Common Laboratory Parameters Are Useful for Screening for Alcohol Use Disorder: Designing a Predictive Model Using Machine Learning.

The diagnosis of alcohol use disorder (AUD) remains a difficult challenge, and some patients may not be adequately diagnosed. This study aims to identify an optimum combination of laboratory markers to detect alcohol consumption, using data science. An analytical observational study was conducted with 337 subjects (253 men and 83 women, with a mean age of 44 years (10.61 Standard Deviation (SD)). The first group included 204 participants being treated in the Addictive Behaviors Unit (ABU) from Albacete (Spain). They met the diagnostic criteria for AUD specified in the Diagnostic and Statistical Manual of mental disorders fifth edition (DSM-5). The second group included 133 blood donors (people with no risk of AUD), recruited by cross-section. All participants were also divided in two groups according to the WHO classification for risk of alcohol consumption in Spain, that is, males drinking more than 28 standard drink units (SDUs) or women drinking more than 17 SDUs. Medical history and laboratory markers were selected from our hospital's database. A correlation between alterations in laboratory markers and the amount of alcohol consumed was established. We then created three predicted models (with logistic regression, classification tree, and Bayesian network) to detect risk of alcohol consumption by using laboratory markers as predictive features. For the execution of the selection of variables and the creation and validation of predictive models, two tools were used: the scikit-learn library for Python, and the Weka application. The logistic regression model provided a maximum AUD prediction accuracy of 85.07%. Secondly, the classification tree provided a lower accuracy of 79.4%, but easier interpretation. Finally, the Naive Bayes network had an accuracy of 87.46%. The combination of several common biochemical markers and the use of data science can enhance detection of AUD, helping to prevent future medical complications derived from AUD.

Hemoglobin Le Lamentin in the province of Albacete, Spain: Discovery of 32 cases.

OBJECTIVES: Hemoglobin Le Lamentin (α20(B1)His→Gln) is a ubiquitous variant that has been previously described in a small number of isolated patients. We report the incidental observation of Hb Le Lamentin in a large population from the province of Albacete, in southeastern Spain. Our study investigates possible reasons for the elevated number of carriers of this variant and its implications for the management of diabetes in our region. DESIGN & METHODS: The subjects are 32 diabetic patients whose hemoglobin displayed an unusual peak while they were being tested for glycated hemoglobin at the laboratory of the University General Hospital of Albacete over a 3-year period. Measurements were made by high performance liquid chromatography using a Variant™ II Turbo Kit-2.0, and subsequently the samples of the 32 patients with anomalous peaks were sent to the Hospital Clínico San Carlos (Madrid, Spain) for molecular characterization of any Hb variants. RESULTS: Molecular studies revealed 31 out of 32 patients heterozygous for Le Lamentin, and in one of them, Hb City of Hope was associated with Hb Le Lamentin. The remaining patient was homozygous for the Le Lamentin mutation. Additionally, most patients were native to the northeastern half of the province of Albacete and were unrelated. CONCLUSIONS: Our study describes the largest finding to date of hemoglobin Le Lamentin in a sample of patients. The fact that our region has been perpetually depopulated, with a population that has remained stable in small localities over the centuries, may have favored the survival of the mutation. Since the presence of this variant underestimates the true value of glycated hemoglobin measured by HPLC, it is necessary to systematically review chromatograms.

[Clinical usefulness of biochemical markers of bone turnover in early postmenopausal women: two years longitudinal study]. / Utilidad clínica de los marcadores bioquímicos de remodelado óseo en la mujer posmenopáusica reciente: estudio longitudinal a 2 años.

BACKGROUND AND OBJECTIVE: Many studies have been performed on the ability of bone turnover markers (BTM) for the prediction of bone loss and to assess the correlation of BTM with bone mineral density (BMD). However, the results from these studies have been mixed. The aim of this study was to assess the usefulness of BTM to predict bone loss and to analize the correlation of BTM with BMD in early postmenopausal women. SUBJECTS AND METHOD: 183 healthy women, aged 50 to 55 years, with natural menopause of 6 to 36 months were randomly selected. We measured bone alkaline phosphatase (BALP), intact osteocalcine (OC) and C-telopeptide (sCTx) in serum, and calcium, deoxipiridinoline (DPD) and N-telopeptide (NTx) in urine. Bone densitometry of the spine (L(2)-L(4)) was performed at the start of the study and two years later. Student t test, ANOVA, chi2 test and ROC curves were used for the statistical analysis. RESULTS: Bone markers, mainly OC and CTx, correlated with BMD and discriminated osteoporosis, osteopenia and normal bone mass (p < 0.001). According to the ROC curves, OC had a sensitivity of 77.8% and specificity of 80.6% for the diagnosis of osteoporosis and sCTx, 83.3% and 74.5%, respectively. Regarding the relation to bone loss, only sCTx showed difference between the lowest and the highest quartile (p = 0.042), but we did not find an association between high turnover and fast bone losers. CONCLUSIONS: Bone markers, mainly OC and sCTx, are useful for identification of osteoporotic and osteopenic early postmenopausal women. However, regarding the bone loss, only CTx has a weak predictive value.