Prediction of Individual Patient Prognosis

Abstract

Physicians take both diagnosis and prognosis into account when allocating treatment. However, by "prognosis" physicians usually imply a somewhat vague impression concerning large groups of patients. One possible task for decision support studies is to design and construct systems that accurately predict individual patient prognoses. The authors constructed and tested such systems in three areas of medicine (inflammatory bowel disease, upper gastrointestinal tract hemorrhage, and acute chest pain). In each area, the individual patient's symptoms were compared with a computer-held database of information via a Bayesian analysis, prior and conditional probabilities being derived from large-scale real-life surveys. Prospective trials designed to test these predictive systems by reference to test series comprising over 4,000 patients indicate that a firm prognostic prediction can generally be made; where made, the accuracy of prediction is over 90%. Ways in which this type of prediction may be of clinical value are discussed.

How do experts read family genograms?

“…For example, predicting illness within the next 3 months is surely not a typical clinical exercise for family therapists. Family physicians, however, are very much concerned with patient prognosis (3) and, in that sense, predicting future health risk should not be a foreign task. In any case, the generalizability of the results is limited to the extent that an expert’s reading of a genogram depends on the type of decision or problem being considered.…”

“…Table 4 summarizes the reliability coefficients, showing both the range of correlation coefficients obtained for different judge pairs and the median (typical) correlation for each category of information. The number of judge / 85 .92 (1) .84 (3) .87 (2) .59 (5) .20 (21) .68 (4) .41 (11) .48 (7) .38 (12) . 18(22) .25 (18) .47 (8) .…”

Rapid Cardiovascular Diagnostics

“…However, 2-7% of patients with acute myocardial infarction (AMI) are inappropriately discharged from the ED [16,17]. Improvements to diagnosis have been made utilising risk scoring systems [18], computerised decision support [19,20] and automated ECG interpretation [21]. Although clinical assessment is paramount in the assessment of chest pain, cardiac biomarker measurements are now routinely used to aid diagnosis.…”

Biomarkers of Cardiac Ischemia

“…Conversely, it has been estimated that between 2 and 7% of patients with AMI are inappropriately discharged from the ED [3,4] and suffer disproportionate morbidity and mortality. Attempts to improve diagnosis have included risk scoring systems [5], computerised decision support [6,7] and automated ECG interpretation [8]. Although clinical assessment remains integral to the assessment of patients with chest pain, cardiac biomarker measurement has become an essential component in the diagnostic armamentarium.…”