Machine Learning-Based Prediction of Hemoglobinopathies Using Complete Blood Count Data.

BACKGROUND: Hemoglobinopathies, the most common inherited blood disorder, are frequently underdiagnosed. Early identification of carriers is important for genetic counseling of couples at risk. The aim of this study was to develop and validate a novel machine learning model on a multicenter data set, covering a wide spectrum of hemoglobinopathies based on routine complete blood count (CBC) testing. METHODS: Hemoglobinopathy test results from 10 322 adults were extracted retrospectively from 8 Dutch laboratories. eXtreme Gradient Boosting (XGB) and logistic regression models were developed to differentiate negative from positive hemoglobinopathy cases, using 7 routine CBC parameters. External validation was conducted on a data set from an independent Dutch laboratory, with an additional external validation on a Spanish data set (n = 2629) specifically for differentiating thalassemia from iron deficiency anemia (IDA). RESULTS: The XGB and logistic regression models achieved an area under the receiver operating characteristic (AUROC) of 0.88 and 0.84, respectively, in distinguishing negative from positive hemoglobinopathy cases in the independent external validation set. Subclass analysis showed that the XGB model reached an AUROC of 0.97 for ß-thalassemia, 0.98 for α0-thalassemia, 0.95 for homozygous α+-thalassemia, 0.78 for heterozygous α+-thalassemia, and 0.94 for the structural hemoglobin variants Hemoglobin C, Hemoglobin D, Hemoglobin E. Both models attained AUROCs of 0.95 in differentiating IDA from thalassemia. CONCLUSIONS: Both the XGB and logistic regression model demonstrate high accuracy in predicting a broad range of hemoglobinopathies and are effective in differentiating hemoglobinopathies from IDA. Integration of these models into the laboratory information system facilitates automated hemoglobinopathy detection using routine CBC parameters.

Analytical interference of intravascular contrast agents with clinical laboratory tests: a joint guideline by the ESUR Contrast Media Safety Committee and the Preanalytical Phase Working Group of the EFLM Science Committee.

The Contrast Media Safety Committee of the European Society of Urogenital Radiology has, together with the Preanalytical Phase Working Group of the EFLM Science Committee, reviewed the literature and updated its recommendations to increase awareness and provide insight into these interferences.

High first trimester ferritin levels differ according to parity and are independently related to preterm birth: A prospective cohort study.

INTRODUCTION: A considerable amount of neonatal morbidity and mortality worldwide is caused by preterm birth. To date, the underlying etiology of preterm birth has not been fully clarified. Previous studies demonstrate that inflammation is one of the pathological factors that might cause preterm birth, and that there is a difference between primiparous and multiparous women in immune response to pregnancy. The objective of this prospective cohort study was to investigate the role of two inflammatory markers, ferritin and C-reactive protein (CRP) and preterm birth, in first trimester women, stratified for parity. In addition, a possible association between high ferritin and CRP, and a possible association between high ferritin and CRP and preterm birth were assessed. MATERIAL AND METHODS: A total of 2044 healthy, low-risk pregnant women from primary obstetric care in the Netherlands participated in this study. Their ferritin and CRP levels were evaluated at 12 weeks' gestation. Levels above the parity specific 95th percentile were defined as high. The main outcome of this study was to assess the presence of a possible association between parity specific high ferritin and CRP, and preterm birth. The secondary outcomes were the ferritin and CRP levels of women, stratified for parity, and the possible association between high ferritin and CRP levels. Logistic regression analysis was performed with preterm birth as a dependent variable and parity specific high ferritin and CRP as an independent variable, adjusting for age and history of preterm birth. RESULTS: Ferritin levels decreased with increasing parity. Ferritin and CRP levels at 12 weeks' gestation were significantly higher in women with preterm birth. In primiparous women, high ferritin levels (OR: 2.5, CI: 1.14-5.38) and high CRP levels (OR: 5.0, CI: 2.61-9.94) were independently associated with preterm birth. In multiparous women, high ferritin levels (OR: 6.0, CI: 2.28-16.67) were independently associated with preterm birth while high CRP levels were not. CONCLUSIONS: First trimester parity specific ferritin and CRP levels could play a part in predictive models for preterm birth, and further research for their additive role in preterm birth is needed.

The dark side of apnea: altered 24-hour melatonin secretion in obstructive sleep apnea (OSAS) is disease severity dependent.

PURPOSE: Melatonin aids in the synchronization of the circadian rhythm to the external environment. Few studies have tried to elucidate the relationship between melatonin and obstructive sleep apnea syndrome (OSAS). These often include few patients, do not differentiate between OSAS severity and/or do not analyse a 24-h melatonin profile. This study set out to investigate disease severity dependent differences in 24-h salivary melatonin secretion of OSAS patients compared to a reference population in a retrospective design. METHODS: 24-h salivary melatonin profiles of 169 OSAS patients were analysed (55 light, 66 moderate, 48 severe) as well as 91 reference patients. Several aspects of the melatonin curve were analysed and stratified according to OSAS severity. Parameters included: dim light melatonin onset (DLMO), time of returning below DLMO (DLMOoff), peak melatonin concentration and time, and total melatonin exposure. RESULTS: Significant effects were corrected for confounding by age and sex using linear regression. Our analysis shows that, compared to reference and in a disease dependent manner, OSAS patients have a significantly lower 24-h melatonin curve, lower melatonin peak concentration, lower total melatonin exposure and a smaller proportion of patients reach DLMO. The differences in peak melatonin production and total melatonin exposure were resistant to confounding by age and/or sex. CONCLUSION: This study describes clear OSAS severity dependent abnormalities in melatonin production in OSAS patients, independent of sex and/or age. Future research should indicate whether oral melatonin supplementation has beneficial effects in OSAS patients with attenuated endogenous melatonin production.

Analytical interference of intravascular contrast agents with clinical laboratory tests: a joint guideline by the ESUR Contrast Media Safety Committee and the Preanalytical Phase Working Group of the EFLM Science Committee.

The Contrast Media Safety Committee of the European Society of Urogenital Radiology has, together with the Preanalytical Phase Working Group of the EFLM Science Committee, reviewed the literature and updated its recommendations to increase awareness and provide insight into these interferences. CLINICAL RELEVANCE STATEMENT: Contrast Media may interfere with clinical laboratory tests. Awareness of potential interference may prevent unwanted misdiagnosis. KEY POINTS: • Contrast Media may interfere with clinical laboratory tests; therefore awareness of potential interference may prevent unwanted misdiagnosis. • Clinical Laboratory tests should be performed prior to radiological imaging with contrast media or alternatively, blood or urine collection should be delayed, depending on kidney function.

Automated prediction of low ferritin concentrations using a machine learning algorithm.

OBJECTIVES: Computational algorithms for the interpretation of laboratory test results can support physicians and specialists in laboratory medicine. The aim of this study was to develop, implement and evaluate a machine learning algorithm that automatically assesses the risk of low body iron storage, reflected by low ferritin plasma levels, in anemic primary care patients using a minimal set of basic laboratory tests, namely complete blood count and C-reactive protein (CRP). METHODS: Laboratory measurements of anemic primary care patients were used to develop and validate a machine learning algorithm. The performance of the algorithm was compared to twelve specialists in laboratory medicine from three large teaching hospitals, who predicted if patients with anemia have low ferritin levels based on laboratory test reports (complete blood count and CRP). In a second round of assessments the algorithm outcome was provided to the specialists in laboratory medicine as a decision support tool. RESULTS: Two separate algorithms to predict low ferritin concentrations were developed based on two different chemistry analyzers, with an area under the curve of the ROC of 0.92 (Siemens) and 0.90 (Roche). The specialists in laboratory medicine were less accurate in predicting low ferritin concentrations compared to the algorithms, even when knowing the output of the algorithms as support tool. Implementation of the algorithm in the laboratory system resulted in one new iron deficiency diagnosis on average per day. CONCLUSIONS: Low ferritin levels in anemic patients can be accurately predicted using a machine learning algorithm based on routine laboratory test results. Moreover, implementation of the algorithm in the laboratory system reduces the number of otherwise unrecognized iron deficiencies.

Real-time monitoring of drug laboratory test interactions: a proof of concept.

OBJECTIVES: For the correct interpretation of test results, it is important to be aware of drug-laboratory test interactions (DLTIs). If DLTIs are not taken into account by clinicians, erroneous interpretation of test results may lead to a delayed or incorrect diagnosis, unnecessary diagnostic testing or therapy with possible harm for patients. A DLTI alert accompanying a laboratory test result could be a solution. The aim of this study was to test a multicentre proof of concept of an electronic clinical decision support system (CDSS) for real-time monitoring of DLTIs. METHODS: CDSS was implemented in three Dutch hospitals. So-called 'clinical rules' were programmed to alert medical specialists for possible DLTIs based on laboratory test results outside the reference range in combination with prescribed drugs. A selection of interactions from the DLTI database of the Dutch society of clinical chemistry and laboratory medicine were integrated in 43 clinical rules, including 24 tests and 25 drugs. During the period of one month all generated DTLI alerts were registered in the laboratory information system. RESULTS: Approximately 65 DLTI alerts per day were detected in each hospital. Most DLTI alerts were generated in patients from the internal medicine and intensive care departments. The most frequently reported DLTI alerts were potassium-proton pump inhibitors (16%), potassium-beta blockers (11%) and creatine kinase-statins (11%). CONCLUSIONS: This study shows that it is possible to alert for potential DLTIs in real-time with a CDSS. The CDSS was successfully implemented in three hospitals. Further research must reveal its usefulness in clinical practice.

Plasma mineral (selenium, zinc or copper) concentrations in the general pregnant population, adjusted for supplement intake, in relation to thyroid function.

The present study reports on first-trimester reference ranges of plasma mineral Se/Zn/Cu concentration in relation to free thyroxine (FT4), thyrotropin (TSH) and thyroid peroxidase antibodies (TPO-Ab), assessed at 12 weeks' gestation in 2041 pregnant women, including 544 women not taking supplements containing Se/Zn/Cu. The reference range (2·5th-97·5th percentiles) in these 544 women was 0·72-1·25 µmol/l for Se, 17·15-35·98 µmol/l for Cu and 9·57-16·41 µmol/l for Zn. These women had significantly lower mean plasma Se concentration (0·94 (sd 0·12) µmol/l) than those (n 1479) taking Se/Zn/Cu supplements (1·03 (sd 0·14) µmol/l; P < 0·001), while the mean Cu (26·25 µmol/l) and Zn (12·55 µmol/l) concentrations were almost identical in these sub-groups. Women with hypothyroxinaemia (FT4 below reference range with normal TSH) had significantly lower plasma Zn concentrations than euthyroid women. After adjusting for covariates including supplement intake, plasma Se (negatively), Zn and Cu (positively) concentrations were significantly related to logFT4; Se and Cu (but not Zn) were positively and significantly related to logTSH. Women taking additional Se/Zn/Cu supplements were 1·46 (95 % CI 1·09, 2·04) times less likely to have elevated titres of TPO-Ab at 12 weeks of gestation. We conclude that first-trimester Se reference ranges are influenced by Se-supplement intake, while Cu and Zn ranges are not. Plasma mineral Se/Zn/Cu concentrations are associated with thyroid FT4 and TSH concentrations. Se/Zn/Cu supplement intake affects TPO-Ab status. Future research should focus on the impact of trace mineral status during gestation on thyroid function.

Clinical usefulness of drug-laboratory test interaction alerts: a multicentre survey.

OBJECTIVES: Knowledge of possible drug-laboratory test interactions (DLTIs) is important for the interpretation of laboratory test results. Failure to recognize these interactions may lead to misinterpretation, a delayed or erroneous diagnosis, or unnecessary extra diagnostic tests or therapy, which may harm patients. The aim of this multicentre survey was to evaluate the clinical value of DLTI alerts. METHODS: A survey was designed with six predefined clinical cases selected from the clinical laboratory practice with a potential DLTI. Physicians from several departments, including internal medicine, cardiology, intensive care, surgery and geriatrics in six participating hospitals were recruited to fill in the survey. The survey addressed their knowledge of DLTIs, motivation to receive an alert and opinion on the potential influence on medical decision making. RESULTS: A total of 210 physicians completed the survey. Of these respondents 93% had a positive attitude towards receiving DLTI alerts; however, the reported value differed per case and per respondent's background. In each clinical case, medical decision making was influenced as a consequence of the reported DLTI message (ranging from 3 to 45% of respondents per case). CONCLUSIONS: In this multicentre survey, most physicians stated DLTI messages to be useful in laboratory test interpretation. Medical decision making was influenced by reporting DLTI alerts in each case. Alerts should be adjusted according to the needs and preferences of the receiving physicians.

Hypothyroxinaemia during gestation is associated with low ferritin and increased levels of inflammatory markers.

Objective: Pregnancy is a state of physiological inflammation facilitating implantation. Early isolated hypothyroxinaemia (IH) and increased inflammation (including obesity) have been associated with severe obstetric complications. The current study evaluated the association between IH, low ferritin and inflammation parameters (interleukin 6 (IL-6), C-reactive protein (CRP), human chorionic gonadotrophin (hCG) and obesity. Moreover, the course of these parameters throughout pregnancy was evaluated in relation to IH. Methods: In the cross-sectional study (A) at 12 weeks, 2759 women participated and 2433 participated in the longitudinal study (B) with assessments at 12, 20 and 28 weeks gestation. At the first trimester, 122 (4.4%) IH women (free thyroxine (FT4) <5th percentile, normal TSH levels) were compared with 2114 (76.6%) reference women (FT4 between tenth and 90th percentiles, normal thyrotrophin (TSH) levels), in study B these figures were 99 (4.1%) and 1847 (75.9%), respectively. Results: Cross-sectionally, compared to reference women, IH was independently associated with low ferritin (<5th percentile, OR: 2.6, 95% CI: 1.4-4.9), high CRP (>95th percentile: OR: 1.9, 95% CI: 1.04-3.7), low hCG ( 30, OR: 1.7, 95% CI: 1.12.9) and higher age (OR: 1.1, 95% CI: 1.04-1.15). Longitudinally, compared to reference women, women with IH at 12 weeks gestation showed persistently and significantly lower ferritin and hCG levels, and persistently higher CRP and IL-6 levels throughout gestation. Conclusion: Gestational IH could be viewed as a condition of increased inflammation, as reported in non-thyroidal illness syndrome. Less favourable inflammation parameters and low iron status during early gestation in IH women seem to persist throughout gestation.

Evaluation of Glial Fibrillary Acidic Protein and Ubiquitin C-Terminal Hydrolase-L1 Using a Rapid Point of Care Test for Predicting Head Computed Tomography Lesions After Mild Traumatic Brain Injury in a Dutch Multi-Center Cohort.

Mild traumatic brain injury (mTBI) is a common condition seen in emergency departments worldwide. Blood-based biomarkers glial fibrillary acidic protein (GFAP) and ubiquitin C-terminal hydrolase-L1 (UCH-L1) are recently U.S. Food and Drug Administration-approved for the prediction of intracranial lesions on head computed tomography (CT) scans in mTBI. We evaluated the diagnostic performance of GFAP and UCH-L1 in a Dutch cohort using the i-STAT TBI assay. In a multi-center observational study, we enrolled 253 mTBI patients. Head CT scans were scored using the Marshall classification system. Logistic regression models were used to assess the contribution of biomarkers and clinical parameters to diagnostic performance. Detection of UCH-L1 and GFAP resulted in a sensitivity of 97% and specificity of 19% for CT positivity in mTBI patients, along with a negative predictive value of 95% (88-100%) and a positive predictive value of 27% (21-33%). Combining biomarker testing with loss of consciousness and time to sample increased specificity to 46%. Combined testing of UCH-L1 and GFAP testing resulted in possibly more unnecessary CT scans compared with GFAP testing alone, with only limited increase in sensitivity. This study confirmed high sensitivity of GFAP and UCH-L1 for CT abnormalities in mTBI patients using the i-STAT TBI test. The results support the potential use of GFAP and UCH-L1 as tools for determining the indication for CT scanning in mTBI patients, possibly offering a cost- and time-effective approach to management of patients with mTBI. Prospective studies in larger cohorts are warranted to validate our findings.

The first trimester plasma copper-zinc ratio is independently related to pregnancy-specific psychological distress symptoms throughout pregnancy.

OBJECTIVES: High plasma copper (Cu) and low zinc (Zn) levels have been associated with depression. However, most studies used low sample sizes and a cross-sectional design, and perinatal data are scarce. We investigated the possible association between pregnancy-specific psychological distress and the plasma CuZn ratio using a prospective design. METHODS: Pregnancy-specific distress symptoms were assessed at each trimester by means of the Tilburg Pregnancy Distress Scale, negative affect subscale, in 2036 pregnant women. Cu and Zn were assessed at 12 wk of gestation in plasma samples by inductively coupled plasma mass spectrometry. Growth mixture modeling determined trajectories of women's pregnancy-specific negative affect (P-NA) symptoms, which were entered in a multiple logistic regression analysis as dependent variable and the CuZn ratio as independent variable. RESULTS: Two P-NA symptom classes were found: 1) persistently low (n = 1820) and 2) persistently high (n = 216). A higher CuZn ratio was independently associated with persistently high P-NA symptom scores (odds ratio = 1.52; 95% confidence interval, 1.13-2.04) after adjustment for confounders. A sensitivity analysis was performed excluding all women with high P-NA scores at 12 wk of gestation (>1 SD above the mean P-NA score). In the 1719 remaining women, a higher CuZn ratio significantly predicted the development of increasing P-NA symptom scores after adjustment for confounders (odds ratio = 1.40; 95% confidence interval, 1.04-1.95). CONCLUSIONS: A higher CuZn plasma ratio is an independent determinant of developing pregnancy-specific distress symptoms throughout pregnancy, suggesting that micronutrients could be used as novel biomarkers for psychological distress research of perinatal mood disorders.

Hypothyroid Symptoms Throughout Pregnancy Are Predominantly Associated with Thyroxine and Not with Thyrotropin Concentrations.

Background: It is unclear whether levels of hypothyroid symptoms in pregnant women with (sub)clinical thyroid dysfunction differ from euthyroid controls and whether free thyroxine (fT4)/thyrotropin (TSH) changes throughout pregnancy affect hypothyroid symptom levels. The objective was twofold: (1) To compare hypothyroid symptom levels between thyroid dysfunction subgroups and a carefully defined reference group; (2) to assess the association between fT4/TSH changes throughout pregnancy and hypothyroid symptom levels adjusted for depressive symptoms. Methods: The current study was a longitudinal prospective cohort study in 1800 healthy pregnant women. At each trimester of pregnancy, hypothyroid symptoms were assessed with a 12-item symptom hypothyroidism checklist and depressive symptoms with the Edinburgh Depression Scale. Thyroid dysfunction was defined using the 2.5-97.5th fT4/TSH percentile of thyroid peroxidase antibodies-negative women. Euthyroid controls consisted of women with appropriate fT4 levels within the 10-90th percentile and with a normal TSH level. Hypothyroid symptom mean scores were compared between controls and several thyroid dysfunction subgroups. Growth mixture modeling was performed to evaluate possible longitudinal trajectories of hypothyroid and depressive symptoms. The association between hypothyroid symptom trajectories (adjusted for depression) and fT4/TSH changes was assessed with multivariate logistic regression analysis. Results: Women with overt hypothyroidism (fT4 < 2.5th, TSH >97.5th) and hypothyroxinemia (fT4 < 2.5th, TSH: 2.5-97.5th) showed higher hypothyroid symptom levels compared with the euthyroid controls and women with subclinical hypothyroidism (SCH, fT4: 2.5-97.5th, TSH >97.5th), because 82% of these SCH women had fT4 levels in the euthyroid range. Two groups of hypothyroid and depressive symptoms were defined: a persistently low and persistently high symptom group. fT4 decreased in 98% of the women from the first to third trimester and per unit pmol/L fT4 decrease (not TSH increase), the likelihood to present persistently high hypothyroid symptoms increased with 46%, adjusted for depression. Conclusions: A properly defined euthyroid control group distinguishes women with hypothyroid symptoms. An fT4 decrease toward end term is associated with persistently high hypothyroid symptom levels. Clinicians should be aware of the importance of fT4 stratification in SCH women.

High Titers of Low Affinity Antibodies in COVID-19 Patients Are Associated With Disease Severity.

Background: Almost 2 years from the beginning of the coronavirus disease 2019 (COVID-19) pandemic, there is still a lot unknown how the humoral response affects disease progression. In this study, we investigated humoral antibody responses against specific SARS-CoV2 proteins, their strength of binding, and their relationship with COVID severity and clinical information. Furthermore, we studied the interactions of the specific receptor-binding domain (RBD) in more depth by characterizing specific antibody response to a peptide library. Materials and Methods: We measured specific antibodies of isotypes IgM, IgG, and IgA, as well as their binding strength against the SARS-CoV2 antigens RBD, NCP, S1, and S1S2 in sera of 76 COVID-19 patients using surface plasmon resonance imaging. In addition, these samples were analyzed using a peptide epitope mapping assay, which consists of a library of peptides originating from the RBD. Results: A positive association was observed between disease severity and IgG antibody titers against all SARS-CoV2 proteins and additionally for IgM and IgA antibodies directed against RBD. Interestingly, in contrast to the titer of antibodies, the binding strength went down with increasing disease severity. Within the critically ill patient group, a positive association with pulmonary embolism, d-dimer, and antibody titers was observed. Conclusion: In critically ill patients, antibody production is high, but affinity is low, and maturation is impaired. This may play a role in disease exacerbation and could be valuable as a prognostic marker for predicting severity.