Algorithm; Artificial intelligence; Calcium; Corrected calcium; Ionized calcium; Biochemistry; Clinical Biochemistry; Biochemistry (medical); General Medicine
Abstract :
[en] ("[en] BACKGROUND AND AIMS: Calcium plays a fundamental role in biological processes. Ionized calcium (Ca2+), is the biologically active fraction, but in practice total or corrected calcium assays are routinely used to determine calcium status.
MATERIALS AND METHODS: We retrospectively compared total and corrected calcium to assess the calcium status, with ionized calcium which is considered for now like the best indicator. To compensate for their lack of performance we created a machine learning algorithm to predict calcium status.
RESULTS: Corrected calcium performed less well than total calcium with 58% and 74% agreement, respectively, in our population. Total calcium was especially good for hypocalcemic samples: 93% agreement versus 45% for normocalcemic and 54% for hypercalcemic samples. Corrected calcium was especially good for hypercalcemic and normocalcemic samples: 90% and 84% agreement respectively versus 40% for hypocalcemic samples. Corrected calcium is mainly faulty in hypoalbuminemia, acid-base disorders, renal insufficiency, hyperphosphatemia, or inflammatory syndrome. With our ML algorithm, we obtained 81% correct classifications. Its main advantage is that its performance are not influenced by the variables studied or the calcium status.
CONCLUSION: In many situations, corrected calcium should not be used. Our ML algorithm may make a better assessment of calcium status than total calcium. Finally, if doubt, an ionized calcium assay should be performed.","[en] ","")
Disciplines :
Laboratory medicine & medical technology
Author, co-author :
Bancal, Candice; Laboratoire de biochimie et biologie moléculaire, CHU Nîmes, France. Electronic address: candice.bancal@chu-nimes.fr
Salipante, Florian; Laboratoire de biostatistique, épidémiologie clinique, santé publique, innovation et méthodologie, CHU de Nîmes, Université de Montpellier, Nîmes, France
Hannas, Nassim; Laboratoire Labosud, groupe Inovie, Montpellier, France
Lumbroso, Serge; Laboratoire de biochimie et biologie moléculaire, CHU Nîmes, France
Cavalier, Etienne ; Centre Hospitalier Universitaire de Liège - CHU > > Service de chimie clinique
De Brauwere, David-Paul; Service de biochimie et biologie moléculaire, UM Pathologies Héréditaires du Métabolisme et Du Globule Rouge, Hospices civils de Lyon, France
Language :
English
Title :
A new approach to assessing calcium status via a machine learning algorithm.
Dickerson, R., Alexander, K., Minard, G., Croce, M., Brown, R., Accuracy of methods to estimate ionized and « corrected » serum calcium concentrations in critically ill multiple trauma patients receiving specialized nutrition support. J. Parenter. Enteral Nutr. 28 (2004), 133–141.
Toffaletti, J., Savory, J., Gitelman, H.J., Use of gel filtration to examine the distribution of calcium among serum proteins. Clin. Chem. 23:12 (1977), 2306–2310.
Toffaletti, J., Gitelman, H.J., Savory, J., Separation and quantification of serum constituents associated with calcium by gel filtration. Clin. Chem. 22:12 (1976), 1968–1972.
Glendenning, P., It is time to start ordering ionized calcium more frequently: preanalytical factors can be controlled and postanalytical data justify measurement [Editorial]. Ann. Clin. Biochem. 50:Pt 3 (2013), 191–193.
Gidenne, S., Vigezzi, J.-F., Delacour, H., Damiano, J., Clerc, Y., Dosage direct du calcium ionisé plasmatique ou estimation par calcul: intérêts et limites [Review]. Ann. Biol. Clin. 61 (2003), 393–399.
Payne, R.B., Little, A.J., Williams, R.B., Milner, J.R., Interpretation of serum calcium in patients with abnormal serum proteins. Br. Med. J. 4:5893 (1973), 643–646.
Orrell, D.H., Albumin as an aid to the interpretation of serum calcium. Clin. Chim. Acta 35:2 (1971), 483–489.
Lian, I.A., Åsberg, A., Should total calcium be adjusted for albumin? A retrospective observational study of laboratory data from central Norway. BMJ Open, 8(4), 2018, e017703.
Besarab, A., Caro, J.F., Increased absolute calcium binding to albumin in hypoalbuminaemia. J. Clin. Pathol. 34:12 (1981), 1368–1374.
Toffaletti, J.G., Predicting ionized hypocalcemia with total calcium: Can « correction » with logistical modeling of multiple analytes do the trick [Editorial]?. J. Appl. Lab. Med. 5 (2020), 1–3.
Gauci, C., Moranne, O., Fouqueray, B., de la Faille, R., Maruani, G., Haymann, J.-P., Jacquot, C., Boffa, J.-J., Flamant, M., Rossert, J., Urena, P., Stengel, B., Souberbielle, J.-C., Froissart, M., Houillier, P., Pitfalls of measuring total blood calcium in patients with CKD. J Am Soc Nephrol 19:8 (2008), 1592–1598.
Gouri, A., Dekaken, A., A comparison of corrected serum calcium levels to ionized calcium levels in haemodialysis patients. Ann. Biol. Clin. 70 (2012), 210–212.
Law, M.M., Smith, J.D., Schneider, H.G., Wilson, S., Misclassification of calcium status in end-stage kidney disease using albumin-adjusted calcium levels. Nephrology 26:9 (2021), 725–732.
Ong, G.S.Y., Walsh, J.P., Stuckey, B.G.A., Brown, S.J., Rossi, E., Ng, J.L., Nguyen, H.H., Kent, G.N., Lim, E.M., The importance of measuring ionized calcium in characterizing calcium status and diagnosing primary hyperparathyroidism. J. Clin. Endocrinol. Metab. 97:9 (2012), 3138–3145.
Buege, M.J., Do, B., Lee, H.C., Weber, D.M., Horowitz, S.B., Feng, L., Qing, Y., Shank, B.R., Corrected calcium versus ionized calcium measurements for identifying hypercalcemia in patients with multiple myeloma. Cancer Treat Res Commun, 21, 2019, 100159.
Slomp, J., van der Voort, P.H.J., Gerritsen, R.T., Berk, J.A.M., Bakker, A.J., Albumin-adjusted calcium is not suitable for diagnosis of hyper- and hypocalcemia in the critically ill. Crit. Care Med. 31:5 (2003), 1389–1393.
Steele, T., Kolamunnage-Dona, R., Downey, C., Toh, C.-H., Welters, I., Assessment and clinical course of hypocalcemia in critical illness. Crit. Care, 17(3), 2013, R106.
Zulkufli, N.S., Jamaluddin, F.A., Tengku Yazid, T.N., Limitations of calculated ionised calcium & adjusted calcium in critically ill patients: Time to consider measured ionised calcium. Malays. J. Pathol. 42 (2020), 385–394.
Pekar, J.D., Grzych, G., Durand, G., Haas, J., Lionet, A., Brousseau, T., et al. Calcium state estimation by total calcium: the evidence to end the never-ending story. Clin. Chem. Lab. Med. 58 (2020), 222–231.
Grzych, G., Pekar, J.D., Durand, G., Deckmyn, B., Maboudou, P., Lippi, G., Albumin-adjusted calcium and ionized calcium for assessing calcium status in hospitalized patients (Trans.) Letter to the Editor Clin. Chem. 65 (2019), 703–705.
Comité de coordination de l’évaluation clinique et de la qualité en Aquitaine, Agence nationale d'accréditation et d’évaluation en santé, éditeurs. Les coûts de la qualité et de la non-qualité des soins dans les établissements de santé: états des lieux et propositions, juillet 2004. Saint-Denis-la-Plaine: Agence nationale d'accréditation et d’évaluation en santé; 2004. Available from https://www.has-sante.fr/upload/docs/application/pdf/Couts_qualite2_2004_Rap.pdf (accessed 21 September 2022).
Bertocchio, J.P., Hypercalcémie. Available from Items Rev. Prat., 2020 https://www.larevuedupraticien.fr/article/hypercalcemie.
Smith, J.D., Wilson, S., Schneider, H.G., Misclassification of calcium status based on albumin-adjusted calcium: Studies in a tertiary hospital setting. Clin. Chem. 64 (2018), 1713–1722.
Labriola, L., Jadoul, M., The choice of the assay for measuring albumin has a major impact on routine laboratory values. Kidney Int., 96, 2019, 248.
Godefroy, J., Mena, Y., Vermond, N., Le Cruguel, S., Le Jeune, M., Plançon, M., et al. Comparison of three albumin assay methods: a need for standardization within a healthcare area. Ann. Biol. Clin. (Paris) 79 (2021), 587–596.
Labriola, L., Wallemacq, P., Gulbis, B., Jadoul, M., The impact of the assay for measuring albumin on corrected ('adjusted’) calcium concentrations. Nephrol. Dial. Transplant. 24 (2009), 1834–1838.
Yamaguchi, S., Hamano, T., Doi, Y., Oka, T., Kajimoto, S., Kubota, K., et al. Hidden hypocalcemia as a risk factor for cardiovascular events and all-cause mortality among patients undergoing incident hemodialysis. Sci. Rep., 10, 2020, 4418.
Obi, Y., Mehrotra, R., Rivara, M.B., Streja, E., Rhee, C.M., Lau, W.L., et al. Hidden hypercalcemia and mortality risk in incident hemodialysis patients. J. Clin. Endocrinol. Metab. 101 (2016), 2440–2449.
Kaku, Y., Ookawara, S., Miyazawa, H., Ito, K., Ueda, Y., Hirai, K., et al. New method for the approximation of corrected calcium concentrations in chronic kidney disease patients. Ther. Apher. Dial. 20 (2016), 46–52.
Ferrari, P., Singer, R., Agarwal, A., Hurn, A., Townsend, M.A., Chubb, P., Serum phosphate is an important determinant of corrected serum calcium in end-stage kidney disease. Nephrology 14 (2009), 383–388.
