scholarly journals Development of a Machine Learning Algorithm for Rapid, Point-of-Care Prediction of Serum Monoclonal Proteins in Multiple Myeloma

Blood ◽  
2020 ◽  
Vol 136 (Supplement 1) ◽  
pp. 13-15
Author(s):  
Ehsan Malek ◽  
Jeries Kort ◽  
Gi-Ming Wang ◽  
Paolo F Caimi ◽  
Kirsten M Boughan ◽  
...  
Keyword(s):  
Research Funding ◽  
Point Of Care ◽  
Advisory Board ◽  
Total Serum Protein ◽  
Total Serum ◽  
Test Set ◽  
Protein Levels ◽  
The Difference ◽  
M Spike ◽  
Monoclonal Proteins

Multiple Myeloma (MM) is a cancer of terminally-differentiated plasma cells residing in the bone marrow. Myeloma cells frequently secrete monoclonal proteins that can be used to assess tumor volume and patient response to therapy. Monoclonal proteins are measured by gel electrophoresis and subsequent immunofixation of the observed M-spike for protein typing. However, this a time-consuming process that may take up to 3-5 days that delays physician-patient decision-making, determining response to treatment and can be a significant psychological stressor for patients. Hence, there is an unmet need to develop a more rapid, point-of-care method to determine M-spike levels. Gamma gap is the difference between total serum protein and albumin and includes a variety metabolic proteins, i.e., transferrin, as well as immunologic proteins, e.g., non-involved immunoglobulins, in addition to the M-spike. Since estimation of the non-M-spike portion of the gamma gap cannot be achieved on routine patient care, the gamma gap cannot serve as an accurate surrogate for M-spike protein levels. Here, we hypothesized that an artificial intelligence (AI) algorithm utilizing readily available clinical and laboratory data along with previous and same-day lab variables can accurately predict M-spike levels without the need for serum electrophoresis. Methods: A total of 171 MM patients with 1,472 observations were included in the study, where the upper limit of the observed M-spike was 3.5 gr/dL. Correlation of the observed M-spike with gamma gap was assessed by two correlation methods using the Pearson and Spearman tests. Forty three clinical and lab variables (including total serum protein and albumin) as predictors of M-spike were fed into the machine learning model. Two lagged variables as the last two preceding M-spike values by the same subject were included. When needed, imputation for missing values was applied through interpolation from subject-level linear trend analysis. The random forest model was used, where regression forests are an ensemble of different regression trees and are used for nonlinear multiple regression. The default number of trees was set to be n = 500, and the number of variables considered at each split after random selection was 13. The goal of using a large number of trees was to train enough that each feature had a chance to appear in several models. The data was randomly split into a training set (80%) and a test set (20%), and a regression tree was built with the training set and then validated using the test set. Bootstrapping was used to generate a collection of data sets (n=500), leading to a random forest of regression trees. Results and estimates were combined across trees. Importance was measured by leaving a covariate out of models, and comparing performance with its inclusion. All analyses were performed using R v3.6.2 and its libraries. Results: Median age of the study cohort was 73 years old, range: 42-96), and 44% were male. The median M-spike value was (0.7 gr/dL, range: 0.1-3.5). Fig. 1 shows the number of observations and magnitude distribution for M-spike levels among the patients included in our study. The correlation of the calculated gamma gap and observed M-spike levels was assessed by two methods (Fig.2). The Pearson coefficient was 0.43 for M-spike levels <1 and 0.72 for M-spike levels >1 gr/dL, respectively (Fig.2a). The Spearman coefficient was 0.41 for M-spike levels <1 and 0.74 for M-spike levels >1 suggesting a low overall correlation overall, especially for M-spike levels <1 gr/dL (Fig .2b). In contrast, as shown in Fig. 3, M-spike levels predicted by the AI algorithm (i.e., fitted M-spike in the test set) correlated highly with the observed M-spike levels in the test set (R-square: 94% and RMSE of 0.21). The Pearson and Spearman coefficients were 0.97 and 0.95, respectively. Fig. 3b. Indicates the residual distribution for the RF model with most of values are close to and on both side zero value. Conclusion: Here, we showed that the difference between total protein and albumin (i.e., gamma gap) is a rough estimate of M-spike, especially with lower values. AI algorithm trained by 43 readily available clinical and laboratory variables could predict the observed M-spike very robustly. Taken together, our results indicate that the AI-based method developed here can be further advanced for rapid, accurate, point-of-care measurement of M-spike protein levels in MM patients. Figure 1 Disclosures Malek: Cumberland: Research Funding; Sanofi: Other: Advisory board; Clegene: Other: Advisory board , Speakers Bureau; Takeda: Other: Advisory board , Speakers Bureau; Janssen: Other: Advisory board, Speakers Bureau; Bluespark: Research Funding; Amgen: Honoraria; Medpacto: Research Funding. Caimi:Amgen: Other: Advisory Board; Verastem: Other: Advisory Board; Celgene: Speakers Bureau; Bayer: Other: Advisory Board; ADC Therapeutics: Other: Advisory Board, Research Funding; Kite Pharma: Other: Advisory Board. de Lima:Celgene: Research Funding; Pfizer: Other: Personal fees, advisory board, Research Funding; Kadmon: Other: Personal Fees, Advisory board; Incyte: Other: Personal Fees, advisory board; BMS: Other: Personal Fees, advisory board.

Effects of sodium fluoride on total serum protein levels and transaminase activity in rats

2002 ◽  
Vol 56 (4) ◽  
pp. 169-172 ◽  
Author(s):  
D Qujeq ◽  
B Laghaie ◽  
A Gholipour ◽  
N Solimani ◽  
S Hassenzadeh
Keyword(s):  
Serum Protein ◽  
Sodium Fluoride ◽  
Total Serum Protein ◽  
Total Serum ◽  
Transaminase Activity ◽  
Protein Levels

scholarly journals Comparison of MGUS Prevalence By Race and Family History Risk Groups Using a High Sensitivity Screening Method (MASS-FIX)

Blood ◽  
2020 ◽  
Vol 136 (Supplement 1) ◽  
pp. 40-41
Author(s):  
Celine M. Vachon ◽  
Josiah Murray ◽  
Cristine Allmer ◽  
Dirk Larson ◽  
Aaron D. Norman ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Clinical Trials ◽  
Research Funding ◽  
Risk Groups ◽  
Advisory Board ◽  
Maldi Tof Mass Spectrometry ◽  
Maldi Tof ◽  
M Proteins ◽  
Prevalence Estimates ◽  
Monoclonal Proteins

Introduction Monoclonal gammopathy of undetermined significant (MGUS) is a premalignant plasma cell disorder that is common in individuals over age 50. MGUS prevalence estimates to date have generally been based on results of serum electrophoresis and immunofixation (for heavy chain [HC] MGUS) and additionally, free light chain (for light chain [LC] MGUS). Mass-spectrometry assays, however, can detect lower levels of monoclonal (M) proteins, identify the isotype and provide accurate quantification of the M-protein. Given the evidence that MGUS is likely present at least 10 years prior to its detection, mass spectrometry may provide more accurate estimates of underlying MGUS. We examined the prevalence of HC-MGUS using matrix-assisted laser desorption/ionization-time of flight (MALDI-TOF) mass spectrometry among three risk groups: European Americans (EA), African Americans (AA) and first-degree relatives (FDR) of patients with multiple myeloma (MM), MGUS, chronic lymphocytic leukemia (CLL) or non-Hodgkin's lymphoma (NHL). Methods We sampled all AA and a random sample of EA participants ages 50 and older enrolled in the Mayo Clinic Biobank. We also selected unaffected first-degree relatives (limiting to ages 50 and older) from our ongoing family study of hematological malignancies. We screened serum samples by the MALDI-TOF mass spectrometry assay, which is clinically used at Mayo Clinic (known as MASS-FIX) for detection and isotypes of M-proteins. The assay uses isotype-specific nanobody enrichment coupled to MALDI-TOF mass spectrometry. For each of the risk groups, HC- MGUS prevalence was estimated by age (50-59, 60-69, 70+). Age- and sex-adjusted prevalence rates were calculated by direct standardization to the 2010 US population. Ninety-five percent confidence intervals (95% CI) for the prevalence rates and comparisons across the three groups were based on the Poisson distribution. Because free LC information was unavailable, LC-MGUS was not estimated. Results A total 327 AA, 854 EA and 792 FDR were screened for M-proteins using the MASS-FIX assay. All three groups had similar sex (42-44% male) and age distributions (mean[SD] age was 64.5[9.5] yrs., 64.4[8.8] yrs. and 64.9[10.5] yrs. for AA, EA and FDR, respectively). As previously noted using conventional detection methods, the overall prevalence of HC-MGUS was higher in the AA population (16.5% [95%CI: 12.2%, 20.8%]) and FDR (21.5% [95%CI: 18.3%, 24.7%]) than in EA (11.2% [95%CI: 8.8%, 13.5%]), both p-values <0.0001. This pattern was generally seen across age groups (Table 1), with increasing prevalence with age. FDR of MM or MGUS cases had a higher prevalence (22.2% [95%CI: 18.4%, 26.0%]) than FDR of CLL or NHL cases (18.8% [95%CI: 13.3%, 24.4%]), although the difference was not statistically significant (p-value=0.82). Overall prevalence estimates of HC-MGUS using MASS-FIX were at least three-fold higher than estimates using conventional methods alone (i.e. age- and sex-adjusted prevalence in Olmsted County, MN, was 3.1% [95% CI: 2.9%-3.4%]). Conclusion We provided some of the first data on prevalence of HC-MGUS across three risk groups, using a sensitive method for detecting monoclonal proteins. The MASS-FIX assay resulted in substantially higher absolute rates of HC-MGUS (at least 3-fold higher) relative to conventional methods. Further, the prevalence of HC-MGUS among the AA and FDR was significantly higher than the EA population. Thus, the more sensitive assay identified greater absolute numbers of individuals with MGUS, but resulted in similar relationships as seen in prior studies across these risk groups. Our results have implications for future studies of the etiology of MGUS and its progression. Disclosures Dispenzieri: Janssen: Research Funding; Pfizer: Research Funding; Alnylam: Research Funding; Intellia: Research Funding; Celgene: Research Funding; Takeda: Research Funding. Kumar:Amgen: Consultancy, Other: Research funding for clinical trials to the institution, Consulting/Advisory Board participation with no personal payments, Research Funding; Janssen Oncology: Other: Research funding for clinical trials to the institution, Consulting/Advisory Board participation with no personal payments; Takeda: Other: Research funding for clinical trials to the institution, Consulting/Advisory Board participation with no personal payments; AbbVie: Other: Research funding for clinical trials to the institution, Consulting/Advisory Board participation with no personal payments; Karyopharm: Consultancy; Genecentrix: Consultancy; Cellectar: Other; Carsgen: Other, Research Funding; Merck: Consultancy, Research Funding; Dr. Reddy's Laboratories: Honoraria; Adaptive Biotechnologies: Consultancy; Celgene/BMS: Other: Research funding for clinical trials to the institution, Consulting/Advisory Board participation with no personal payments; Genentech/Roche: Other: Research funding for clinical trials to the institution, Consulting/Advisory Board participation with no personal payments; Oncopeptides: Consultancy, Other: Independent Review Committee; IRC member; Kite Pharma: Consultancy, Research Funding; BMS: Consultancy, Research Funding; Tenebio: Other, Research Funding; Sanofi: Research Funding; MedImmune: Research Funding; Novartis: Research Funding. Murray:The Binding Site: Patents & Royalties: Patent Use of Mass Spec to identify monoclonal proteins licensed to The Binding Site.

scholarly journals Quality of bovine colostrum and its relation to genetics, management, physiology and its freezing

2020 ◽  
pp. e1465
Author(s):  
Ana Luiza Schogor ◽  
Patricia Glombowsky ◽  
Fabiana Both ◽  
Beatriz Danieli ◽  
Fernanda Rigon ◽  
...  
Keyword(s):  
Holstein Cows ◽  
Total Serum Protein ◽  
Total Serum ◽  
Freezing Process ◽  
Plasma Protein Concentration ◽  
Protein Levels ◽  
The Mean ◽  
Over Time ◽  
Process Material

Objective. The aims of this study were to assess whether colostrum quality is modified by genetic, physiological and management characteristics in the pre-partum period, as well as evaluate whether quality and composition of colostrum is altered in the freezing process. Material and methods. In the experiment I, colostrum and blood samples of 35 cows (18 Holstein and 17 Jerseys) were collected. In the experiment II, six colostrum samples of Holstein cows were collected and frozen during 60 days. Results. The mean immunoglobulin (Ig) concentration was 77.65 mg/ml to Jersey and 82.77 mg/ml to Holstein. The genetic, parturition order, and the interaction between these factors were no significant on IgG concentration in the colostrum. Also, it was observed an effect genetic of cow in the weight on calf at birth and on three days of age (p<0.0001). Regarding transmission of calf passive immunity, no effects of cow breed and calving order were observed on plasma protein concentration of calf, as well as after three days of freezing. Calves of Holstein (83%) and Jersey (82%) breed showed total serum protein levels above 5.5 g/dL. Holstein cows housed in individual paddocks with diet supplementation provided better quality of colostrum (93.57 mg Ig/mL). Over time, the percentage of fat reduced at freezing, that reduced over time (p<0.05) in Experiment II. Conclusions. The pre-partum management exerts influence on colostrum quality, and the freezing not interfere on centesimal and immunological quality of colostrum, with exception the fat, that decrease along the time.

THE CATABOLISM OF 131I-LABELLED HOMOLOGOUS γ-GLOBULIN IN NORMAL, HYPERTHYROID AND HYPOTHYROID RATS

1960 ◽  
Vol 21 (1) ◽  
pp. 83-89 ◽  
Author(s):  
C. P. FARTHING ◽  
JULIA GERWING ◽  
JENNIFER SHEWELL
Keyword(s):  
Serum Protein ◽  
Half Life ◽  
Total Serum Protein ◽  
Total Serum ◽  
Protein Levels ◽  
Globulin Level ◽  
Thyroxine Treatment ◽  
Biological Half Life ◽  
Catabolic Rate

SUMMARY The biological half-life of injected homologous 131I-γ-globulin was found to be 4·8 days in euthyroid, 5·8 days in thyroidectomized, and 3·8 days in thyroxine-treated rats. The catabolic rate of homologous γ-globulin, expressed as a percentage of the intravascular protein broken down per day, was decreased from 25·5% in normal rats to 22·5% in thyroidectomized animals, and increased to 39·2% by thyroxine treatment. Total serum protein levels were not affected by thyroxine treatment (0·02 mg/kg) in the rat, but increased after thyroidectomy. This increase was chiefly due to an increased γ-globulin level, and it is postulated that catabolism of γ-globulin in the thyroidectomized rat is decreased to a greater extent than is γ-globulin synthesis.

ALL-VEGETABLE PROTEIN MIXTURES FOR HUMAN FEEDING: XII. BIOCHEMICAL OBSERVATIONS ON RATS FED INCAP VEGETABLE MIXTURE 9 AND ANIMAL PROTEINS

1964 ◽  
Vol 42 (5) ◽  
pp. 631-639 ◽  
Author(s):  
R. Bressani ◽  
J. E. Braham ◽  
L. G. Elías ◽  
S. G. de Zaghi
Keyword(s):  
Protein Intake ◽  
Nitrogen Concentration ◽  
Skim Milk ◽  
Liver Fat ◽  
Total Serum Protein ◽  
Total Serum ◽  
Bone Composition ◽  
Protein Levels ◽  
Similar Chemical ◽  
Biological Tests

Biological tests were carried out to study the effect of INCAP (Institute of Nutrition of Central America and Panama) Vegetable Mixture 9, casein, and skim milk on the carcass, liver, blood, and bone composition of rats. At low levels of protein intake body and liver fat levels were higher in the animals fed the vegetable mixture. Higher values for total serum protein, albumin, globulin, and urea nitrogen concentration were obtained with skim milk, but the albumin/globulin ratio and the red and white blood cell count were similar for both protein foods. The fresh weights of the femur and tibia were found to be significantly lower for the rats fed Vegetable Mixture 9, while bone moisture and fat were significantly higher. Likewise, the percentages of ash, calcium, and phosphorus were also significantly lower in the animals fed the vegetable mixture.At higher levels of protein intake, carcass and liver fat were again higher for the animals fed the vegetable mixture. The blood analyses revealed no differences between the two proteins tested, except for a higher urea content in the animals fed skim milk.The differences in carcass, liver, and bone composition between animals fed the vegetable mixture and the animal proteins were probably due to minor essential amino acid deficiencies in the mixture, since supplementation with lysine, threonine, and methionine resulted in similar chemical composition values. Higher protein levels of intake also decreased the differences in carcass, liver, and bone composition of rats fed INCAP Vegetable Mixture 9, casein, or skim milk.

EFFECTS OF VARYING DIETARY ENERGY, PROTEIN AND AMINO ACID LEVELS ON GROWTH, NUTRIENT DIGESTIBILITY, AND SERUM PROTEIN LEVELS OF EARLY WEANED PIGS

1967 ◽  
Vol 47 (1) ◽  
pp. 77-83 ◽  
Author(s):  
J. F. Standish ◽  
J. P. Bowland
Keyword(s):  
Amino Acid ◽  
Serum Protein ◽  
Feed Intake ◽  
Crude Protein ◽  
Feed Utilization ◽  
Nutrient Digestibility ◽  
Total Serum Protein ◽  
Total Serum ◽  
Or Efficiency ◽  
Protein Levels

Fifteen rations formulated by a factorial arrangement of 3 fat and 5 protein treatments were fed to non-castrate crossbred pigs from 3 to 9 weeks of age. Levels of 0, 4, and 8% fat and 12, 16, and 20% crude protein, and 12 and 16% crude protein with supplemental lysine and methionine to equal that present in the 20% protein diet were fed. Each increment of protein resulted in increased rate of gain. The amino acid supplemented 16% protein ration supported as rapid gain and as efficient utilization of feed as did the 20% ration. Feed intake and efficiency of feed utilization were improved as protein was raised from 12 to 16% and when lysine and methionine were added to the rations. Fat levels were not found to affect rate of gain, feed intake or efficiency of feed utilization. Apparent digestibility of nitrogen was higher in the 20% protein ration than the 12 or 16% protein rations and was also found to increase when amino acids were added to the low protein rations. More of the apparent digestible nitrogen was retained from the amino acid-supplemented rations. Increasing fat levels were found to reduce: the total serum protein levels in gilts but not in boars.

Compensating for the influence of total serum protein in the Schwartz formula

2012 ◽  
Vol 50 (9) ◽  
Author(s):  
Marijn M. Speeckaert ◽  
Birgitte Wuyts ◽  
Veronique Stove ◽  
Johan Vande Walle ◽  
Joris R. Delanghe
Keyword(s):  
Serum Creatinine ◽  
Total Protein ◽  
Protein Concentration ◽  
Serum Proteins ◽  
Relative Bias ◽  
Total Serum Protein ◽  
Total Serum ◽  
Schwartz Formula ◽  
Kinetic Rate ◽  
The Difference

AbstractThe Schwartz 2009 creatinine-based revised formula is the only pediatric GFR estimating formula, which is compatible with the recent global creatinine standardization. This formula is only applicable if enzymatic creatinine methods are used. We propose an equation, taking into account the relative bias caused by serum proteins to use Jaffe based creatinine data for GFR estimation.In a cohort study of 100 pediatric patients, serum creatinine was measured using a kinetic rate-blanked Jaffe assay (modified kinetic alkaline picrate method), a kinetic rate-blanked Jaffe compensated assay for reactive proteins and an enzymatic assay (creatinine plus method). Serum total protein, albumin, urea, uric acid and total bilirubin were measured with the use of commercial agents.The difference in serum creatinine between the enzymatic method and the compensated Jaffe method was mainly dependent on the total protein concentration in serum (rIn this study, we demonstrated the usability of the alkaline picrate method in the Schwartz formula, taking into account the relative bias caused by serum proteins.

scholarly journals Selected haematological changes in Clarias gariepinus (Burchell, 1822) infected with a Trypansosoma sp. from the Vaal Dam, South Africa

2013 ◽  
Vol 80 (1) ◽  
Author(s):  
Maryke L. Ferreira ◽  
Annemarie Avenant-Oldewage
Keyword(s):  
Serum Protein ◽  
Total Protein ◽  
Clarias Gariepinus ◽  
Total Serum Protein ◽  
Total Serum ◽  
Total Plasma ◽  
Breeding Stock ◽  
Protein Levels ◽  
Total Plasma Protein ◽  
Haematological Changes

The use of haematological techniques to assess fish health is generally accepted. The aim of the current study was to determine selected haematological changes that occur in Clarias gariepinus (Burchell, 1822). infected with trypanosomes. Blood films were prepared according to standard techniques to confirm trypanosome infections and whole blood was collected, the serum and plasma separated, and prepared for albumin and total protein concentration analysis. Plasma albumin levels were significantly higher in infected wild caught fish than in uninfected wild caught fish and uninfected breeding stock. Serum albumin levels were significantly lower in infected wild caught fish when compared to uninfected breeding stock. The total plasma and serum protein levels were within the normal range for C. gariepinus, that is, 3 g – 6 g/100 mL. The total plasma protein levels varied significantly between the three groups. However, the total serum protein levels were only significantly different between uninfected breeding stock and uninfected wild caught fish, as well as uninfected breeding stock and infected wild caught fish. The total protein levels were significantly higher in infected wild caught fish than in the other groups, a possible indication of an infection or inflammatory host response.

Sign in / Sign up

Export Citation Format

Share Document