Correction: The BioRef Infrastructure, a Framework for Real-Time, Federated, Privacy-Preserving, and Personalized Reference Intervals: Design, Development, and Application.

[This corrects the article DOI: 10.2196/47254.].

The BioRef Infrastructure, a Framework for Real-Time, Federated, Privacy-Preserving, and Personalized Reference Intervals: Design, Development, and Application.

BACKGROUND: Reference intervals (RIs) for patient test results are in standard use across many medical disciplines, allowing physicians to identify measurements indicating potentially pathological states with relative ease. The process of inferring cohort-specific RIs is, however, often ignored because of the high costs and cumbersome efforts associated with it. Sophisticated analysis tools are required to automatically infer relevant and locally specific RIs directly from routine laboratory data. These tools would effectively connect clinical laboratory databases to physicians and provide personalized target ranges for the respective cohort population. OBJECTIVE: This study aims to describe the BioRef infrastructure, a multicentric governance and IT framework for the estimation and assessment of patient group-specific RIs from routine clinical laboratory data using an innovative decentralized data-sharing approach and a sophisticated, clinically oriented graphical user interface for data analysis. METHODS: A common governance agreement and interoperability standards have been established, allowing the harmonization of multidimensional laboratory measurements from multiple clinical databases into a unified "big data" resource. International coding systems, such as the International Classification of Diseases, Tenth Revision (ICD-10); unique identifiers for medical devices from the Global Unique Device Identification Database; type identifiers from the Global Medical Device Nomenclature; and a universal transfer logic, such as the Resource Description Framework (RDF), are used to align the routine laboratory data of each data provider for use within the BioRef framework. With a decentralized data-sharing approach, the BioRef data can be evaluated by end users from each cohort site following a strict "no copy, no move" principle, that is, only data aggregates for the intercohort analysis of target ranges are exchanged. RESULTS: The TI4Health distributed and secure analytics system was used to implement the proposed federated and privacy-preserving approach and comply with the limitations applied to sensitive patient data. Under the BioRef interoperability consensus, clinical partners enable the computation of RIs via the TI4Health graphical user interface for query without exposing the underlying raw data. The interface was developed for use by physicians and clinical laboratory specialists and allows intuitive and interactive data stratification by patient factors (age, sex, and personal medical history) as well as laboratory analysis determinants (device, analyzer, and test kit identifier). This consolidated effort enables the creation of extremely detailed and patient group-specific queries, allowing the generation of individualized, covariate-adjusted RIs on the fly. CONCLUSIONS: With the BioRef-TI4Health infrastructure, a framework for clinical physicians and researchers to define precise RIs immediately in a convenient, privacy-preserving, and reproducible manner has been implemented, promoting a vital part of practicing precision medicine while streamlining compliance and avoiding transfers of raw patient data. This new approach can provide a crucial update on RIs and improve patient care for personalized medicine.

Big Data in Laboratory Medicine-FAIR Quality for AI?

Laboratory medicine is a digital science. Every large hospital produces a wealth of data each day-from simple numerical results from, e.g., sodium measurements to highly complex output of "-omics" analyses, as well as quality control results and metadata. Processing, connecting, storing, and ordering extensive parts of these individual data requires Big Data techniques. Whereas novel technologies such as artificial intelligence and machine learning have exciting application for the augmentation of laboratory medicine, the Big Data concept remains fundamental for any sophisticated data analysis in large databases. To make laboratory medicine data optimally usable for clinical and research purposes, they need to be FAIR: findable, accessible, interoperable, and reusable. This can be achieved, for example, by automated recording, connection of devices, efficient ETL (Extract, Transform, Load) processes, careful data governance, and modern data security solutions. Enriched with clinical data, laboratory medicine data allow a gain in pathophysiological insights, can improve patient care, or can be used to develop reference intervals for diagnostic purposes. Nevertheless, Big Data in laboratory medicine do not come without challenges: the growing number of analyses and data derived from them is a demanding task to be taken care of. Laboratory medicine experts are and will be needed to drive this development, take an active role in the ongoing digitalization, and provide guidance for their clinical colleagues engaging with the laboratory data in research.

Machine Learning Prediction of Hypoglycemia and Hyperglycemia From Electronic Health Records: Algorithm Development and Validation.

BACKGROUND: Acute blood glucose (BG) decompensations (hypoglycemia and hyperglycemia) represent a frequent and significant risk for inpatients and adversely affect patient outcomes and safety. The increasing need for BG management in inpatients poses a high demand on clinical staff and health care systems in addition. OBJECTIVE: This study aimed to generate a broadly applicable multiclass classification model for predicting BG decompensation events from patients' electronic health records to indicate where adjustments in patient monitoring and therapeutic interventions are required. This should allow for taking proactive measures before BG levels are derailed. METHODS: A retrospective cohort study was conducted on patients who were hospitalized at a tertiary hospital in Bern, Switzerland. Using patient details and routine data from electronic health records, a multiclass prediction model for BG decompensation events (<3.9 mmol/L [hypoglycemia] or >10, >13.9, or >16.7 mmol/L [representing different degrees of hyperglycemia]) was generated based on a second-level ensemble of gradient-boosted binary trees. RESULTS: A total of 63,579 hospital admissions of 38,250 patients were included in this study. The multiclass prediction model reached specificities of 93.7%, 98.9%, and 93.9% and sensitivities of 67.1%, 59%, and 63.6% for the main categories of interest, which were nondecompensated cases, hypoglycemia, or hyperglycemia, respectively. The median prediction horizon was 7 hours and 4 hours for hypoglycemia and hyperglycemia, respectively. CONCLUSIONS: Electronic health records have the potential to reliably predict all types of BG decompensation. Readily available patient details and routine laboratory data can support the decisions for proactive interventions and thus help to reduce the detrimental health effects of hypoglycemia and hyperglycemia.

A Sam68-dependent alternative splicing program shapes postsynaptic protein complexes.

Alternative splicing is one of the key mechanisms to increase the diversity of cellular transcriptomes, thereby expanding the coding capacity of the genome. This diversity is of particular importance in the nervous system with its elaborated cellular networks. Sam68, a member of the Signal Transduction Associated RNA-binding (STAR) family of RNA-binding proteins, is expressed in the developing and mature nervous system but its neuronal functions are poorly understood. Here, we perform genome-wide mapping of the Sam68-dependent alternative splicing program in mice. We find that Sam68 is required for the regulation of a set of alternative splicing events in pre-mRNAs encoding several postsynaptic scaffolding molecules that are central to the function of GABAergic and glutamatergic synapses. These components include Collybistin (Arhgef9), Gephyrin (Gphn), and Densin-180 (Lrrc7). Sam68-regulated Lrrc7 variants engage in differential protein interactions with signalling proteins, thus, highlighting a contribution of the Sam68 splicing program to shaping synaptic complexes. These findings suggest an important role for Sam68-dependent alternative splicing in the regulation of synapses in the central nervous system.

Neuronal cell type-specific alternative splicing is regulated by the KH domain protein SLM1.

The unique functional properties and molecular identity of neuronal cell populations rely on cell type-specific gene expression programs. Alternative splicing represents a powerful mechanism for expanding the capacity of genomes to generate molecular diversity. Neuronal cells exhibit particularly extensive alternative splicing regulation. We report a highly selective expression of the KH domain-containing splicing regulators SLM1 and SLM2 in the mouse brain. Conditional ablation of SLM1 resulted in a severe defect in the neuronal isoform content of the polymorphic synaptic receptors neurexin-1, -2, and -3. Thus, cell type-specific expression of SLM1 provides a mechanism for shaping the molecular repertoires of synaptic adhesion molecules in neuronal populations in vivo.

Growth cone MKK7 mRNA targeting regulates MAP1b-dependent microtubule bundling to control neurite elongation.

Local mRNA translation in neurons has been mostly studied during axon guidance and synapse formation but not during initial neurite outgrowth. We performed a genome-wide screen for neurite-enriched mRNAs and identified an mRNA that encodes mitogen-activated protein kinase kinase 7 (MKK7), a MAP kinase kinase (MAPKK) for Jun kinase (JNK). We show that MKK7 mRNA localizes to the growth cone where it has the potential to be translated. MKK7 is then specifically phosphorylated in the neurite shaft, where it is part of a MAP kinase signaling module consisting of dual leucine zipper kinase (DLK), MKK7, and JNK1. This triggers Map1b phosphorylation to regulate microtubule bundling leading to neurite elongation. We propose a model in which MKK7 mRNA localization and translation in the growth cone allows for a mechanism to position JNK signaling in the neurite shaft and to specifically link it to regulation of microtubule bundling. At the same time, this uncouples activated JNK from its functions relevant to nuclear translocation and transcriptional activation.

SAM68 regulates neuronal activity-dependent alternative splicing of neurexin-1.

The assembly of synapses and neuronal circuits relies on an array of molecular recognition events and their modification by neuronal activity. Neurexins are a highly polymorphic family of synaptic receptors diversified by extensive alternative splicing. Neurexin variants exhibit distinct isoform-specific biochemical interactions and synapse assembly functions, but the mechanisms governing splice isoform choice are not understood. We demonstrate that Nrxn1 alternative splicing is temporally and spatially controlled in the mouse brain. Neuronal activity triggers a shift in Nrxn1 splice isoform choice via calcium/calmodulin-dependent kinase IV signaling. Activity-dependent alternative splicing of Nrxn1 requires the KH-domain RNA-binding protein SAM68 that associates with RNA response elements in the Nrxn1 pre-mRNA. Our findings uncover SAM68 as a key regulator of dynamic control of Nrxn1 molecular diversity and activity-dependent alternative splicing in the central nervous system.

The role of the cytoskeleton during neuronal polarization.

The formation of an axon and dendrites, neuronal polarization, is a prerequisite for neurons to integrate and propagate information within the brain. During the past years progress has been made toward understanding the initial stage of neuronal polarization, axon formation. First, the physiological role of some candidate regulators of neuronal polarity has been affirmed, including Sad kinases, the Rho-GTPase Cdc42, and the actin regulators Ena/VASP proteins. Second, recent studies have revealed microtubule stabilization as a mechanism complementary to actin dynamics underlying neuronal polarization. Moreover, stable microtubules in the axon may form a landmark to confer identity to the axon. This review highlights the recent advances in understanding the intracellular mechanisms underlying neuronal polarization and discusses them in the context of putative cytoskeletal effectors.

Microtubule stabilization specifies initial neuronal polarization.

Axon formation is the initial step in establishing neuronal polarity. We examine here the role of microtubule dynamics in neuronal polarization using hippocampal neurons in culture. We see increased microtubule stability along the shaft in a single neurite before axon formation and in the axon of morphologically polarized cells. Loss of polarity or formation of multiple axons after manipulation of neuronal polarity regulators, synapses of amphids defective (SAD) kinases, and glycogen synthase kinase-3beta correlates with characteristic changes in microtubule turnover. Consistently, changing the microtubule dynamics is sufficient to alter neuronal polarization. Application of low doses of the microtubule-destabilizing drug nocodazole selectively reduces the formation of future dendrites. Conversely, low doses of the microtubule-stabilizing drug taxol shift polymerizing microtubules from neurite shafts to process tips and lead to the formation of multiple axons. Finally, local stabilization of microtubules using a photoactivatable analogue of taxol induces axon formation from the activated area. Thus, local microtubule stabilization in one neurite is a physiological signal specifying neuronal polarization.