1214 Clinical Chemistry 42:8 1214-1222 (1996) Development and evaluation of a urine protein expert system MIRosiv IVANDIC,* WALTER HOFMANN, and WALTER G. GUDER Based on the quantitative determination of creatmine, total protein, albumin, a1-microglobulin, IgG, a2-macroglobu- liii, and N-acetyl-I3,n-glucosaininidase in urine in combina- tion with a test strip screening, the findings of hematuria, leukocyturia, and proteinuria can be assigned to prerenal, renal, or postrenal causes. Using this graded diagnostic strategy as a knowledge base, we developed a computer- based expert system for urine protein differentiation (“UPES”) as a decision-supporting tool. The knowledge base was implemented as a combination of “Wthen” rules and two-step bivariate distance classffication of marker proteins. The knowledge for this form of pattern recogni- tion was derived from the results for a set of 267 patients with clinically and histologically documented nephropa- thies. To determine the diagnostic value of UPES, we tested another set of data: results for 129 urine analyses from 94 patients. Using these data, the system reached 98% concordance with the clinical diagnoses for the patients and was superior to the diagnostic interpretations of four hu- man experts. UPES has been successfully integrated into the laboratory routine process, including automated data import. INDEXING TERMS: knowledge-based system . decision-support- ing system #{149} albumin . a,-microglobulin #{149} a2-macroglobulin proteinuria #{149} kidney diseases #{149} hematuria #{149} leukocyturia nephropathy Continuously changing medical knowledge has resulted in in- creasing specialization in medicine. Providing optimal medical care requires experts who can keep up with the enormous information flow; however, such experts are not always available. To conserve the knowledge of a specialist and to widely distribute this knowledge, software tools called expert systems Institut f#{252}r Klinische Chemie, St#{228}dt. Krankenhaus Munchen-Bogenhausen, Englschalkinger Str. 77, D-81925 Munchen, Germany. Author for correspondence. Fax +49 89 9270 2113; e-mail wguho@pc- labor.uni-bremen.de. Dedicated to H. Keller of ZUrich (Switzerland), on the occasion of his 70th birthday. This paper contains part of the results of the doctoral thesis of MI. Received November 7, 1995; accepted April I, 1996. or, better, knowledge-based systems have been developed and are being used with increasing frequency. Laboratory medicine, given its high degree of specialization and its use of objective quantitative findings, seems especially suited to benefit from these computer programs [1, 2]. Here we describe such a decision-supporting system, the Urine Protein Expert System (UPES), developed for the inter- pretation of urine protein differentiation.’ As with electro- phoretic techniques [3-5], quantitative analysis of urine marker proteins has been successfully applied to detect and differentiate nephropathies [5-7]. The multivariate evaluation of the excre- tion pattern allows differentiation of prerenal from glomerular, tubular, and postrenal causes of proteinuria and hematuria [8-11]. Knowledge for describing and interpreting complex urine protein patterns has accumulated in recent years, a result of collaboration between nephrologists and clinical chemists. We have tried to implement this knowledge in the form of “if/then” rules in the knowledge base of UPES, a knowledge base that contains facts and strategies drawn from literature as well as from heuristics and empirical guidelines. The rules have been worked out in close collaboration with specialists in the field of urine protein differentiation. Because various nephropathies could not be sufficiently identified by interpretation of excretion patterns when based on rules alone, we have used another method of knowledge repre- sentation, geometric distance classification, to extract and apply the knowledge of this multivariate pattern recognition. Using this hybrid model of a knowledge base, UPES is able to process the laboratory results provided and to propose a medical report generated from 36 text elements. Twenty-four of those elements (all the ones used in this paper) are listed in the Appendix. Matenais and Methods Analytical procedures. Test strip screening was performed with test strips from Behring (Marburg, Germany). Quantitative determinations of total protein, albumin, ce,-microglobulmn, IgG, a2-macroglobulmn (turbidimetrically), N-acetyi-/3,n-glu- Nonstandard abbreviations: UPES, Urine Protein Expert System; /3-NAG, N-acervl-(3,o-glucosaminidase; and GFR, glomerular filtration rate. Downloaded from https://academic.oup.com/clinchem/article/42/8/1214/5646316 by guest on 07 January 2022
9
Embed
Development and evaluation of a urine protein - Clinical Chemistry
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
1214
Clinical Chemistry 42:8
1214-1222 (1996)
Development and evaluation of a urine proteinexpert system
MIRosiv IVANDIC,* WALTER HOFMANN, and WALTER G. GUDER
Based on the quantitative determination of creatmine, totalprotein, albumin, a1-microglobulin, IgG, a2-macroglobu-
liii, and N-acetyl-I3,n-glucosaininidase in urine in combina-tion with a test strip screening, the findings of hematuria,leukocyturia, and proteinuria can be assigned to prerenal,
renal, or postrenal causes. Using this graded diagnostic
strategy as a knowledge base, we developed a computer-based expert system for urine protein differentiation(“UPES”) as a decision-supporting tool. The knowledge
base was implemented as a combination of “Wthen” rulesand two-step bivariate distance classffication of marker
proteins. The knowledge for this form of pattern recogni-tion was derived from the results for a set of 267 patientswith clinically and histologically documented nephropa-thies. To determine the diagnostic value of UPES, we
tested another set of data: results for 129 urine analyses
from 94 patients. Using these data, the system reached 98%
concordance with the clinical diagnoses for the patients andwas superior to the diagnostic interpretations of four hu-
man experts. UPES has been successfully integrated into
the laboratory routine process, including automated data
import.
INDEXING TERMS: knowledge-based system . decision-support-
ing system #{149}albumin . a,-microglobulin #{149}a2-macroglobulin
renal dysfunction-protein excretion patterns ranging from
normal values to as much as twice the upper reference limit from
patients from any of these three diagnostic groups
Diagnoses that were not histologically documented were
based on clinical criteria (e.g., anamnesis, clinical examination,
laboratory results,medical imaging, clinicalcourse) and made by
the physician treating the patient. Table 1 summarizes the
composition of the training set.
Validationset.To evaluate the diagnostic interpretation of urine
protein patterns, we used data from 129 urine analyses. These
test data were collected from 94 patients of the II. Medical
Department of the Hospital Munchen-Harlaching and the III.
Medical Department of the Hospital Munchen-Bogenhausen.
As in the training set, the urines were assigned to the diagnostic
groups primary glomerulopathy, secondary glomerulopathy,
and interstitial nephropathy, according to their diagnoses (Table
1).
Discriminant analysis. To compare the diagnostic performance of
the distance classifier with the performance of a statistical
method, we performed classificatory linear and quadratic dis-
criminant analysis. We used the training set to compute the
parameters (coefficients and constants) of the linear and qua-
dratic functions. Equal prior probabilities were assumed for all
four diagnostic groups. The same validation data were used to
evaluate the results of discriminant analysis as were used with
geometric distance classification (Table 1).
#{149}#{149}#{149}S
#{149}a. #{149}#{149}#{149}#{149}.#{149} a
#{149}%#{149}#{149}.#{149}a. #{149}S . #{149}
#{149}SS U at#{149} U #{149} #{149}
#{149}I. .R#{149}1
U... #{149}aU #{149}#{149}#{149}#{149}
Fig. 1. Use of circles to describe clusters of twodifferent classes: (A) individual examples of two dif-ferent classes forming two distinct clusters; (B) anoptimal characterization of the clusters by using sixcircles (GEODICLA; see text); (C) the resulting sixrepresentatives of the two classes.
Dow
nloaded from https://academ
ic.oup.com/clinchem
/article/42/8/1214/5646316 by guest on 07 January 2022
1216 Ivandi#{233}et al.: Urine protein expert system (UPES)
Table 1. Compos ition of the trainTraining collective
ing and the valid ation collective.Validation collective
Urine samples Patients Urine sampies Patients
Diagnostic groups
Primary glomerulopathy
Secondary glomerulopathy
Interstitial nephropathy
Renal dysfunctionTotal
n
285
123
66
29503
n
57 117
24 97
13 33
6 20267
%
44
36
12
7
n
46
76
7
-
129
%
36
59
5
-
n
27
62
5
-
94
%
29
66
5
-
ResultsINPUT DATA
For interpretation of a urine protein pattern, UPES requires at
least the data for urine creatinine, total protein, albumin, and
a,-microglobulin. For differential diagnosis during the decision
process, the system asks for data on IgG, a2-macroglobulin, and
p-NAG if necessary. The program refers all quantitative mea-
surements to the urine creatinine content to take into account
the concentration of the urine sample [7]. These quantitative
data are processed together with the results of the urine teststrips for assessing leukocytes (granulocyte esterase), hemoglo-
bin (pseudoperoxidase), protein, and glucose. As an option, the
glomerular filtrationrate (GFR) can be considered by providing
the data for serum creatinine and serum a,-microglobulin.
Apart from the results of the serum and urine analysis,
additional data concerning the patient and the request of the
urine protein differentiation data can be entered into UPES by
using an input screen or can be imported automatically by
retrieving a file.
KNOWLEDGE EASE
The knowledge base of UPES is divided into five modules-
Plausibility and consistency check, Hematuria, Leukocyturia,
Proteinuria, and GFR-which are considered if necessary. Theimplemented strategy is represented as if/then rules. The geo-
metric distance classification is used only in the Proteinuria
module to interpret the marker protein patterns.
Plausibility and consistemy check. All data are checked for plausi-
bility during the input or import process; formats and thresholds
are used to exclude values that exceed medical and analytical
ranges. For analytical validation, this module considers thevalues for total protein, albumin, test strip protein, and the two
serum measurements (creatinine and a,-microglobulin). A
warning appears on the screen (“Discrepancy between test strip,
albumin, and total protein!”) if the comparison of the test strip
result and the quantitative measurements fulfills one of the
following conditions:protein test strip positive and total protein �200 mg/L
protein test strip negative and albumin >300 mg/L
albumin > total protein and albumin >50 mg/L
These rules take into account that the detection limit of the test
strip is -300 mg/L albumin and thus detect false-positive and
false-negative test strip results.If the value for urine protein excretion is normal and one of
the serum values indicates a decreased GFR (see next section),
the user is asked to check the input data.
MedicalassessmentofGFR. The GFR module isconsidered only
if the concentrations of the optional serum analytes creatinine
and a,-microglobulin are provided. a,-Microglobulin partially
fills the diagnostic gap associated with creatinine, by sometimes
detecting a decrease of GFR earlier than creatinine does [15-
17].A major restriction of the GFR is unlikely if both serum
analytes are within their reference ranges (text element I; see
Appendix).The GFR is assumed to be decreased if concentra-
tions of both analytes are increased (text element 2). In combi-
nation with a normal urine excretion pattern, this is interpreted
as a lossof functioning nephrons that iscompletely compensated
by the remaining nephrons (text element 3).
An increase of only a,-microglobulin in serum indicates a
possible restriction in glomerular clearance (diagnostic gap ofcreatinine). In this case, determination of creatinine clearance is
recommended to confirm or to exclude this suspicion (text
element 4). If only creatinine is increased, this more likely
indicates the presence of pseudocreatinines or increased muscle
mass (text element 5), given the greater diagnostic sensitivity of
a, -microglobulin.
Medical assessment of hematuria. Whenever the test strip result for
blood is positive, the Hematuria module is considered, to
distinguish prerenal from glomerular, tubular, and postrenal
causes.Prerenal causes of the test strip result are assumed if the
criteria for prerenal proteinuria are met (i.e., a “protein gap”; see
text element 6) [18]. If albumin excretion is <100 mg/L,
differentiationof renal and postrenal hematuria by urine protein
analysis is not possible [9]. In such cases, UPES suggests using
phase-contrast microscopy to look for dysmorphic ervthrocytes
[19, 20] (text element 7).
At higher albumin concentrations,the system considersthe
ratios of albumin with a2-macroglobulin, IgG, and a,-micro-globulin to assign the hematuria to a renal (glomerular or
tubulo-interstitial)or postrenal bleeding [9, 10]. If a2-macro-globulin and lgG results have not yet been provided, UPES asks
fortheirmanual input.
Because of their molecular size, only small amounts of
a,-macroglobulin(250 kDa) and IgG (125 kDa) usually pass theglomerular filter,and those are reabsorbed in the tubule. When
Dow
nloaded from https://academ
ic.oup.com/clinchem
/article/42/8/1214/5646316 by guest on 07 January 2022
mg/g creatinine
14-20
20-50
50-100>100
20-3030-100
100-10001000-3000
>3000
ClinicalCbemisy 42, No. 8, 1996 1217
albumin ratios with these proteins in urine are similar to those
in plasma, therefore, a postrenal lesion is indicated (a2-macro-
globulinlalbumin >0.02 and IgG/albumin >0.2). In this case,
the system proposes that the clinicianrepeat the urine protein
differentiation to exclude additional renal hematuria after
postrenal hematuria has ceased (text element 8).
In renalhematuria (a2-macroglobulinlalbumin<0.02), gb-
merular and tubulo-interstitial causes can be distinguished by
the concentrations of IgG: In tubular hematuria, even small
amounts of filtered IgG cannot be reabsorbed (IgG/albumin
>0.2). Increased excretion of the tubular marker a,-micro-
globulin is taken as additional confirmation of the tubulo-
interstitial lesion (text element 9).
Medical assessment of leukoyturia. The Leukocyturia module is
considered whenever the leukocyte esteraseteststripshows a
positive result. An isolated leukocyturia in combination with a
normal urineproteinpatternindicateseithera contamination of
the urine sample or an inflammation of the lower urinarytract
(textelement 10).Leukocyturia with a slightglomerular pro-
>40 mg/g creatinine (text element 24) [12]. Chronic tububo-
interstitial diseases are described by increased a,-microgbobulin
excretion without a major increase of p-NAG.
OUTPUT (FINAL REPORT)
UPES composes the finalreport from the selectedtextitems
afterthe urineand serum proteinfindingshave been medically
assessed.
Dow
nloaded from https://academ
ic.oup.com/clinchem
/article/42/8/1214/5646316 by guest on 07 January 2022
PrimaryGP Secondary GP TP
Table 3. Diagnostic interpretation of urine protein differentiatIons of 46 prImary glomerulopathles, 76 secondaryglomerulopathies, and 7 interstitIal nephropathies by UPES, linear and quadratic discrimlnant functions, and four experts.
Clinical diagnosis
Expertise Pulm.GP GP GP/TP Dys Others Sec.GP GP GP/TP Dys Others TP GP/TP Dys Others
patterns interpreted as implausible constellations and urines not classified or misclassified are summarizedas Others.b 2 patterns not classified by UPES.
“2 patterns classified by UPES as a primary glomerulopathy.
LDF, linear discriminated function; QDF, quadratic discriminant function.
ClinicalChemistry42, No. 8, 1996 1219
EVALUATING THE KNOWLEDGE BASE WITH THE
VALIDATION SET
To compare the medical interpretation of proteinuria by UPES,
statistical methods and human expertise, we assessed the results
of urine proteindifferentiationof the validationset(129 urines
from 94 patients)as classifiedby IJPES, linear and quadratic
discrimination fimctions, and four experts in our laboratory who
were familiarwith thismethod of urine analysis.The resultsof
these evaluationsare given in Table 3; misclassifIcationsare
summarized as “others.”
Because there are no gold standards for evaluating urinary
protein patterns,it was difficult to define correct and false
interpretations. Patients with a documented diabeticnephropa-
thy, for example, showed many different patterns of protein
excretion. The patterns were describedby human experts and by
the system asreflectinggbomerularand (or)tubulardysfunction,
secondary gbomerulopathy, primary or secondary gbomerubopa-thy, or mixed (gbomerubar and tubular) nephropathy, and allof
these diagnostic groups were assumed to be a correct interpre-
tation. Only the description “primary gbomerubopathy” would
be judged a clearmisclassificationof these patients.
UPES. Of 46 urines from patients with gbomerubonephritis,
UPES identified 9 primary gbomerubopathies (20%) by first-step
classification. The correct but more global diagnosis “primary
or secondary glomerulopathy” was chosen in the majorityof
cases(31 of46 urines,67%) because of theoverlappingzones of
the albuminla,-microgbobulin patterns. Using the IgG excre-
tion in a second-stage pattern classification correctly assigned 6
of these 31 ambiguous cases to the primary gbomerulopathygroup. Two patientswith gbomerubonephritisand albuminuria
>10 g/g creatininecould not be interpretedby UPES.
Only 2 of 76 urines(3%) with secondary glomerulopathies
were misclassified as primary glomerulopathies by UPES. Both
of these urines showed substantial albuminuria (844 and 552
mg/g creatinine) and IgG excretion (63 and 59 mg/g creatinine)
but no significanttubularproteinuria. Again, UPES assigned
most (46, or 61%) of the 76 urines to the diagnosticgroup
“primary or secondary glomerulopathy.” The excretion ratio for
IgG/albumin misled the system in 3 of these 46 decisions to
favor the primary type of glomerulopathy.The remaining 27urines (36%) were classified as “renal dysfunction” because of
the low quantitiesof marker proteinsexcreted.
Finally, UPES interpreted the urine patterns of all 7 inter-
stitial nephropathies correctly.
Discriminant functions. As an alternative classification method, weused the discriminantfunctionsestimated from the albumin,
a,-microglobulin, and IgG patternsof the trainingset (no
implausible constellations were included). Each protein pattern
was classified to the diagnostic group having the highest group
probability, as computed with linear and quadratic discriminant
functions. Resubstitution of the trainingsetresultedina reclas-
sificationrateof 75% by lineardiscriminantfunctionsand 79%
by quadratic discriminant functions.
To allow consideration of an ambiguous classification, as in
UPES, we took into account the differencebetween the two
highest group probabilities.If this differencewas <0.3, the
pattern was assigned to both classes(ambiguous classification).
Linear discriminant functions described 38 samples (29%) ofthe validationsetas caused by “renaldysfunction”;68 patterns
(53%) were interpretedcorrectlyasbelonging toother diagnos-
tic groups matching the known diagnosis. By quadratic discrimi-nant functions,37 cases(29%) were classifiedas“renaldysfunc-
tion,” whereas other, correct diagnostic classes were chosen for
65 samples (50%). In total,there were 23(18%) vs 27 (21%)
misclassifications by linear and quadratic discriminant functions,respectively (Table 3).
Human experts. The qualityof the human expertisevaried
greatly, depending on the experience of each expert with urine
protein differentiation. Generally, the humans interpreted moreproteinuriasas being “renaldysfunction”than did UPES. Two
experts more oftendecidedon an unambiguous diagnosis,atthe
Dow
nloaded from https://academ
ic.oup.com/clinchem
/article/42/8/1214/5646316 by guest on 07 January 2022
1220 Ivandi#{233}et al.: Urine protein expert system (UPES)
risk of increasing their misclassifications; the other two experts
preferred the more general diagnosis “primary or secondary
glomerulopathy,” to be on the safe side. Notably, one expert
reliedon a positiveglucoseteststripresultto classify a glomeru-
bopathy as the secondary type. In contrast to UPES, he and two
other expertsfailedto identifythe primary gbomerubopathy in a
32-year-old woman with IgA nephropathy and familial glucos-
uria.
DiscussionEvaluation with the validation data set showed that noninvasive
urineproteindifferentiationmay be a usefuldiagnosticstrategy
in nephrology. The knowledge-based system UPES performed
well in diagnostic interpretation of urine protein patterns,
correctly distinguishing all interstitial nephropathies from gb-merulopathies. It misclassified only 2 of 129 urines (2%),
incorrectlyconcluding that patternsof significantglomerular
proteinuria had instead indicated a primary gbomerubopathy.
Discriminantfunctionswere not able to deal properlywith
the overlapping zones of allclinicalclasses.The four human
experts also had problems correctly classifying primary and
secondary gbomerulopathies-which are difficult to distinguish
by clinicalchemistrymeans.
After the evaluation,we adjusted the knowledge base of
UPES to improve the medical assessment. We added one circle
to the secondary glomerulopathy class so that this diagnostic
group would be considered in cases of significant glomerular
proteinuria.Another circlewas also added to the primary
gbomerubopathy class to ascertain the identification of cases ofexcessive proteinuria. The addition of these two circles will help
prevent misclassificationin similarcases.
Knowledge-based systems, as means of rationalization, accel-
erate the time-consuming process of medical assessment and
increase the economic efficiency of a clinical laboratory. Such
programs make possible consistent and standardized medical
assessmentof constantand high quality,especiallywhen dealing
with the highly complex data produced in increasingly special-
ized areas [22-24]. Apart from learning effects, transparent data
interpretation rather than simple “data intoxication” [25] may
provide clinical physicians with useful additional information
[26].
The knowledge-based system we designed provides for the
first time a concise decision-supporting system to exclude and
differentiate proteinuria, hematuria, and leukocyturia. Working
with the complex excretion pattern of different marker proteins,
UPES can distinguish prerenal, glomerular, tubulo-interstitial,
and postrenal causes of pathological urine findings. By using two
and difficult task sufficiently solved by UPES. Moreover, the
evaluation results provided evidence that even experts can learn
from a continually growing knowledge base of an expert system.
Given that gold standards have yet to be defined for many of the
observed protein patterns (e.g., “dysfunction”), future prospec-
tive studies may help improve the predictive qualities of the
system. Consideration of additional clinical information, imple-
mentation of other urine results (e.g., microscopy), and exten-
sion to previous urine protein patternsare currentlyunder
development.
We conclude that urine protein differentiationin itspresent
form issuperior to traditional urine analysis as a mirror of renal
function [32] and isa valuableadditionto the morphological
information provided by histopathobogy and medical imaging.
Use of the decision-supportingsystem UPES for medical as-
sessment of urine proteindifferentiationprovidesa standardof
high and constant quality. A graduated and transparent decision
process is implemented in a hybrid knowledge base that uses
both production rules and geometric distance classification as
complementary methods of knowledge representation.In the
hands of a responsible physician, UPES can be a useful tool for
increasing the efficiencyand qualityof a laboratory.
References1. Spackman KA,Conrrelly OP. Knowledge-based systems in labora-
tory medicine and pathology. Arch Pathol Lab Med 1987;111:116-9.
2. Winkel P. The application of expert systems in the clinical labora-tory. din Chem 1989:35:1595-600.
3. PesceAi, Boreisha I, Pollak VE. Rapid differentiation of glomerularand tubular proteinuria by sodium dodecyl sulfate polyacrylamidegel electrophoresis. Clin Chim Acta 1972;40:27-34.
4. Boesken WH, Kopf K, Schollmeyer P. Differentiation of proteinuriadiseases by diskelectrophoretic molecular weight analysis ofurinary proteins. Clin Nephrol 1973:1:311-6.
5. Petersen A, Evrin PE, Berggard I. Differentiation of glomerular,tubular and normal proteinuria: determinations of urinary excretionof $32-microglobulin, albumin and total protein. J Clin Invest1969;48:1189-98.
6. Cameron JS,BlandfordG.The simple assessment ofselectivity in
high proteinuria. Lancet 1966;i:242.7. Hofmann W, Guder WG. A diagnostic programme for quantitative
analysis of proteinuria. J CIin Chem Clin Biochem 1989:27:589-600.
8. Hofmann W, Rossm#{252}llerB, Guder WG, Edel HH. A new strategy forcharacterizing proteinuria and haematuria from a single pattern ofdefinedproteinsin urine. EurJClinChem ClinBiochem 1992:30:707-12.
9. Hofmann W, Schmidt 0, Guder WG, Edel H. Differentiation ofhematuria by quantitative determination of urinary marker pro-teins. Kim Wochenschr 1991;69:68-75.
10.Guder WG, Hofmann W. Differentiation of proteinuria and haema-tuna by single protein analysis in urine. Clirr Biochem 1993:26:277-82.
11. Hofmann W, Sedlmeir-Hofmanrr C, lvandi M, Schmidt 0, GuderWG, Edel H. Assessment of urinary.protein patterns on the basis
of clinically characterized patients. Typical examples with reports.Lab Med 1993;17:502-12.
12. Schmidt 0, Hofmann W, Guder WG. Adaptation of the diagnosticstrategy of urine protein differentiation to the Hitachi 911 ana-lyzer. Lab Med 1995:19:153-61.
13. lvandi#{227}M. Entwicklung und Evaluierung eines wissensbasierten
Befundungssystems zur Urineiwei8differenzierung [Dissertationl.M#{252}nchen:Ludwig-Maximilians-Universitat, 1995.
14. Barschdorff D, Bothe A. Signal classification using a new self-organising and fast converging neural network. Noise Vibration1991;9:11-9.
15. Itoh Y, Enomoto H, Takagi K, Kawai T. Clinical usefulness ofserum a1-microglobulin as a sensitive indicator for renal insuffi-ciency. Nephron 1983;33:69-70.
17. Jung M, Jung K. Low-molecular-mass proteins in serum as mark-ers of glomerular filtration rate: cystatin C, a1-microglobulin and
p2mrogloi Lab Med 1994;18:461-5.18. Boege F,KoehlerB, LiebermannF.Identificationand quantifica-
tion of Bence-Jones proteinuria by automated nephelometricscreening. J dIm Chem Clin Biochem 1990;28:37-42.
19. Birch OF, Fairley KF. Haematuria: glomerular or nonglomerular?1979;ii:845-6.
20. K#{227}hlerH, Wandel E, BrunckB. Acarrthocyturia-acharacteristicmarker for glomerular bleeding. Kidney Int 1991;40:115-20.
21. Hofmann W. A mathematical equation to discriminate overloadproteinuria from tubulo-interstitial involvement in glomerular dis-eases. Clin Nephrol 1995;44:28-31.
22. Keller H,TrendelenburgC,eds.Clinicalbiochemistrydata presen-tation and interpretation. Berlin: de Gruyter, 1989.
Dow
nloaded from https://academ
ic.oup.com/clinchem
/article/42/8/1214/5646316 by guest on 07 January 2022
23. Bepperling C, Hehrmann R, Haas H, Hotz G, Olbricht T, Schmidt R,et al. A knowledge-based system for the interpretationofthyroidhormone measurements: evaluation and optimisation of thesystem Pro.M.D.-SD in five clinical laboratories. Lab Med 1994;18:564-71.
24.TrendelenburgC, PohI B. Pro.M.D. expert system and itsapplica-tion in laboratory medicine.Ann Biol Clin 1993:51:226-7.
25. O’Moore RR.Decision-supporting based on laboratory data. Meth-ods Inform Med 1988;27:187-90.
26. WmnkelP. Interpreting the results is the expertise of the laboratory.Clin Chim Acta 1994;224:S9-S51.
27. SolbergHE. Discriminantanalysis.CritRev dIm Lab Scm1978;9:209-42.
29. Furlong JW, Dupuy ME, Heinsimer JA. Neural network analysis ofserial cardiac enzyme data-a clinical application of artificialmachine intelligence. Am J dIm Pathol 1991:96:134-41.
30. Reibnegger G, Weiss G, Wachter H. Self-organizing neural net-works as a means of cluster analysis in clinical chemistry. EurJ dIm Chem dIm Biochem 1993:31:311-7.
31. McClelland JL, Rumelhart DE. Explorations in parallel distributedprocessing. Cambridge, MA: MIT Press, 1989.