Fundamentals of clinical methodology: 2. Etiology

Modeling Uncertainty in Clinical Diagnosis Using Fuzzy Logic

This paper describes a fuzzy approach to computer-aided medical diagnosis in a clinical context. It introduces a formal view of diagnosis in clinical settings and shows the relevance and possible uses of fuzzy cognitive maps. A constraint satisfaction method is introduced that uses the temporal uncertainty in symptom durations that may occur with particular diseases. The method results in an estimate of the stage of the disease if the temporal constraints of the disease in relation to the occurrence of the symptoms are satisfied. A lightweight fuzzy process is described and evaluated in the context of diagnosis of two confusable diseases. The process is based on the idea of an incremental simple additive model for fuzzy sets supporting and negating particular diseases. These are combined to produce an index of support for a particular disease. The process is developed to allow fuzzy symptom information on the intensity and duration of symptoms. Results are presented showing the effectiveness of the method for supporting differential diagnosis.

Fuzzy linguistic model for evaluating the risk of neonatal death

OBJECTIVE

To introduce a fuzzy linguistic model for evaluating the risk of neonatal death.

METHODS

The study is based on the fuzziness of the variables newborn birth weight and gestational age at delivery. The inference used was Mamdani's method. Neonatologists were interviewed to estimate the risk of neonatal death under certain conditions and to allow comparing their opinions and the model values.

RESULTS

The results were compared with experts' opinions and the Fuzzy model was able to capture the expert knowledge with a strong correlation (r=0.96).

CONCLUSIONS

The linguistic model was able to estimate the risk of neonatal death when compared to experts' performance.

Fundamentals of clinical methodology. 4. Diagnosis

The concept of medical diagnosis is reconstructed and its syntax, semantics, and pragmatics are analyzed. It is shown that medical diagnosis is relative to a complex diagnostic structure part of which are the method of diagnostic reasoning and the knowledge base used. Clinical knowledge-based systems research is interpreted as the advent of an engineering science of clinical practice.

Predictions of coronary artery stenosis by artificial neural network

Data from angiography patient records comprised 14 input variables of a neural network. Outcomes (coronary artery stenosis or none) formed both supervisory and output variables. The network was trained by backpropagation on 332 records, optimized on 331 subsequent records, and tested on final 100 records. If 0.40 was chosen as the output distinguishing stenosis from no stenosis, 81 patients who had stenosis would have been identified, while 9 of 19 patients who did not have stenosis might have been spared angiography. The results demonstrated that artificial neural networks could identify some patients who do not need coronary angiography.

Fundamentals of clinical methodology: 3. Nosology

Intelligent clinical judgement is one of the main goals of medical artificial intelligence. To achieve that goal requires a reliable nosological language. Such a language is not yet available, however. In this paper the notions of health, disease, and nosology are analyzed. It is shown that health and disease as generic concepts, and also individual disease entities are best understood as fuzzy sets. Clinical language and linguistics, nosology and diagnosis may thus become directly amenable to fuzzy theory.

Fundamentals of clinical methodology: 2. Etiology

The concept of etiology is analyzed and the possibilities and limitations of deterministic, probabilistic, and fuzzy etiology are explored. Different kinds of formal structures for the relation of causation are introduced which enable us to explicate the notion of cause on qualitative, comparative, and quantitative levels. The conceptual framework developed is an approach to a theory of causality that may be useful in etiologic research, in building nosological systems, and in differential diagnosis, therapeutic decision-making, and controlled clinical trials. The bearings of the theory are exemplified by examining the current Chlamydia pneumoniae hypothesis on the incidence of myocardial infarction.