan, and direct cholangiography are at hand today for the differential diagnosis of jaundice. Computer-aided diagnosis using Bayes' rule has proved a reliable tool for the clinician and can be used in the planning of a diagnostic strategy for the individual jaundiced patient.

Follow-up and prospective studies of the classification of liver disease

Two hundred patients with different liver diseases were observed during a period of 6-8 years. The diagnosis at the first hospitalization was based on morphological criteria (and, in some cases, additional clinical information). In 162 of the cases an initial 'specific' diagnosis could be made. By the time of the follow-up study the diagnosis was confirmed in 73% of them. In 22 of 38 patients who were initially unclassifiable, the diagnosis was made definite by the follow-up study. Eighty-five patients were hospitalized for re-examination 6-8 years after the initial study. Several of the liver diseases initially had quite typical patterns of clinical chemical data. Allocation by discriminant analysis was therefore in good agreement with the morphological classification. The follow-up study showed that several patients with initially atypical patterns of clinical chemical results had their diagnosis changed. In 35 patients with the final diagnosis of chronic active hepatitis (CAH) or primary biliary cirrhosis (PBC), laboratory data from the last hospitalization were used for discriminant analysis with teaching data from the initial study. Ninety-seven per cent were correctly allocated, and we conclude that these patients retain recognizable patterns of laboratory results for several years, even when given immunosuppressive treatment. The potential clinical usefulness of discriminant analysis of laboratory data for differential diagnosis was evaluated by a prospective study of 65 patients with the morphological diagnosis of CAH or PBC. Correspondence with the morphological classification system was found in almost 90% of the cases.

Applying descriptive discriminant analysis as a visual aid for physicians interpreting biochemical test results

Descriptive discriminant analysis displays for classes of common hepatic and biliary disorders and other mimicking conditions using 11 biochemical measurements, were demonstrated to physicians as an aid to interpretation. Displayed on a video, biochemical distinctions among disorders were made apparent to viewers. Physician users could easily see where their patient's results fell in relation to other results from patients with relevant diseases. Users had difficulty specifying which diseases they wanted included in displays. This technique would be useful for verifying experts' test result interpretations, when the differential diagnosis can be explicitly stated.

Differential diagnostic value in hepatobiliary disease of serum conjugated bile acid concentrations and some routine liver tests assessed by discriminant analysis

Serum concentrations of glycine and taurine conjugates of cholic, chenodeoxycholic, and deoxycholic acid were measured with a HPLC-enzymatic assay in 104 patients with hepatobiliary diseases. The capability of discriminating between four major diagnostic categories by the serum bile acid concentrations, alone and in conjunction with five commonly used biochemical liver tests, was evaluated by stepwise linear discriminant analysis. The serum bile acid pattern alone was inferior to the routine liver tests in separating the diagnostic groups. When the two sets of analytes were combined, the generalized group distance (Rao's V) was significantly increased, showing that the serum bile acid pattern contained discriminatory information in addition to the routine liver tests. The gain in correct reclassification of patients obtained by adding the serum bile acids, however, was only marginal.

High molecular weight alkaline phosphatase: a clinical study

High molecular weight alkaline phosphatase activities have been measured in the sera of 72 patients with a variety of forms of liver disease, 14 patients with bone disease and 8 healthy volunteers. These measurements have been compared with measurements of other indices of hepatic function in order to establish the place of this enzyme in the diagnosis of liver disease. High molecular weight alkaline phosphatase proved to be a sensitive and specific tests for detecting liver disease, particularly obstructive liver disease. It was better than all the other liver function tests in distinguishing liver metastases from other hepatobiliary diseases. It may therefore prove especially useful in the early detection of liver metastases.