Learning Analytics Applied to Clinical Diagnostic Reasoning Using a Natural Language Processing-Based Virtual Patient Simulator: Case Study.

BACKGROUND: Virtual patient simulators (VPSs) log all users' actions, thereby enabling the creation of a multidimensional representation of students' medical knowledge. This representation can be used to create metrics providing teachers with valuable learning information. OBJECTIVE: The aim of this study is to describe the metrics we developed to analyze the clinical diagnostic reasoning of medical students, provide examples of their application, and preliminarily validate these metrics on a class of undergraduate medical students. The metrics are computed from the data obtained through a novel VPS embedding natural language processing techniques. METHODS: A total of 2 clinical case simulations (tests) were created to test our metrics. During each simulation, the students' step-by-step actions were logged into the program database for offline analysis. The students' performance was divided into seven dimensions: the identification of relevant information in the given clinical scenario, history taking, physical examination, medical test ordering, diagnostic hypothesis setting, binary analysis fulfillment, and final diagnosis setting. Sensitivity (percentage of relevant information found) and precision (percentage of correct actions performed) metrics were computed for each issue and combined into a harmonic mean (F1), thereby obtaining a single score evaluating the students' performance. The 7 metrics were further grouped to reflect the students' capability to collect and to analyze information to obtain an overall performance score. A methodological score was computed based on the discordance between the diagnostic pathway followed by students and the reference one previously defined by the teacher. In total, 25 students attending the fifth year of the School of Medicine at Humanitas University underwent test 1, which simulated a patient with dyspnea. Test 2 dealt with abdominal pain and was attended by 36 students on a different day. For validation, we assessed the Spearman rank correlation between the performance on these scores and the score obtained by each student in the hematology curricular examination. RESULTS: The mean overall scores were consistent between test 1 (mean 0.59, SD 0.05) and test 2 (mean 0.54, SD 0.12). For each student, the overall performance was achieved through a different contribution in collecting and analyzing information. Methodological scores highlighted discordances between the reference diagnostic pattern previously set by the teacher and the one pursued by the student. No significant correlation was found between the VPS scores and hematology examination scores. CONCLUSIONS: Different components of the students' diagnostic process may be disentangled and quantified by appropriate metrics applied to students' actions recorded while addressing a virtual case. Such an approach may help teachers provide students with individualized feedback aimed at filling competence drawbacks and methodological inconsistencies. There was no correlation between the hematology curricular examination score and any of the proposed scores as these scores address different aspects of students' medical knowledge.

CD80 expression is upregulated by TP53 activation in human cancer epithelial cells.

CD80 is recognized as one of the most potent costimulatory molecules by which immune cells limit cancer progression; however, the current understanding of the regulation of its expression on human tumor cells is limited. The TP53 tumor suppressor plays a critical role in cancer and its significant role in the control of immune responses is emerging. Here, we evaluated the role of TP53 as a regulator of CD80 expression in human cancer cells. A set of well-known TP53-reactivating compounds were used on TP53-wild-type, TP53-deficient, TP53-mutated and TP53-knockdown cancer cell lines to determine if TP53 can regulate CD80. CD80 expression was analyzed in samples from patients with TP53-active vs TP53-inactive Colon Adenocarcinomas (COAD) from TCGA panCancer Atlas. We report that the pharmacological activation of TP53 can stimulate the expression of CD80 in human tumor cells of epithelial origin. We also provide evidence that CD80 expression exhibits a strong correlation with TP53 activation in a subgroup of colon tumors with better overall survival. These results confirm the link between TP53 and immune surveillance in human cancer and provide the possibility that conventional TP53-activation approaches for tumoricidal effects may be repurposed for immunotherapy strategies.

A Natural Language Processing-Based Virtual Patient Simulator and Intelligent Tutoring System for the Clinical Diagnostic Process: Simulator Development and Case Study.

BACKGROUND: Shortage of human resources, increasing educational costs, and the need to keep social distances in response to the COVID-19 worldwide outbreak have prompted the necessity of clinical training methods designed for distance learning. Virtual patient simulators (VPSs) may partially meet these needs. Natural language processing (NLP) and intelligent tutoring systems (ITSs) may further enhance the educational impact of these simulators. OBJECTIVE: The goal of this study was to develop a VPS for clinical diagnostic reasoning that integrates interaction in natural language and an ITS. We also aimed to provide preliminary results of a short-term learning test administered on undergraduate students after use of the simulator. METHODS: We trained a Siamese long short-term memory network for anamnesis and NLP algorithms combined with Systematized Nomenclature of Medicine (SNOMED) ontology for diagnostic hypothesis generation. The ITS was structured on the concepts of knowledge, assessment, and learner models. To assess short-term learning changes, 15 undergraduate medical students underwent two identical tests, composed of multiple-choice questions, before and after performing a simulation by the virtual simulator. The test was made up of 22 questions; 11 of these were core questions that were specifically designed to evaluate clinical knowledge related to the simulated case. RESULTS: We developed a VPS called Hepius that allows students to gather clinical information from the patient's medical history, physical exam, and investigations and allows them to formulate a differential diagnosis by using natural language. Hepius is also an ITS that provides real-time step-by-step feedback to the student and suggests specific topics the student has to review to fill in potential knowledge gaps. Results from the short-term learning test showed an increase in both mean test score (P<.001) and mean score for core questions (P<.001) when comparing presimulation and postsimulation performance. CONCLUSIONS: By combining ITS and NLP technologies, Hepius may provide medical undergraduate students with a learning tool for training them in diagnostic reasoning. This may be particularly useful in a setting where students have restricted access to clinical wards, as is happening during the COVID-19 pandemic in many countries worldwide.

On the explainability of hospitalization prediction on a large COVID-19 patient dataset.

We develop various AI models to predict hospitalization on a large (over 110k) cohort of COVID-19 positive-tested US patients, sourced from March 2020 to February 2021. Models range from Random Forest to Neural Network (NN) and Time Convolutional NN, where combination of the data modalities (tabular and time dependent) are performed at different stages (early vs. model fusion). Despite high data unbalance, the models reach average precision 0.96-0.98 (0.75-0.85), recall 0.96-0.98 (0.74-0.85), and F1-score 0.97-0.98 (0.79-0.83) on the non-hospitalized (or hospitalized) class. Performances do not significantly drop even when selected lists of features are removed to study model adaptability to different scenarios. However, a systematic study of the SHAP feature importance values for the developed models in the different scenarios shows a large variability across models and use cases. This calls for even more complete studies on several explainability methods before their adoption in high-stakes scenarios.

Artificial Intelligence Decision Support for Medical Triage.

Applying state-of-the-art machine learning and natural language processing on approximately one million of teleconsultation records, we developed a triage system, now certified and in use at the largest European telemedicine provider. The system evaluates care alternatives through interactions with patients via a mobile application. Reasoning on an initial set of provided symptoms, the triage application generates AI-powered, personalized questions to better characterize the problem and recommends the most appropriate point of care and time frame for a consultation. The underlying technology was developed to meet the needs for performance, transparency, user acceptance and ease of use, central aspects to the adoption of AI-based decision support systems. Providing such remote guidance at the beginning of the chain of care has significant potential for improving cost efficiency, patient experience and outcomes. Being remote, always available and highly scalable, this service is fundamental in high demand situations, such as the current COVID-19 outbreak.

Epithelial CD80 promotes immune surveillance of colonic preneoplastic lesions and its expression is increased by oxidative stress through STAT3 in colon cancer cells.

BACKGROUND: One of the most potent costimulatory molecules involved in the recognition and killing of tumor cells is CD80. However, its role and the molecular mechanisms regulating its expression in sporadic colorectal carcinogenesis remain elusive. Here, we provide evidence for CD80 overexpression in human colon epithelial cells derived from preneoplastic mucosa. METHODS: Expression of CD80 on colonic epithelial cells isolated from normal human colonic mucosa, preneoplastic and neoplastic specimens was assessed by flow cytometry. WT and CD80KO mice received azoxymethane to induce colon preneoplastic lesions and sacrificed to perform histology, flow cytometry analysis and immunohistochemistry of colonic mucosa. Some WT mice were treated with a monoclonal anti-CD80 antibody following AOM administration. Primary colon epithelial cells and CT26 cell line were used to quantify the expression of CD80 in response to pro-oxidant stimuli. Specific pharmacological inhibitors and siRNA silencing were used to inhibit MAPK pathways and STAT3. RESULTS: CD80 expression was significantly increased in colon epithelial cells of human preneoplastic lesions. In the AOM model, CD80 impairment by administration of neutralizing antibodies or use of CD80 knockout mice enhanced dysplasia development. In vitro, CD80 upregulation was induced by oxidative stress in colon cancer cells and primary colon epithelial cells. In addition, reactive oxygen species could induce CD80 expression via the JNK and p38 MAPK pathways, that activated STAT3 transcription factor in colon cancer epithelial cells. CONCLUSION: This study provide evidence for a major role of CD80 in orchestrating immune surveillance of colon preneoplastic lesions and might help to develop novel approaches that exploit anti-tumor immunity to prevent and control colon cancer.

Cognitive DDx Assistant in Rare Diseases.

There are between 6,000 - 7,000 known rare diseases today. Identifying and diagnosing a patient with rare disease is time consuming, cumbersome, cost intensive and requires resources generally available only at large hospital centers. Furthermore, most medical doctors, especially general practitioners, will likely only see one patient with a rare disease if at all. A cognitive assistant for differential diagnosis in rare disease will provide the knowledge on all rare diseases online, help create a list of weighted diagnosis and access to the evidence base on which the list was created. The system is built on knowledge graph technology that incorporates data from ICD-10, DOID, medDRA, PubMed, Wikipedia, Orphanet, the CDC and anonymized patient data. The final knowledge graph comprised over 500,000 nodes. The solution was tested with 101 published cases for rare disease. The learning system improves over training sprints and delivers 79.5 % accuracy in finding the diagnosis in the top 1 % of nodes. A further learning step was taken to rank the correct result in the TOP 15 hits. With a reduced data pool, 51% of the 101 cases were tested delivering the correct result in the TOP 3 - 13 (TOP 6 on average) for 74% of these cases. The results show that data curation is among the most critical aspects to deliver accurate results. The knowledge graph technology demonstrates its power to deliver cognitive solutions for differential diagnosis in rare disease that can be applied in clinical practice.

Herpes Simplex Virus Type 1 Engages Toll Like Receptor 2 to Recruit Macrophages During Infection of Enteric Neurons.

Herpes simplex virus type 1 (HSV-1) is a widespread neurotropic pathogen responsible for a range of clinical manifestations. Inflammatory cell infiltrate is a common feature of HSV-1 infections and has been implicated in neurodegeneration. Therefore, viral recognition by innate immune receptors (i.e., TLR2) and the subsequent inflammatory response are now deemed key players in HSV-1 pathogenesis. In this study we infected with HSV-1 the enteric nervous system (ENS) of wild-type (WT) and TLR2 knock-out (TLR2ko) mice to investigate whether and how TLR2 participates in HSV-1 induced neuromuscular dysfunction. Our findings demonstrated viral specific transcripts suggestive of abortive replication in the ENS of both WT and TLR2ko mice. Moreover, HSV-1 triggered TLR2-MyD88 depend signaling in myenteric neurons and induced structural and functional alterations of the ENS. Gastrointestinal dysmotility was, however, less pronounced in TLR2ko as compared with WT mice. Interesting, HSV-1 caused up-regulation of monocyte chemoattractant protein-1 (CCL2) and recruitment of CD11b+ macrophages in the myenteric ganglia of WT but not TLR2ko mice. At the opposite, the myenteric plexuses of TLR2ko mice were surrounded by a dense infiltration of HSV-1 reactive CD3+CD8+INFγ+ lymphocytes. Indeed, depletion CD3+CD8+ cells by means of administration of anti-CD8 monoclonal antibody reduced neuromuscular dysfunction in TLR2ko mice infected with HSV-1. During HSV-1 infection, the engagement of TLR2 mediates production of CCL2 in infected neurons and coordinates macrophage recruitment. Bearing in mind these observations, blockage of TLR2 signaling could provide novel therapeutic strategies to support protective and specific T-cell responses and to improve neuromuscular dysfunction in pathogen-mediated alterations of the ENS.

Correction: Saccharomyces boulardii CNCM I-745 supplementation reduces gastrointestinal dysfunction in an animal model of IBS.

[This corrects the article DOI: 10.1371/journal.pone.0181863.].

Saccharomyces boulardii CNCM I-745 supplementation reduces gastrointestinal dysfunction in an animal model of IBS.

BACKGROUND: We evaluated the effect of Saccharomyces boulardii CNCM I-745 on intestinal neuromuscular anomalies in an IBS-type mouse model of gastrointestinal motor dysfunctions elicited by Herpes Simplex Virus type 1 (HSV-1) exposure. METHODS: Mice were inoculated intranasally with HSV-1 (102 PFU) or vehicle at time 0 and 4 weeks later by the intragastric (IG) route (108 PFU). Six weeks after IG inoculum, mice were randomly allocated to receive oral gavage with either S. boulardii (107 CFU/day) or vehicle. After 4 weeks the following were determined: a) intestinal motility using fluorescein-isothiocyanate dextran distribution in the gut, fecal pellet expulsion, stool water content, and distal colonic transit of glass beads; b) integrity of the enteric nervous system (ENS) by immunohistochemistry on ileal whole-mount preparations and western blot of protein lysates from ileal longitudinal muscle and myenteric plexus; c) isometric muscle tension with electric field and pharmacological (carbachol) stimulation of ileal segments; and d) intestinal inflammation by levels of tumor necrosis factor α, interleukin(IL)-1ß, IL-10 and IL-4. RESULTS: S. boulardii CNCM I-745 improved HSV-1 induced intestinal dysmotility and alteration of intestinal transit observed ten weeks after IG inoculum of the virus. Also, the probiotic yeast ameliorated the structural alterations of the ENS induced by HSV-1 (i.e., reduced peripherin immunoreactivity and expression, increased glial S100ß protein immunoreactivity and neuronal nitric oxide synthase level, reduced substance P-positive fibers). Moreover, S. boulardii CNCM I-745 diminished the production of HSV-1 associated pro-inflammatory cytokines in the myenteric plexus and increased levels of anti-inflammatory interleukins. CONCLUSIONS: S. boulardii CNCM I-745 ameliorated gastrointestinal neuromuscular anomalies in a mouse model of gut dysfunctions typically observed with irritable bowel syndrome.

Microstructure and ferroelectricity of BaTiO3 thin films on Si for integrated photonics.

Significant progress has been made in integrating novel materials into silicon photonic structures in order to extend the functionality of photonic circuits. One of these promising optical materials is BaTiO3 or barium titanate (BTO) that exhibits a very large Pockels coefficient as required for high-speed light modulators. However, all previous demonstrations show a noticable reduction of the Pockels effect in BTO thin films deposited on silicon substrates compared to BTO bulk crystals. Here, we report on the strong dependence of the Pockels effect in BTO thin films on their microstructure, and provide guidelines on how to engineer thin films with strong electro-optic response. We employ several deposition methods such as molecular beam epitaxy and chemical vapor deposition to realize BTO thin films with different morphology and crystalline structure. While a linear electro-optic response is present even in porous, polycrystalline BTO thin films with an effective Pockels coefficient r eff = 6 pm V-1, it is maximized for dense, tetragonal, epitaxial BTO films (r eff = 140 pm V-1). By identifying the key structural predictors of electro-optic response in BTO/Si, we provide a roadmap to fully exploit the linear electro-optic effect in novel hybrid oxide/semiconductor nanophotonic devices.

Oxygenated amorphous carbon for resistive memory applications.

Carbon-based electronics is a promising alternative to traditional silicon-based electronics as it could enable faster, smaller and cheaper transistors, interconnects and memory devices. However, the development of carbon-based memory devices has been hampered either by the complex fabrication methods of crystalline carbon allotropes or by poor performance. Here we present an oxygenated amorphous carbon (a-COx) produced by physical vapour deposition that has several properties in common with graphite oxide. Moreover, its simple fabrication method ensures excellent reproducibility and tuning of its properties. Memory devices based on a-COx exhibit outstanding non-volatile resistive memory performance, such as switching times on the order of 10 ns and cycling endurance in excess of 10(4) times. A detailed investigation of the pristine, SET and RESET states indicates a switching mechanism based on the electrochemical redox reaction of carbon. These results suggest that a-COx could play a key role in non-volatile memory technology and carbon-based electronics.

A strong electro-optically active lead-free ferroelectric integrated on silicon.

The development of silicon photonics could greatly benefit from the linear electro-optical properties, absent in bulk silicon, of ferroelectric oxides, as a novel way to seamlessly connect the electrical and optical domain. Of all oxides, barium titanate exhibits one of the largest linear electro-optical coefficients, which has however not yet been explored for thin films on silicon. Here we report on the electro-optical properties of thin barium titanate films epitaxially grown on silicon substrates. We extract a large effective Pockels coefficient of r(eff) = 148 pm V(-1), which is five times larger than in the current standard material for electro-optical devices, lithium niobate. We also reveal the tensor nature of the electro-optical properties, as necessary for properly designing future devices, and furthermore unambiguously demonstrate the presence of ferroelectricity. The integration of electro-optical active films on silicon could pave the way towards power-efficient, ultra-compact integrated devices, such as modulators, tuning elements and bistable switches.