Abstract: A silicon photomultiplier (SiPM) is disclosed. The SiPM includes a plurality of microcells coupled to a summation node of the SiPM. Each of the plurality of microcells comprises a single-photon avalanche diode and a passive quenching device coupled in series with the single-photon avalanche diode. Each of the plurality of microcells also comprises a current mirror configured to generate a microcell output current based on a current from the single-photon avalanche diode.

Abstract: The current invention relates to a peritoneal dialysis filter device, which comprises a housing comprising a first port and a second port, and a hollow fibre membrane formed from hollow hydrophilic fibres within the housing. When in use, a dialysate from a subject enters the filter device through the first port and exits via the second port in an outflow direction, and a regenerated dialysate from a sorbent system enters the filter device through the second port and exits via the first port in an inflow direction. Also disclosed herein is a peritoneal dialysis system comprising said filter device, a method for controlling dialysate flow in a peritoneal dialysis system, and a haemodialysis device.

Abstract: Disclosed herein is a method of removing fluid from a subject, using the steps of (i) administering a first hypertonic solution comprising a sugar-based osmotic agent to a peritoneal cavity in the subject; (ii) allowing water from the subject to pass into the peritoneal cavity by osmosis, thereby forming a second hypertonic solution within the peritoneal cavity, the second hypertonic solution having a lower concentration of the sugar-based osmotic agent than the first hypertonic solution; (iii) withdrawing a portion of the second hypertonic solution from the peritoneal cavity and combining the withdrawn second hypertonic solution with a sugar concentrate to form a third hypertonic solution; (iv) administering the third hypertonic solution to the peritoneal cavity to form a fourth hypertonic solution within the peritoneal cavity by mixing of the second and third hypertonic solutions; and (v) repeating steps (ii) to (iv) for a desired treatment time.

Abstract: An example system for parsing and transforming input data that includes processing circuitry and memory, the memory configured to store the input data. The processing circuitry is configured to determine a first delimiter in the input data. The processing circuitry is configured to determine a plurality of second delimiter hypotheses and parse the input data according to the first delimiter and the plurality of second delimiter hypotheses to generate a plurality of tables that are each associated with a respective one of the plurality of second delimiter hypotheses. The processing circuitry is configured to determine a respective consistency score for each of the plurality of tables and select a table from among the plurality of tables based on the respective consistency score associated with the table. The processing circuitry is configured to format the input data based on the selected table to generate formatted data and output the formatted data.

Abstract: Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for retrieving a subgraph that is used to generate one or more answer outputs responsive to an input query by: (i) generating one or more context embeddings that are associated with an input query, (ii) identifying one or more candidate node paths and one or more node relations based on a knowledge graph, (iii) identifying, using a predictive machine learning model, one or more context-relationship rankings based on the one or more candidate node paths, the one or more node relations, and the one or more context embeddings, and (iv) generating one or more subgraph data objects based on the one or more context-relationship rankings.

Abstract: Various embodiments of the present disclosure provide an end-to-end multi-modal processing pipeline for improving computer comprehension of multi-modal documents. The techniques include extracting embedded media segments from the multi-modal document and identifying semantic section entities based on text segments within the document. The techniques include generating a multi-modal section embedding for each of the semantic section entities that fuses insights from both text and embedded media segments of the multi-modal document. The techniques include generating a multi-modal unstructured rule based on the multi-modal section embedding and then generating a multi-modal structured rule from the multi-modal unstructured rule. The performance of various prediction-based actions may be initiated based on the multi-modal structured rule.

Abstract: Various embodiments of the present disclosure provide machine learning architectures and data processing techniques for improving computer-based text comprehension. The techniques may include identifying a plurality of data entity tokens from a target section of a multi-section natural language document and generating, using an embedding layer of a semantic chunking model, a text span embedding for a text span of the target section. The techniques may include leveraging the semantic chunking model to generate an attended span representation for the text span based on the text span embedding and the plurality of data entity tokens. The techniques may include identifying an entity topic that corresponds to the text span based on the attended span representation and, responsive to an identification of the entity topic, generating a subgraph data object for a knowledge graph using the text span.

Abstract: Sorbent cartridges having an improved shelf life comprising multiple layers of sorbent materials wherein moisture levels in the multiple layers of sorbent materials are controlled, and wherein a first layer of the sorbent cartridge comprises activated carbon and a second layer in direct contact with the first layer comprises one or both of hydrous zirconium oxide and zirconium phosphate.

Abstract: Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for (i) generating document-topic-entity relationship features that are associated with a plurality of topics, a plurality of entities, and a plurality of documents, (ii) generating knowledge graph data objects based on the document-topic-entity relationship features, (iii) generating prompt elements based on a query input, the prompt elements comprising (a) context data associated with one or more query topics, one or more query entities, or one or more query documents and (b) the knowledge graph data objects, (iv) generating, using a natural language processing machine learning model, one or more subgraph data objects based on the prompt elements, and (v) providing, one or more answer outputs based on the one or more subgraph data objects.

Abstract: Disclosed herein is a method of peritoneal dialysis, the method comprising the steps of: (i) administering to a subject a first hypertonic solution comprising a sugar to a peritoneal cavity in the subject, followed by; (ii) a tidal therapy phase and then a dwell phase; or a dwell phase and then a tidal therapy phase.

Abstract: Disclosed herein is a material for use in sorbent-based dialysis, the material comprising: acidic and/or neutral cation exchange particles; alkaline anion exchange particles; and one or more of an alkali metal carbonate, a water insoluble alkaline earth metal carbonate, and a water insoluble polymeric ammonium carbonate. Also disclosed herein are uses of said material and its preparation.

Abstract: An example system for parsing and transforming input data that includes processing circuitry and memory, the memory configured to store the input data. The processing circuitry is configured to determine a first delimiter in the input data. The processing circuitry is configured to determine a plurality of second delimiter hypotheses and parse the input data according to the first delimiter and the plurality of second delimiter hypotheses to generate a plurality of tables that are each associated with a respective one of the plurality of second delimiter hypotheses. The processing circuitry is configured to determine a respective consistency score for each of the plurality of tables and select a table from among the plurality of tables based on the respective consistency score associated with the table. The processing circuitry is configured to format the input data based on the selected table to generate formatted data and output the formatted data.

Abstract: Various embodiments of the present disclosure provide machine learning techniques for transforming disparate, third-party datasets to canonical representations. The techniques include generating, using a machine learning prediction model, a canonical representation for an input dataset. The machine learning prediction model is previously trained using permutative input embeddings for a training dataset based on canonical data entity features, such that each permutative input embedding corresponds to a different sequence of the canonical data entity features. The permutative input embeddings are leveraged to generate a latent representation for the training dataset. The latent representation is combined with a canonical data map to generate an alignment vector, which is refined to generate an output vector for the input dataset. The machine learning prediction model is trained using a model loss generated based on a comparison of the output vector with a corresponding labeled vector.

Abstract: Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for disambiguating data fields mapped to a plurality of data tables according to a common data model by generating disambiguation embeddings based on a matrix representation of the common data model and one or more logical data type weights, generating a plurality of input embedding vectors for one or more prediction inputs based on the disambiguation embeddings, generating a plurality of prediction vectors based on the plurality of input embedding vectors, and assigning one or more select data fields to respective one or more candidate data tables based on the plurality of prediction vectors.

Abstract: Forecasting solutions including customization of raw data using uncertainty coefficient and using ensemble neural network architecture. The raw data is customized by cleaning and augmenting to obtain a processed dataset that is non-discreet and continuous, and; the ensemble neural network architecture is customized to include plurality of dependent and independent features to obtain ensembled weights from ensemble recurrent neural network (RNN) type architecture, a one versus rest ensemble RNN architecture and a forest of ensemble, to obtain an appropriate forecasting model that includes dynamically adaptive weights from ground truth along with the ensembled weights to create a final weighted output such that the final weighted output/forecast result has more accuracy and reduced false positives. The present invention allows for feedback mechanism from disruptive forecasting results if any from query module to go back to training module that enhances the accuracy of the next result without re-training.

Abstract: A system and method for classification of spend data wherein the system comprises a user computer system, a processing unit, a communication interface, a first input receiving component, a second input receiving component, and a spend classification module further comprising a sentence tokenizer, a word tokenizer, a co-reference tagger, at least one language dictionary, and at least one standard taxonomy and/or custom taxonomy, a keyword sense tagger, and a sense scorer, such that the sense scorer further includes a category normalizer matrix, a category summarizer matrix and a heuristic learning matrix; and wherein the method comprises the steps of receiving a dataset of spend data from the user, transmitting the dataset to the spend data classification module, processing of the dataset by the spend data classification module, receiving a query term from the user, mapping the query term, and displaying the data so processed to the user.

Abstract: The current invention relates to a peritoneal dialysis filter device, which comprises a housing comprising a first port and a second port, and a hollow fibre membrane formed from hollow hydrophilic fibres within the housing. When in use, a dialysate from a subject enters the filter device through the first port and exits via the second port in an outflow direction, and a regenerated dialysate from a sorbent system enters the filter device through the second port and exits via the first port in an inflow direction. Also disclosed herein is a peritoneal dialysis system comprising said filter device, a method for controlling dialysate flow in a peritoneal dialysis system, and a haemodialysis device.

Abstract: Methods of preventing or treating elevated pulmonary vascular pressure or exercise-induced pulmonary hemorrhage in mammals are provided, the methods comprise administering compositions comprising type V phosphodiesterase inhibitors and an organic base (e.g., meglumine) to the mammal. Compositions, kits and methods of making type V phosphodiesterase inhibitor are also provided. In one embodiment, the composition comprises E-4021, which is sodium 1-[6-chloro-4-(3,4-methylenedioxybenzyl)-aminoquinazolin-2-yl]piperidine-4-carboxylate sesquihydrate and meglumine.