Moving Biosurveillance Beyond Coded Data Using AI for Symptom Detection From Physician Notes: Retrospective Cohort Study.

BACKGROUND: Real-time surveillance of emerging infectious diseases necessitates a dynamically evolving, computable case definition, which frequently incorporates symptom-related criteria. For symptom detection, both population health monitoring platforms and research initiatives primarily depend on structured data extracted from electronic health records. OBJECTIVE: This study sought to validate and test an artificial intelligence (AI)-based natural language processing (NLP) pipeline for detecting COVID-19 symptoms from physician notes in pediatric patients. We specifically study patients presenting to the emergency department (ED) who can be sentinel cases in an outbreak. METHODS: Subjects in this retrospective cohort study are patients who are 21 years of age and younger, who presented to a pediatric ED at a large academic children's hospital between March 1, 2020, and May 31, 2022. The ED notes for all patients were processed with an NLP pipeline tuned to detect the mention of 11 COVID-19 symptoms based on Centers for Disease Control and Prevention (CDC) criteria. For a gold standard, 3 subject matter experts labeled 226 ED notes and had strong agreement (F1-score=0.986; positive predictive value [PPV]=0.972; and sensitivity=1.0). F1-score, PPV, and sensitivity were used to compare the performance of both NLP and the International Classification of Diseases, 10th Revision (ICD-10) coding to the gold standard chart review. As a formative use case, variations in symptom patterns were measured across SARS-CoV-2 variant eras. RESULTS: There were 85,678 ED encounters during the study period, including 4% (n=3420) with patients with COVID-19. NLP was more accurate at identifying encounters with patients that had any of the COVID-19 symptoms (F1-score=0.796) than ICD-10 codes (F1-score =0.451). NLP accuracy was higher for positive symptoms (sensitivity=0.930) than ICD-10 (sensitivity=0.300). However, ICD-10 accuracy was higher for negative symptoms (specificity=0.994) than NLP (specificity=0.917). Congestion or runny nose showed the highest accuracy difference (NLP: F1-score=0.828 and ICD-10: F1-score=0.042). For encounters with patients with COVID-19, prevalence estimates of each NLP symptom differed across variant eras. Patients with COVID-19 were more likely to have each NLP symptom detected than patients without this disease. Effect sizes (odds ratios) varied across pandemic eras. CONCLUSIONS: This study establishes the value of AI-based NLP as a highly effective tool for real-time COVID-19 symptom detection in pediatric patients, outperforming traditional ICD-10 methods. It also reveals the evolving nature of symptom prevalence across different virus variants, underscoring the need for dynamic, technology-driven approaches in infectious disease surveillance.

Real world performance of the 21st Century Cures Act population-level application programming interface.

OBJECTIVE: To evaluate the real-world performance of the SMART/HL7 Bulk Fast Health Interoperability Resources (FHIR) Access Application Programming Interface (API), developed to enable push button access to electronic health record data on large populations, and required under the 21st Century Cures Act Rule. MATERIALS AND METHODS: We used an open-source Bulk FHIR Testing Suite at 5 healthcare sites from April to September 2023, including 4 hospitals using electronic health records (EHRs) certified for interoperability, and 1 Health Information Exchange (HIE) using a custom, standards-compliant API build. We measured export speeds, data sizes, and completeness across 6 types of FHIR. RESULTS: Among the certified platforms, Oracle Cerner led in speed, managing 5-16 million resources at over 8000 resources/min. Three Epic sites exported a FHIR data subset, achieving 1-12 million resources at 1555-2500 resources/min. Notably, the HIE's custom API outperformed, generating over 141 million resources at 12 000 resources/min. DISCUSSION: The HIE's custom API showcased superior performance, endorsing the effectiveness of SMART/HL7 Bulk FHIR in enabling large-scale data exchange while underlining the need for optimization in existing EHR platforms. Agility and scalability are essential for diverse health, research, and public health use cases. CONCLUSION: To fully realize the interoperability goals of the 21st Century Cures Act, addressing the performance limitations of Bulk FHIR API is critical. It would be beneficial to include performance metrics in both certification and reporting processes.

Cumulus: A federated EHR-based learning system powered by FHIR and AI.

Objective: To address challenges in large-scale electronic health record (EHR) data exchange, we sought to develop, deploy, and test an open source, cloud-hosted app 'listener' that accesses standardized data across the SMART/HL7 Bulk FHIR Access application programming interface (API). Methods: We advance a model for scalable, federated, data sharing and learning. Cumulus software is designed to address key technology and policy desiderata including local utility, control, and administrative simplicity as well as privacy preservation during robust data sharing, and AI for processing unstructured text. Results: Cumulus relies on containerized, cloud-hosted software, installed within a healthcare organization's security envelope. Cumulus accesses EHR data via the Bulk FHIR interface and streamlines automated processing and sharing. The modular design enables use of the latest AI and natural language processing tools and supports provider autonomy and administrative simplicity. In an initial test, Cumulus was deployed across five healthcare systems each partnered with public health. Cumulus output is patient counts which were aggregated into a table stratifying variables of interest to enable population health studies. All code is available open source. A policy stipulating that only aggregate data leave the institution greatly facilitated data sharing agreements. Discussion and Conclusion: Cumulus addresses barriers to data sharing based on (1) federally required support for standard APIs (2), increasing use of cloud computing, and (3) advances in AI. There is potential for scalability to support learning across myriad network configurations and use cases.

Beyond compliance with the 21st Century Cures Act Rule: a patient controlled electronic health information export application programming interface.

OBJECTIVE: The 21st Century Cures Act Final Rule requires that certified electronic health records (EHRs) be able to export a patient's full set of electronic health information (EHI). This requirement becomes more powerful if EHI exports use interoperable application programming interfaces (APIs). We sought to advance the ecosystem, instantiating policy desiderata in a working reference implementation based on a consensus design. MATERIALS AND METHODS: We formulate a model for interoperable, patient-controlled, app-driven access to EHI exports in an open source reference implementation following the Argonaut FHIR Accelerator consensus implementation guide for EHI Export. RESULTS: The reference implementation, which asynchronously provides EHI across an API, has three central components: a web application for patients to request EHI exports, an EHI server to respond to requests, and an administrative export management web application to manage requests. It leverages mandated SMART on FHIR/Bulk FHIR APIs. DISCUSSION: A patient-controlled app enabling full EHI export from any EHR across an API could facilitate national-scale patient-directed information exchange. We hope releasing these tools sparks engagement from the health IT community to evolve the design, implement and test in real-world settings, and develop patient-facing apps. CONCLUSION: To advance regulatory innovation, we formulate a model that builds on existing requirements under the Cures Act Rule and takes a step toward an interoperable, scalable approach, simplifying patient access to their own health data; supporting the sharing of clinical data for both improved patient care and medical research; and encouraging the growth of an ecosystem of third-party applications.

Real World Performance of the 21st Century Cures Act Population Level Application Programming Interface.

Objective: To evaluate the real-world performance in delivering patient data on populations, of the SMART/HL7 Bulk FHIR Access API, required in Electronic Health Records (EHRs) under the 21st Century Cures Act Rule. Materials and Methods: We used an open-source Bulk FHIR Testing Suite at five healthcare sites from April to September 2023, including four hospitals using EHRs certified for interoperability, and one Health Information Exchange (HIE) using a custom, standards-compliant API build. We measured export speeds, data sizes, and completeness across six types of FHIR resources. Results: Among the certified platforms, Oracle Cerner led in speed, managing 5-16 million resources at over 8,000 resources/min. Three Epic sites exported a FHIR data subset, achieving 1-12 million resources at 1,555-2,500 resources/min. Notably, the HIE's custom API outperformed, generating over 141 million resources at 12,000 resources/min. Discussion: The HIE's custom API showcased superior performance, endorsing the effectiveness of SMART/HL7 Bulk FHIR in enabling large-scale data exchange while underlining the need for optimization in existing EHR platforms. Agility and scalability are essential for diverse health, research, and public health use cases. Conclusion: To fully realize the interoperability goals of the 21st Century Cures Act, addressing the performance limitations of Bulk FHIR API is critical. It would be beneficial to include performance metrics in both certification and reporting processes.

A landscape survey of planned SMART/HL7 bulk FHIR data access API implementations and tools.

The Office of National Coordinator for Health Information Technology final rule implementing the interoperability and information blocking provisions of the 21st Century Cures Act requires support for two SMART (Substitutable Medical Applications, Reusable Technologies) application programming interfaces (APIs) and instantiates Health Level Seven International (HL7) Fast Healthcare Interoperability Resources (FHIR) as a lingua franca for health data. We sought to assess the current state and near-term plans for the SMART/HL7 Bulk FHIR Access API implementation across organizations including electronic health record vendors, cloud vendors, public health contractors, research institutions, payors, FHIR tooling developers, and other purveyors of health information technology platforms. We learned that many organizations not required through regulation to use standardized bulk data are rapidly implementing the API for a wide array of use cases. This may portend an unprecedented level of standardized population-level health data exchange that will support an apps and analytics ecosystem. Feedback from early adopters on the API's limitations and unsolved problems in the space of population health are highlighted.

Push Button Population Health: The SMART/HL7 FHIR Bulk Data Access Application Programming Interface.

The 21st Century Cures Act requires that certified health information technology have an application programming interface (API) giving access to all data elements of a patient's electronic health record, "without special effort". In the spring of 2020, the Office of the National Coordinator of Health Information Technology (ONC) published a rule-21st Century Cures Act Interoperability, Information Blocking, and the ONC Health IT Certification Program-regulating the API requirement along with protections against information blocking. The rule specifies the SMART/HL7 FHIR Bulk Data Access API, which enables access to patient-level data across a patient population, supporting myriad use cases across healthcare, research, and public health ecosystems. The API enables "push button population health" in that core data elements can readily and standardly be extracted from electronic health records, enabling local, regional, and national-scale data-driven innovation.

Immunomodulatory activity of exopolysaccharide from the rhizobacterium Paenibacillus polymyxa CCM 1465.

Bacterial polysaccharides are promising stimulants of protective functions in humans and animals. We investigated the ability of exopolysaccharide from the rhizobacterium Paenibacillus polymyxa CCM 1465 to induce nonspecific resistance factors in the macroorganism. We examined in vitro the effect of the exopolysaccharide, produced with different carbon sources, on the phagocytic activity of murine macrophages, on the generation of reactive oxygen species and of enzymes (acid phosphatase and myeloperoxidase), on the proliferation of murine splenocytes, and on the synthesis of proinflammatory cytokines [interleukin-1 (IL-1) and tumor necrosis factor α (TNF-α)] by human mononuclear cells. The exopolysaccharide promoted the phagocytosis of bacterial cells, activated metabolic processes in human and animal leukocytes, and moderately affected the production of TNF-α and IL-1ß. The exopolysaccharides produced on media with glucose and sucrose differed in their effect on the immune cells, possibly owing to their different compositions, structures, and properties. The results validly indicate that the exopolysaccharide of P. polymyxa CCM 1465 promotes nonspecific immunity. Therefore, it can find application as a biologically active immunomodulatory substance.

Structure of the O-specific polysaccharide from Azospirillum fermentarium CC-LY743T.

O-specific polysaccharide was obtained by mild acid hydrolysis of the lipopolysaccharide of nitrogen-fixing bacterium Azospirillum fermentarium CC-LY743T (IBPPM 578) and was studied by sugar analysis along with 1H and 13C NMR spectroscopy, including 1H,1H COSY, TOCSY, ROESY, and 1H,13C HSQC and HMBC experiments. The polysaccharide was found to be linear and to consist of alterating α-l-fucose and α-d-mannose residues in tetrasaccharide repeating units of the following structure: →2)-α-D-Manp-(1 → 3)-α-L-Fucp-(1 → 3)-α-D-Manp-(1 → 3)-α-L-Fucp-(1→.

Structural studies of the O-specific polysaccharide from detergent degrading bacteria Pseudomonas putida TSh-18.

An O-specific polysaccharide was obtained by mild acid degradation of the lipopolysaccharide of bacteria Pseudomonas putida TSh-18, capable of degrading non-ionogenic technical detergents. The polysaccharide was found to contain a rarely occurring sugar derivative 4,6-dideoxy-4-[(R)-3-hydroxybutanoylamino]-d-galactose [d-Fucp4N(RHb)]. Sugar and methylation analyses, Smith degradation, solvolysis with CF3CO2H, and 1H and 13C NMR spectroscopy enabled elucidation of the following structure of the branched trisaccharide repeating units of the polysaccharide.

Elucidation of a masked repeating structure of the O-specific polysaccharide of the halotolerant soil bacteria Azospirillum halopraeferens Au4.

An O-specific polysaccharide was obtained by mild acid hydrolysis of the lipopolysaccharide isolated by the phenol-water extraction from the halotolerant soil bacteria Azospirillum halopraeferens type strain Au4. The polysaccharide was studied by sugar and methylation analyses, selective cleavages by Smith degradation and solvolysis with trifluoroacetic acid, one- and two-dimensional (1)H and (13)C NMR spectroscopy. The following masked repeating structure of the O-specific polysaccharide was established: →3)-α-L-Rhap2Me-(1→3)-[ß-D-Glcp-(1→4)]-α-D-Fucp-(1→2)-ß-D-Xylp-(1→, where non-stoichiometric substituents, an O-methyl group (~45%) and a side-chain glucose residue (~65%), are shown in italics.

Assessing the efficacy of co-inoculation of wheat seedlings with the associative bacteria Paenibacillus polymyxa 1465 and Azospirillum brasilense Sp245.

Co-inoculation of associative bacteria, which have high nitrogen-fixing activity, tolerance for environmental conditions, and the ability to compete with the natural microflora, is used widely to enhance the growth and yields of agricultural plants. We evaluated the ability of 2 co-inoculated plant-growth-promoting rhizobacteria, Paenibacillus polymyxa 1465 and Azospirillum brasilense Sp245, to colonize roots of wheat (Triticum aestivum L. 'Saratovskaya 29') seedlings, and we assessed the morphometric parameters of wheat early in its development. Analysis by ELISA with polyclonal antibodies raised against the exopolysaccharide of P. polymyxa 1465 and the lipopolysaccharide of A. brasilense Sp245 demonstrated that the root-colonizing activity of A. brasilense was higher when the bacterium was co-inoculated with P. polymyxa than when it was inoculated singly. Immunofluorescence microscopy with Alexa Fluor 532-labeled antibodies revealed sites of attachment of co-inoculated P. polymyxa and A. brasilense and showed that the 2 bacteria colonized similar regions of the roots. Co-inoculation exerted a negative effect on wheat seedling development, inhibiting root length by 17.6%, total root weight by 11%, and total shoot weight by 12%. Under certain conditions, dual inoculation of wheat may prove ineffective, apparently owing to the competition between the rhizobacteria for colonization sites on the plant roots. The findings from this study may aid in developing techniques for mixed bacterial inoculation of cultivated plants.

Structure of the polysaccharides from the lipopolysaccharide of Azospirillum brasilense Jm125A2.

Two polysaccharides were obtained by mild acid degradation of the lipopolysaccharide of associative nitrogen-fixing bacteria Azospirillum brasilense Jm125A2 isolated from the rhizosphere of a pearl millet. The following structures of the polysaccharides were established by sugar and methylation analyses, Smith degradation, and (1)H and (13)C NMR spectroscopy: [Formula: see text] Structure 1 has been reported earlier for a polysaccharide from A. brasilense S17 (Fedonenko YP, Konnova ON, Zdorovenko EL, Konnova SA, Zatonsky GV, Shaskov AS, Ignatov VV, Knirel YA. Carbohydr Res 2008;343:810-6), whereas to our knowledge structure 2 has not been hitherto found in bacterial polysaccharides.

Structural studies of the polysaccharides from the lipopolysaccharides of Azospirillum brasilense Sp246 and SpBr14.

Lipopolysaccharides from closely related Azospirillum brasilense strains, Sp246 and SpBr14, were obtained by phenol-water extraction. Mild acid hydrolysis of the lipopolysaccharides followed by GPC on Sephadex G-50 resulted in polysaccharide mixtures. On the basis of sugar and methylation analyses, Smith degradation and (1)H and (13)C NMR spectroscopy data, it was concluded that both bacteria possess the same two distinct polysaccharides having structures 1 and 2: [structure: see text]. Structure 1 has been reported earlier for a polysaccharide of A. brasilense 54 [Fedonenko et al., 2011] whereas to our knowledge structure 2 has not been hitherto found in bacterial polysaccharides.

Structural studies of the O-specific polysaccharide(s) from the lipopolysaccharide of Azospirillum brasilense type strain Sp7.

Lipopolysaccharide was obtained by phenol-water extraction from dried bacterial cells of Azospirillum brasilense type strain Sp7. Mild acid hydrolysis of the lipopolysaccharide followed by GPC on Sephadex G-50 resulted in a polysaccharide mixture, which was studied by composition and methylation analyses, Smith degradation and (1)H and (13)C NMR spectroscopy. The following polysaccharide structures were established, where italics indicate a non-stoichiometric (∼40%) 2-O-methylation of l-rhamnose.

Structure of repeating units of a polysaccharide(s) from the lipopolysaccharide of Azospirillum brasilense SR80.

A high-molecular mass polysaccharide fraction was obtained by mild acid hydrolysis of the lipopolysaccharide of diazotrophic rhizobacterium Azospirillum brasilense SR80 followed by GPC on Sephadex G-50 Superfine. Studies by composition and methylation analyses, Smith degradation, and 1D and 2D (1)H and (13)C NMR spectroscopy demonstrated the presence of two structurally distinct repeating units having the following structures: It seems likely, although not proved, that these are repeats of two distinct polysaccharides rather than they build blocks within the same polysaccharide chain. The former structure is new, whereas the latter is closely related to the O-polysaccharide structure of A. brasilense Jm6B2 established earlier, which differs in partial (~60%) 3-O-methylation of d-rhamnose only [Boiko, A. S.; Dmitrenok, A. S.; Fedonenko, Yu. P.; Zdorovenko, E. L.; Konnova, S. A.; Knirel, Y. A.; Ignatov, V. V. Carbohydr. Res.2012, 355, 92-95].

Paenibacillus polymyxa rhizobacteria and their synthesized exoglycans in interaction with wheat roots: colonization and root hair deformation.

We examined the ability of several Paenibacillus polymyxa strains to colonize wheat roots and the ability of P. polymyxa exoglycans to induce root hair deformation. For the first time, exopolysaccharides isolated from P. polymyxa were found to produce, with different intensities, various morphological changes in the root hairs of wheat seedlings, which are some of the earliest responses of plants to bacteria in the surrounding milieu. P. polymyxa 1465, giving the highest exopolysaccharide yield and the highest viscosity of aqueous exopolysaccharide solutions, was best able to colonize wheat seedling roots, and its exopolysaccharide proved to be the best in producing root hair deformation. It is suggested that P. polymyxa exoglycans have an active role in the establishment of plant-microbe associations.

Structural analysis of the O-polysaccharide of the lipopolysaccharide from Azospirillum brasilense Jm6B2 containing 3-O-methyl-D-rhamnose (D-acofriose).

Two types of neutral O-polysaccharides were obtained by mild acid degradation of the lipopolysaccharide isolated by phenol-water extraction from the asymbiotic diazotrophic rhizobacterium Azospirillum brasilense Jm6B2. The following structure of the major O-polysaccharide was established by composition and methylation (ethylation) analyses, Smith degradation, and 1D and 2D (1)H and (13)C NMR spectroscopy: [structure: see text] where a non-stoichiometric (~60%) 3-O-methylation of D-rhamnose is indicated by italics.

An improved rapid method for the preparation of D-rhamnose.

A method is developed for the preparation of D-rhamnose from an O-polysaccharide (OPS) isolated by mild acid hydrolysis of Azospirillum brasilense SR75 cell mass. After the OPS hydrolysis, D-rhamnose was recovered by gel-permeation chromatography on Toyopearl TSK HW-40 and was crystallized. The sugar activity was demonstrated immunochemically. The advantages of the method are that it expedites and simplifies the extraction of D-rhamnose and increases its yield.

Structural and functional peculiarities of the lipopolysaccharide of Azospirillum brasilense SR55, isolated from the roots of Triticum durum.

Azospirillum brasilense SR55, isolated from the rhizosphere of Triticum durum, was classified as serogroup II on the basis of serological tests. Such serogroup affiliation is uncharacteristic of wheat-associated Azospirillum species. The lipid A of A. brasilense SR55 lipopolysaccharide contained 3-hydroxytetradecanoic, 3-hydroxyhexadecanoic, hexadecanoic and octadecenoic fatty acids. The structure of the lipopolysaccharide's O polysaccharide was established, with the branched octasaccharide repeating unit being represented by l-rhamnose, l-3-O-Me-rhamnose, d-galactose and d-glucuronic acid. The SR55 lipopolysaccharide induced deformations of wheat root hairs. The lipopolysaccharide was not involved in bacterial cell aggregation, but its use to pretreat wheat roots was conducive to cell adsorption. This study shows that Azospirillum bacteria can utilise their own lipopolysaccharide as a carbon source, which may give them an advantage in competitive natural environments.