Suppose one has a new diagnostic system (a computed tomography or ultrasound scanner, …), or a new diagnostic test for detecting a disease (diabetes, prostate cancer, …). Obviously we need to compare the performance of the new diagnostic system/test with the performance of the old one. How to proceed? It is customary to execute two series of “experiments” (for example 1000 mammography examinations for detecting breast cancer), one with the old method and one with the new one. To compare the quality of the two systems, we need the involvement of the so called “standard of reference” (SR); it is a sort of perfect test, that always gives the correct answer, but that cannot be used in daily practice since it is (for example) too invasive (a painful feeding tube), or destructive (a biopsy), or very expansive, or delayed in time (a follow-up mammogram obtained at last 10 months after). The outcomes of the two tests will be compared to the reports of the SR.

Fig. 1. The model of the “diagnostic channel” underlying informational analysis of a diagnostic test.

In the case of a dichotomous diagnostic test, we have two possible outcomes for it: “yes” (the disease is present,D=1), or “no” (the disease is not present,D=0). But, since the test can make mistakes, it can occur that the test says “yes” when the correct answer would be “no”, or the vice-versa. So, to evaluate a test, it is customary to calculate four numbers, respectively the (percentage of) true positives (orsensitivitySE),假阳性(FP比率),假negatives (FN ratio), and true negatives (orspecificitySP). A test is good when it has high percentage of TPandTN. The SR has 100% for both TP and TN. But how to compare two diagnostic tests, with one having e.g. SE=80% and SP=60%, and the other SE=60% and SP=80%? Unfortunately, up to now, nobody was able to propose a convincing global parameter derived from the above mentioned percentages. Now our innovation.

Fig. 2. GIR is the global information ratio, an index calculated by comparing the behavior of the Information Ratio Curve of the test with the Limit Information Curve, that is the best possible diagnostic performance.

A diagnostic test is conceived to gaininformationon the disease of the patient, that is ahiddenobjective status which can be present (D=1) or absent (D=0). The physician makes assumptions on the disease by interpreting the result of the diagnostic test;R=1 means that (it is diagnosed) the disease is present,R=0 means the disease is absent. All this process (e.g., a mammography examination interpreted by a radiologist) can be thought of as the outcome of thediagnostic channelof Fig. 1. So the accurate diagnostic test (or the accurate reader) will be the one able to extract as much information as possible from the diagnostic channel. We know that a perfect method to measure information already exists; it is theMutual Information(MI), which is a mathematical function developed in the framework ofInformation Theory; note that all modern digital communication systems that interact over a network are based (also) on this theory. So we have used MI to compare diagnostic tests, being able to determine the clinical conditions that maximize the flux of information (e.g. with respect to theprevalenceof the disease). We have also introduced an index for the diagnostic test, which cumulates the information among all possibleprevalence scenarios; if we compare it with the same index obtained by the SR, we have the so calledInformation Ratio(IR). This analysis can be easily extended also to tests yielding continuous values (e.g., PSA level) or ordered categories (e.g., 7-point scale in breast imaging), corresponding to multiple cutoffs of specificity. In this case we introduce a curve that illustrates the behavior of IR versus 1-SP (see Fig. 2.) and that is alternative to classical ROC analysis.

Rossano Girometti¹, Francesco Fabris^2
1Dipartimento di Scienze Mediche e Biologiche, Istituto di Radiologia Diagnostica,
Università degli Studi di Udine, Udine, Italy
²Dipartimento di Matematica e Geoscienze, Università degli Studi di Trieste, Trieste, Italy

Publication

Informational analysis: a Shannon theoretic approach to measure the performance of a diagnostic test.
Girometti R, Fabris F.
Med Biol Eng Comput. 2015 Sep

Read offline:

Related Articles:

	Turning on neuronal gene programs in prostate cancer cellsCancer of the prostate gland is a common malignancy afflicting males worldwide. This cancer is the second deadliest amongst male in United States, with most of the mortality resulting from…
	Prostate volume estimation: is there need for a change in…As men age, prostate enlargement often leads to complications such as obstruction of the bladder neck and urinary retention with potential consequences on the kidney. Therefore, knowledge of prostate volume…
	Does tangential radiation for breast cancer cover internal…乳腺癌是最常见的癌症之一women in the United States. Radiation is a very commonly used treatment modality for breast cancer: it is offered to…
	Lung ultrasound. A field for misconceptions... and…Born from the wreckage of the Titanic, used in the marine then industry, ultrasound impacted medicine in the 50s. However, the lung has always been considered as not accessible to…
	Ultrasound generate electricity inside the bodyImplantable medical devices (IMDs) are highly beneficial to patient health. Concerning rapidly evolving technologies for IMDs, sustainable and reliable powering methods for IMDs is truly essential. They are generally relying…
	Insight into the needs of thyroid cancer patients before…The thyroid is a butterfly-shaped gland in the neck below the Adam’s apple. It produces hormones that help influence our metabolism and normal development. Over the last 30 years, the…