Machine learning in diagnostic support in medical emergency departments.

Diagnosing patients in the medical emergency department is complex and this is expected to increase in many countries due to an ageing population. In this study we investigate the feasibility of training machine learning algorithms to assist physicians handling the complex situation in the medical emergency departments. This is expected to reduce diagnostic errors and improve patient logistics and outcome. We included a total of 9,190 consecutive patient admissions diagnosed and treated in two hospitals in this cohort study. Patients had a biochemical workup including blood and urine analyses on clinical decision totaling 260 analyses. After adding nurse-registered data we trained 19 machine learning algorithms on a random 80% sample of the patients and validated the results on the remaining 20%. We trained algorithms for 19 different patient outcomes including the main outcomes death in 7 (Area under the Curve (AUC) 91.4%) and 30 days (AUC 91.3%) and safe-discharge(AUC 87.3%). The various algorithms obtained areas under the Receiver Operating Characteristics -curves in the range of 71.8-96.3% in the holdout cohort (68.3-98.2% in the training cohort). Performing this list of biochemical analyses at admission also reduced the number of subsequent venipunctures within 24 h from patient admittance by 22%. We have shown that it is possible to develop a list of machine-learning algorithms with high AUC for use in medical emergency departments. Moreover, the study showed that it is possible to reduce the number of venipunctures in this cohort.

Tyrosine and tryptophan in urine as biomarkers for prostate cancer: A validation study.

Prostate cancer (PCa) is a common male malignancy and early diagnosis is crucial for successful treatment. The current study aims to validate results from a pilot study that demonstrated an inverse association between urine tyrosine and tryptophan levels and the severity of PCa. This study comprised a cohort of 97 patients with benign prostatic hyperplasia, 93 patients diagnosed with localized PCa, 75 patients diagnosed with locally advanced PCa, and 68 patients diagnosed with metastatic PCa. The tyrosine and tryptophan levels in the samples were analyzed by liquid chromatography-tandem mass spectrometry (LC-MS/MS) and electrochemical sensors in accordance with the pilot to maintain uniformity for accurately evaluating the data. One-way ANOVA with post Tukey test as well as the Wilcoxon Rank Sum Test were performed. Analyzing 333 patients across PCa stages with consistent methods, we observed no significant differences in tyrosine and tryptophan levels between PCa patients and controls, finally rejecting the use of tyrosine and tryptophan as PCa biomarkers. We did, however, verify the strong correlation between the urinary concentrations of tyrosine and tryptophan found in the pilot study.

Extended interval dosing with ocrelizumab in multiple sclerosis.

BACKGROUND: This study investigates clinical and biomarker differences between standard interval dosing (SID) and extended interval dosing (EID) of ocrelizumab therapy in multiple sclerosis (MS). METHODS: This is a prospective, double-arm, open-label, multi-center study in Denmark. Participants diagnosed with MS on ocrelizumab therapy >12 months were included (n = 184). Clinical, radiological, and blood-based biomarker outcomes were evaluated. MRI disease activity, relapses, worsening of neurostatus, and No Evidence of Disease Activity-3 (NEDA-3) were used as a combined endpoint. RESULTS: Out of 184 participants, 107 participants received EID (58.2%), whereas 77 participants received SID (41.8%). The average extension was 9 weeks with a maximum of 78 weeks. When comparing EID to SID, we found higher levels of B-cells, lower serum concentrations of ocrelizumab, and similar levels of age-adjusted NFL and GFAP in the two groups. No difference in NEDA-3 between EID and SID was demonstrated (hazard ratio: 1.174, p = 0.69). Higher levels of NFL were identified in participants with disease activity. Body mass index correlated with levels of ocrelizumab and B-cells. CONCLUSION: Extending one treatment interval of ocrelizumab on average 9 weeks and up to 78 weeks did not result in clinical, radiological, or biomarker evidence of worsening compared with SID.

Performance Measures and Plasma Biomarker Levels in Patients with Multiple Sclerosis after 14 Days of Fampridine Treatment: An Explorative Study.

Peripheral cytokine levels may serve as biomarkers for treatment response and disease monitoring in patients with multiple sclerosis (pwMS). The objectives were to assess changes in plasma biomarkers in PwMS after 14 days of fampridine treatment and to explore correlations between changes in performance measures and plasma biomarkers. We included 27 PwMS, 14 women and 13 men, aged 52.0 ± 11.6 years, with a disease duration of 17 ± 8.5 years, and an Expanded Disability Status Scale of 6 [IQR 5.0/6.5]. Gait and hand function were assessed using performance tests completed prior to fampridine and after 14 days of treatment. Venous blood was obtained, and chemiluminescence analysis conducted to assess plasma cytokines and neurodegenerative markers. All performance measures demonstrated improvements. Biomarkers showed decreased tumor necrosis factor (TNF) receptor-2 levels. Associations were found between change scores in (i) Six Spot Step Test and Interleukin (IL)-2, IL-8, and IL-17 levels; (ii) timed 25-foot walk and interferon-γ, IL-2, IL-8, TNF-α, and neurofilament light levels, and (iii) 12-Item Multiple Sclerosis Walking Scale and IL-17 levels. The associations may reflect increased MS-related inflammatory activity rather than a fampridine-induced response or that a higher level of inflammation induces a better response to fampridine.

Monitoring performance of clinical artificial intelligence: a scoping review protocol.

OBJECTIVE: The objective of this scoping review is to describe the scope and nature of research on the monitoring of clinical artificial intelligence (AI) systems. The review will identify the various methodologies used to monitor clinical AI, while also mapping the factors that influence the selection of monitoring approaches. INTRODUCTION: AI is being used in clinical decision-making at an increasing rate. While much attention has been directed toward the development and validation of AI for clinical applications, the practical implementation aspects, notably the establishment of rational monitoring/quality assurance systems, has received comparatively limited scientific interest. Given the scarcity of evidence and the heterogeneity of methodologies used in this domain, there is a compelling rationale for conducting a scoping review on this subject. INCLUSION CRITERIA: This scoping review will include any publications that describe systematic, continuous, or repeated initiatives that evaluate or predict clinical performance of AI models with direct implications for the management of patients in any segment of the health care system. METHODS: Publications will be identified through searches of the MEDLINE (Ovid), Embase (Ovid), and Scopus databases. Additionally, backward and forward citation searches, as well as a thorough investigation of gray literature, will be conducted. Title and abstract screening, full-text evaluation, and data extraction will be performed by 2 or more independent reviewers. Data will be extracted using a tool developed by the authors. The results will be presented graphically and narratively. REVIEW REGISTRATION: Open Science Framework https://osf.io/afkrn.

Serum metabolic signatures for Alzheimer's Disease reveal alterations in amino acid composition: a validation study.

INTRODUCTION: Alzheimer's Disease (AD) is complex and novel approaches are urgently needed to aid in diagnosis. Blood is frequently used as a source for biomarkers; however, its complexity prevents proper detection. The analytical power of metabolomics, coupled with statistical tools, can assist in reducing this complexity. OBJECTIVES: Thus, we sought to validate a previously proposed panel of metabolic blood-based biomarkers for AD and expand our understanding of the pathological mechanisms involved in AD that are reflected in the blood. METHODS: In the validation cohort serum and plasma were collected from 25 AD patients and 25 healthy controls. Serum was analysed for metabolites using nuclear magnetic resonance (NMR) spectroscopy, while plasma was tested for markers of neuronal damage and AD hallmark proteins using single molecule array (SIMOA). RESULTS: The diagnostic performance of the metabolite biomarker panel was confirmed using sparse-partial least squares discriminant analysis (sPLS-DA) with an area under the curve (AUC) of 0.73 (95% confidence interval: 0.59-0.87). Pyruvic acid and valine were consistently reduced in the discovery and validation cohorts. Pathway analysis of significantly altered metabolites in the validation set revealed that they are involved in branched-chain amino acids (BCAAs) and energy metabolism (glycolysis and gluconeogenesis). Additionally, strong positive correlations were observed for valine and isoleucine between cerebrospinal fluid p-tau and t-tau. CONCLUSIONS: Our proposed panel of metabolites was successfully validated using a combined approach of NMR and sPLS-DA. It was discovered that cognitive-impairment-related metabolites belong to BCAAs and are involved in energy metabolism.

Cytochrome P450 activity in rheumatoid arthritis patients during continuous IL-6 receptor antagonist therapy.

BACKGROUND: Inflammation suppresses cytochrome P450 (CYP) enzyme activity, and single-dose interleukin 6 receptor antagonists (anti-IL-6R) reverse this effect. Here, we assess the impact of continuous anti-IL-6R therapy in patients with rheumatoid arthritis. METHODS: In a clinical pharmacokinetic trial, the Basel cocktail was administered before and after 3 and 12 weeks of anti-IL-6R therapy to assess CYP enzyme activity (registered in the ClinicalTrials.gov database (identifier NCT04842981) on April 13th, 2021). In a retrospective study, the 4ß-hydroxycholesterol/cholesterol ratio was measured as a biomarker for CYP3A4 activity before and after 3 and 6 months of anti-IL-6R therapy. The control group was patients initiating a tumor necrosis factor alfa (TNF-α) inhibitor. RESULTS: In the clinical pharmacokinetic trial (n = 3), midazolam metabolic ratio (CYP3A4) was inconclusive due to the limited sample size. Midazolam AUC and Cmax indicate a weak impact on CYP3A4 activity after 3 weeks of anti-IL-6R therapy compared to baseline (AUC geometric mean ratio (GMR): 0.80, 95% CI: 0.64-0.99 and Cmax GMR: 0.58, 95% CI: 0.37-0.91), which returns to baseline levels after 12 weeks of therapy (AUC GMR 1.02, 95% CI: 0.72-1.46 and Cmax GMR 1.03, 95% CI 0.72-1.47). No effect on the 4ß-hydroxycholesterol/cholesterol ratio was observed in the retrospective study. CONCLUSION: Based on sparse data from three patients, continuous anti-IL-6R therapy seems to cause an acute but transient increase in CYP3A4 activity in rheumatoid arthritis patients, which may be due to a normalization of the inflammation-suppressed CYP activity. Further studies are warranted to understand the mechanism behind this putative transient effect. Trial registration Registered in the ClinicalTrials.gov database (identifier NCT04842981) on April 13th, 2021.

Warming Prior to Heel Stick: Blood Sample Quality and Infant Comfort-A Randomized Controlled Trial.

BACKGROUND: Capillary blood sampling (heel stick) in infants is commonly performed in neonatal care units. Before the procedure, warming the infant's heel is often a customary practice, but no consensus exists on the most effective heel-warming method. PURPOSE: To compare the effects of routinely used warming methods (glove, gel pack, or blanket) applied prior to heel stick on blood sample quality and infant's comfort. METHODS: This prospective, double-blind, randomized controlled trial conducted in the neonatal intensive care unit included infants (postmenstrual age of ≥28 + 0 weeks and ≤43 + 6 weeks) who were computer-randomized to 1 of 3 warming methods.The primary outcome was blood flow velocity at sampling. Secondary outcomes were hemolysis index, infant COMFORTneo score, and frequency of postprocedure skin injuries. In addition, irrespective of the warming method used, the correlation between heel skin temperature and postprocedure heel skin injury was analyzed. RESULTS: A total of 176 heel warmings were successfully randomized, and 173 were analyzed. Despite a significant difference in obtained heel skin temperature after warming between the 3 warming methods ( P = .001), no difference in blood flow velocity ( P = .91), hemolysis index ( P = .99), or COMFORTneo score ( P = .76) was found. Baseline skin temperatures above 37.0°C were associated with higher incidences of skin injury, and skin temperatures after warming were significantly higher in skin-injured heels ( P = .038). IMPLICATIONS FOR PRACTICE AND RESEARCH: All 3 warming methods had similar effects on blood sample quality and infant's comfort. However, excessive warming of the heel should be avoided to prevent skin injuries.

Consultation on UTUC II Stockholm 2022: diagnostic and prognostic methods-what's around the corner?

PURPOSE: To map current literature and provide an overview of upcoming future diagnostic and prognostic methods for upper tract urothelial carcinoma (UTUC), including translational medical science. METHODS: A scoping review approach was applied to search the literature. Based on the published literature, and the experts own experience and opinions consensus was reached through discussions at the meeting Consultation on UTUC II in Stockholm, September 2022. RESULTS: The gene mutational profile of UTUC correlates with stage, grade, prognosis, and response to different therapeutic strategies. Analysis of pathway proteins downstream of known pathogenic mutations might be an alternative approach. Liquid biopsies of cell-free DNA may detect UTUC with a higher sensitivity and specificity than urinary cytology. Extracellular vesicles from tumour cells can be detected in urine and may be used to identify the location of the urothelial carcinoma in the urinary tract. 3D microscopy of UTUC samples may add information in the analysis of tumour stage. Chemokines and chemokine receptors were linked to overall survival and responsiveness to neoadjuvant chemotherapy in muscle-invasive bladder cancer, which is potentially also of interest in UTUC. CONCLUSION: Current diagnostic methods for UTUC have shortcomings, especially concerning prognostication, which is important for personalized treatment decisions. There are several upcoming methods that may be of interest for UTUC. Most have been studied for urothelial carcinoma of the bladder, and it is important to keep in mind that UTUC is a different entity and not all methods are adaptable or applicable to UTUC.

Identification of early stage and metastatic prostate cancer using electrochemical detection of beta-2-microglobulin in urine samples from patients.

To improve prostate cancer (PCa) diagnosis, it is imperative to identify novel biomarkers and establish effective screening techniques. Here, we introduce electrochemical biosensing of ß-2-Microglobulin (ß2M) in urine as a potential diagnostic tool for PCa. The immunosensor is composed of a screen-printed graphene electrode coated with anti ß2M antibodies. The sensor is capable of detecting the protein directly in urine without any sample pretreatment within 45 min including sample incubation and a lower limit of detection of 204 µg/L. The sensor demonstrated a significant difference in the ß2M-creatinine ratio in urine between control and both local- and metastatic PCa (mPCa) (P = 0.0302 and P = 0.0078 respectively), and between local- and mPCa (P = 0.0302). This first example of electrochemical sensing of ß2M for the diagnosis of PCa may set the stage for an affordable, on-site screening technique for PCa.

Phase II trial of delta-tocotrienol in neoadjuvant breast cancer with evaluation of treatment response using ctDNA.

Neoadjuvant treatment of breast cancer is applied to an increasing extent, but treatment response varies and side effects pose a challenge. The vitamin E isoform delta-tocotrienol might enhance the efficacy of chemotherapy and reduce the risk of side effects. The aim of this study was to investigate the clinical effect of delta-tocotrienol combined with standard neoadjuvant treatment and the possible association between detectable circulating tumor DNA (ctDNA) during and after neoadjuvant treatment with pathological treatment response. This open-label, randomized phase II trial included 80 women with newly diagnosed, histologically verified breast cancer randomized to standard neoadjuvant treatment alone or in combination with delta-tocotrienol. There was no difference in the response rate or frequency of serious adverse events between the two arms. We developed a multiplex digital droplet polymerase chain reaction (ddPCR) assay for the detection of ctDNA in breast cancer patients that targets a combination of two methylations specific for breast tissue (LMX1B and ZNF296) and one cancer specific methylation (HOXA9). The sensitivity of the assay increased when the cancer specific marker was combined with the ones specific to breast tissue (p < 0.001). The results did not show any association between ctDNA status and pathological treatment response, neither at midterm nor before surgery.

A variability in response of osteoclasts to zoledronic acid is mediated by smoking-associated modification in the DNA methylome.

BACKGROUND: Clinical trials have shown zoledronic acid as a potent bisphosphonate in preventing bone loss, but with varying potency between patients. Human osteoclasts ex vivo reportedly displayed a variable sensitivity to zoledronic acid > 200-fold, determined by the half-maximal inhibitory concentration (IC50), with cigarette smoking as one of the reported contributors to this variation. To reveal the molecular basis of the smoking-mediated variation on treatment sensitivity, we performed a DNA methylome profiling on whole blood cells from 34 healthy female blood donors. Multiple regression models were fitted to associate DNA methylation with ex vivo determined IC50 values, smoking, and their interaction adjusting for age and cell compositions. RESULTS: We identified 59 CpGs displaying genome-wide significance (p < 1e-08) with a false discovery rate (FDR) < 0.05 for the smoking-dependent association with IC50. Among them, 3 CpGs have p < 1e-08 and FDR < 2e-03. By comparing with genome-wide association studies, 15 significant CpGs were locally enriched (within < 50,000 bp) by SNPs associated with bone and body size measures. Furthermore, through a replication analysis using data from a published multi-omics association study on bone mineral density (BMD), we could validate that 29 out of the 59 CpGs were in close vicinity of genomic sites significantly associated with BMD. Gene Ontology (GO) analysis on genes linked to the 59 CpGs displaying smoking-dependent association with IC50, detected 18 significant GO terms including cation:cation antiporter activity, extracellular matrix conferring tensile strength, ligand-gated ion channel activity, etc. CONCLUSIONS: Our results suggest that smoking mediates individual sensitivity to zoledronic acid treatment through epigenetic regulation. Our novel findings could have important clinical implications since DNA methylation analysis may enable personalized zoledronic acid treatment.

Initiation of glucose-lowering drugs reduces the anticoagulant effect of warfarin-But not through altered drug metabolism in patients with type 2 diabetes.

AIMS: Drug metabolism might be altered in patients with type 2 diabetes. We aimed to evaluate if initiation of glucose-lowering drugs impacts warfarin efficacy and drug metabolism. METHODS: First, we conducted a register-based self-controlled cohort study on Danish and Scottish warfarin users. Warfarin efficacy (international normalized ratio [INR]) was compared before and after initiation of glucose-lowering drugs. Second, we conducted a clinical pharmacokinetic trial comprising treatment-naïve type 2 diabetes patients. Patients ingested probe drugs for drug-metabolizing enzymes (the Basel Cocktail) before initiating glucose-lowering treatment, and after 3 and 12 weeks of treatment. Drug metabolism, glycaemic control, and inflammation were assessed on each visit. RESULTS: In the Danish and Scottish cohorts (n = 982 and n = 44, respectively), initiating glucose-lowering drugs reduced warfarin efficacy. INR decreased from 2.47 to 2.21 in the Danish cohort (mean difference -0.26; 95% CI -0.35; -0.17) and from 2.33 to 2.13 in the Scottish cohort (-0.21; 95% CI -0.52; 0.11) after initiation of glucose-lowering treatment. This impact on INR was more pronounced among individuals with stronger effects of glucose-lowering treatment. In the clinical pharmacokinetic trial (n = 10), initiating metformin did not affect drug metabolism after 3 weeks (geometric mean ratio of CYP3A metabolic ratio: 1.12 [95% CI: 0.95; 1.32]) or 12 weeks of metformin treatment. Glycaemic control improved during treatment, while inflammation remained low and unchanged during treatment. CONCLUSIONS: In conclusion, initiation of glucose-lowering drugs among chronic warfarin users seems associated with a reduction in INR, particularly among individuals with a large decrease in HbA1c . This effect seems unrelated to CYP enzyme activity and warfarin drug metabolism.

Neurofilament light chain as a biomarker of axonal damage in sensory neurons and paclitaxel-induced peripheral neuropathy in patients with ovarian cancer.

ABSTRACT: Paclitaxel-induced peripheral neuropathy (PIPN) is a barrier to effective cancer treatment and impacts quality of life among patients with cancer. We used a translational approach to assess the utility of neurofilament light chain (NFL) as a biomarker of PIPN in a human cell model and in patients with ovarian cancer. We measured NFL in medium from human induced pluripotent stem cell-derived sensory neurons (iPSC-SNs) exposed to paclitaxel. Serum NFL (sNFL) levels were quantified in 190 patients with ovarian cancer receiving paclitaxel/carboplatin chemotherapy at baseline and after each of the following 2 or 6 cycles. Adverse outcomes related to PIPN were retrospectively obtained, and Cox regression model was performed with different sNFL cut-offs after first cycle. The apparent elimination half-life of sNFL was estimated in patients who discontinued paclitaxel. Paclitaxel neurotoxicity in iPSC-SNs was accompanied by NFL release in a concentration-dependent manner ( P < 0.001, analysis of variance). Serum NFL levels increased substantially in patients during paclitaxel/carboplatin chemotherapy with considerable interindividual variability. Patients with sNFL >150 pg/mL after first cycle had increased risk to discontinue paclitaxel early (unadjusted HR: 2.47 [95% CI 1.16-5.22], adjusted HR: 2.25 [95% CI: 0.88-5.79]). Similar trends were shown for risk of severe PIPN and paclitaxel dose reduction because of PIPN. The median elimination half-life of sNFL was 43 days (IQR 27-82 days). Neurofilament light chain constitutes an objective biomarker of neurotoxicity in iPSC-SNs and in ovarian cancer patients with high sNFL predicting PIPN-related adverse outcomes. If prospectively validated, NFL can be used to study PIPN and may guide clinical decision making and personalize treatment with paclitaxel.

Long-Term Antibody Response against SARS-CoV-2 in Health Care Workers: Effectiveness of Homologous and Heterologous Regimens and Their Relation to Systemic Vaccine-Associated Symptoms.

This prospective study provides data on the long-term humoral immunogenicity of a heterologous off-label vaccine regimen combining the adenoviral-vectored ChAdOx1 nCoV-19 from Astra-Zeneca (ChAd) with the mRNA-1273 vaccine from Moderna (m1273) in comparison with two different homologous mRNA vaccine schedules. Of the 316 COVID-19 naïve adult health care workers (HCW) included to complete a survey on vaccine-associated symptoms (VAS), 197 had received the homologous BNT162b2 mRNA vaccine from Pfizer/BioNTech (BNT/BNT), 76 the homologous m1273/m1273, and 43 the heterologous ChAd/m1273 vaccine regimen. The concentration of antibodies against SARS-CoV-2 spike protein in plasma 5−7 months after the second vaccine dose was higher in the m1273/m1273 and ChAd/m1273 than the BNT/BNT vaccine group. The frequency of systemic VAS after the first vaccine dose was 86% after ChAd compared with 35% and 39% after BNT and m1273, respectively (p < 0.0001), and after the second vaccine dose, the highest (89%) in the m1273/m1273 group (p < 0.001). Individuals with systemic VAS achieved higher levels of antibodies irrespective of vaccine regimen. In conclusion, VAS serve as a strong predictor of long-term humoral immune response, and the heterologous ChAd/m1273 vaccine regimen provides an at least equal long-term humoral immune response compared with the standard vaccine regimens used in Denmark.

Using fecal immunochemical test values below conventional cut-off to individualize colorectal cancer screening.

Background and study aims Of the participants in the Danish screening program, 89.9 % to 92.5 % have fecal immunochemical test (FIT) values < 10 µg/g feces (equivalent to 50 ng hemoglobin/mL buffer). This study aimed to investigate the risk of interval colorectal cancer (CRC) in this group before the next biennial screening round. Patients and methods This cohort study included all citizens from the region of Southern Denmark who participated in the Danish bowel screening program from 2014 trough 2016 and had a FIT value < 10 µg/g feces. Individuals receiving a CRC diagnosis were identified through the national CRC registry, with a follow up of 2 years corresponding to the current screening interval. We also examined the 3-year CRC incidence. Hazard ratios (HRs) were estimated using univariate and multivariate Cox proportional hazard regression models. Results Data from 185,654 citizens presenting with a FIT value < 10 µg/g feces were eligible for analysis. Overall, interval CRC incidence was 0.07 % within 2 years with HRs of 4.16 (95 % confidence interval [CI] 2.67;6.48) and 5.8 (95 % CI 3.34;10.05) for FIT values of 4 to 6.9 µg/g feces and 7 to 9.9 µg/g feces, respectively, compared to those having a FIT value below the limit of quantification of 4 µg/g feces. After 3 years, the overall CRC incidence increased to 0.14 %; however, this was not significant. Conclusions This study demonstrates a positive correlation between FIT value and risk of interval cancer even for very low values. It further suggests that an increase in the screening interval could be reasonable in the low FIT categories.

Correlation between stage of prostate cancer and tyrosine and tryptophan in urine samples measured electrochemically.

Prostate cancer (PCa) is the second most common cancer in men and one of the leading causes of cancer-related deaths. Early detection is the key to successful treatment and provides the greatest chance to cure the patient. Currently, early detection involves screening for prostate-specific antigen levels in blood, which is not a tumor-specific biomarker. There is a critical need to develop clinically useful methods for screening for more reliable biomarkers. Here, we introduce an electrochemical biosensor that measures the concentrations of the amino acids tyrosine and tryptophan, and propose it as a possible diagnostic and prognostic tool for PCa. The limits of detection of tyrosine and tryptophan using the electrochemical sensors were 1.15 and 1.13 µmol/L in 1:10 urine: PBS, respectively. This study is the first to present electrochemical measurements of tyrosine and tryptophan directly in patient urine samples. We demonstrated an inverse correlation between the measured electrochemical signals and the severity of PCa. The most notable observation was a significant difference between controls and metastatic PCa patients (P ≤ 0.001). This observation was further validated using Liquid-Chromatography-Mass Spectrometry. Our data provides the basis for further research with electrochemical measurements of tyrosine and tryptophan as potential biomarkers for PCa.

Using artificial intelligence in a primary care setting to identify patients at risk for cancer: a risk prediction model based on routine laboratory tests.

OBJECTIVES: To evaluate the ability of an artificial intelligence (AI) model to predict the risk of cancer in patients referred from primary care based on routine blood tests. Results obtained with the AI model are compared to results based on logistic regression (LR). METHODS: An analytical profile consisting of 25 predefined routine laboratory blood tests was introduced to general practitioners (GPs) to be used for patients with non-specific symptoms, as an additional tool to identify individuals at increased risk of cancer. Consecutive analytical profiles ordered by GPs from November 29th 2011 until March 1st 2020 were included. AI and LR analysis were performed on data from 6,592 analytical profiles for their ability to detect cancer. Cohort I for model development included 5,224 analytical profiles ordered by GP's from November 29th 2011 until the December 31st 2018, while 1,368 analytical profiles included from January 1st 2019 until March 1st 2020 constituted the "out of time" validation test Cohort II. The main outcome measure was a cancer diagnosis within 90 days. RESULTS: The AI model based on routine laboratory blood tests can provide an easy-to use risk score to predict cancer within 90 days. Results obtained with the AI model were comparable to results from the LR model. In the internal validation Cohort IB, the AI model provided slightly better results than the LR analysis both in terms of the area under the receiver operating characteristics curve (AUC) and PPV, sensitivity/specificity while in the "out of time" validation test Cohort II, the obtained results were comparable. CONCLUSIONS: The AI risk score may be a valuable tool in the clinical decision-making. The score should be further validated to determine its applicability in other populations.

Vitamin K supplementation and arterial calcification in dialysis: results of the double-blind, randomized, placebo-controlled RenaKvit trial.

BACKGROUND: Arterial calcification is associated with cardiovascular mortality in dialysis patients. Active matrix Gla protein (MGP) is a vitamin K-dependent inhibitor of arterial calcification. Elevated plasma concentrations of inactive MGP, i.e. dephosphorylated-uncarboxylated MGP (dp-ucMGP), are prevalent in dialysis patients. MGP inactivity might contribute to arterial calcification. We investigated whether vitamin K supplementation had an effect on arterial calcification in chronic dialysis patients. METHODS: In a 2-year, double-blind, placebo-controlled intervention trial, 48 dialysis patients were randomized to vitamin K [menaquinone-7 (MK-7), 360 µg daily] or placebo. MK-7 in serum and dp-ucMGP in plasma were used to assess vitamin K status. Carotid-femoral pulse wave velocity (cfPWV) and scores of coronary arterial calcification (CAC) and abdominal aortic calcification (AAC) were used to assess arterial calcification. RESULTS: Thirty-seven participants completed Year 1, and 21 completed Year 2. At Year 2, serum MK-7 was 40-fold higher, and plasma dp-ucMGP 40% lower after vitamin K supplementation compared with placebo {mean dp-ucMGP difference: -1380 pmol/L [95% confidence interval (CI) -2029 to -730]}. There was no significant effect of vitamin K supplementation on cfPWV [mean difference at Year 2: 1.2 m/s (95% CI -0.1 to 2.4)]. CAC Agatston score increased significantly in vitamin K supplemented participants, but was not significantly different from placebo [mean difference at Year 2: 664 (95% CI -554 to 1881)]. AAC scores increased in both groups, significantly so within the placebo group at Year 1, but with no significant between-group differences. CONCLUSIONS: Vitamin K supplementation improved vitamin K status, but did not hinder or modify the progression of arterial calcification in dialysis patients.