Multilingual Framework for Risk Assessment and Symptom Tracking (MRAST).

The importance and value of real-world data in healthcare cannot be overstated because it offers a valuable source of insights into patient experiences. Traditional patient-reported experience and outcomes measures (PREMs/PROMs) often fall short in addressing the complexities of these experiences due to subjectivity and their inability to precisely target the questions asked. In contrast, diary recordings offer a promising solution. They can provide a comprehensive picture of psychological well-being, encompassing both psychological and physiological symptoms. This study explores how using advanced digital technologies, i.e., automatic speech recognition and natural language processing, can efficiently capture patient insights in oncology settings. We introduce the MRAST framework, a simplified way to collect, structure, and understand patient data using questionnaires and diary recordings. The framework was validated in a prospective study with 81 colorectal and 85 breast cancer survivors, of whom 37 were male and 129 were female. Overall, the patients evaluated the solution as well made; they found it easy to use and integrate into their daily routine. The majority (75.3%) of the cancer survivors participating in the study were willing to engage in health monitoring activities using digital wearable devices daily for an extended period. Throughout the study, there was a noticeable increase in the number of participants who perceived the system as having excellent usability. Despite some negative feedback, 44.44% of patients still rated the app's usability as above satisfactory (i.e., 7.9 on 1-10 scale) and the experience with diary recording as above satisfactory (i.e., 7.0 on 1-10 scale). Overall, these findings also underscore the significance of user testing and continuous improvement in enhancing the usability and user acceptance of solutions like the MRAST framework. Overall, the automated extraction of information from diaries represents a pivotal step toward a more patient-centered approach, where healthcare decisions are based on real-world experiences and tailored to individual needs. The potential usefulness of such data is enormous, as it enables better measurement of everyday experiences and opens new avenues for patient-centered care.

Machine Learning Algorithms to Predict Breast Cancer Recurrence Using Structured and Unstructured Sources from Electronic Health Records.

Recurrence is a critical aspect of breast cancer (BC) that is inexorably tied to mortality. Reuse of healthcare data through Machine Learning (ML) algorithms offers great opportunities to improve the stratification of patients at risk of cancer recurrence. We hypothesized that combining features from structured and unstructured sources would provide better prediction results for 5-year cancer recurrence than either source alone. We collected and preprocessed clinical data from a cohort of BC patients, resulting in 823 valid subjects for analysis. We derived three sets of features: structured information, features from free text, and a combination of both. We evaluated the performance of five ML algorithms to predict 5-year cancer recurrence and selected the best-performing to test our hypothesis. The XGB (eXtreme Gradient Boosting) model yielded the best performance among the five evaluated algorithms, with precision = 0.900, recall = 0.907, F1-score = 0.897, and area under the receiver operating characteristic AUROC = 0.807. The best prediction results were achieved with the structured dataset, followed by the unstructured dataset, while the combined dataset achieved the poorest performance. ML algorithms for BC recurrence prediction are valuable tools to improve patient risk stratification, help with post-cancer monitoring, and plan more effective follow-up. Structured data provides the best results when fed to ML algorithms. However, an approach based on natural language processing offers comparable results while potentially requiring less mapping effort.

An artificial intelligence-based approach for identifying rare disease patients using retrospective electronic health records applied for Pompe disease.

Objective: We retrospectively screened 350,116 electronic health records (EHRs) to identify suspected patients for Pompe disease. Using these suspected patients, we then describe their phenotypical characteristics and estimate the prevalence in the respective population covered by the EHRs. Methods: We applied Symptoma's Artificial Intelligence-based approach for identifying rare disease patients to retrospective anonymized EHRs provided by the "University Hospital Salzburg" clinic group. Within 1 month, the AI screened 350,116 EHRs reaching back 15 years from five hospitals, and 104 patients were flagged as probable for Pompe disease. Flagged patients were manually reviewed and assessed by generalist and specialist physicians for their likelihood for Pompe disease, from which the performance of the algorithms was evaluated. Results: Of the 104 patients flagged by the algorithms, generalist physicians found five "diagnosed," 10 "suspected," and seven patients with "reduced suspicion." After feedback from Pompe disease specialist physicians, 19 patients remained clinically plausible for Pompe disease, resulting in a specificity of 18.27% for the AI. Estimating from the remaining plausible patients, the prevalence of Pompe disease for the greater Salzburg region [incl. Bavaria (Germany), Styria (Austria), and Upper Austria (Austria)] was one in every 18,427 people. Phenotypes for patient cohorts with an approximated onset of symptoms above or below 1 year of age were established, which correspond to infantile-onset Pompe disease (IOPD) and late-onset Pompe disease (LOPD), respectively. Conclusion: Our study shows the feasibility of Symptoma's AI-based approach for identifying rare disease patients using retrospective EHRs. Via the algorithm's screening of an entire EHR population, a physician had only to manually review 5.47 patients on average to find one suspected candidate. This efficiency is crucial as Pompe disease, while rare, is a progressively debilitating but treatable neuromuscular disease. As such, we demonstrated both the efficiency of the approach and the potential of a scalable solution to the systematic identification of rare disease patients. Thus, similar implementation of this methodology should be encouraged to improve care for all rare disease patients.

Correlating global trends in COVID-19 cases with online symptom checker self-assessments.

BACKGROUND: Online symptom checkers are digital health solutions that provide a differential diagnosis based on a user's symptoms. During the coronavirus disease 2019 (COVID-19) pandemic, symptom checkers have become increasingly important due to physical distance constraints and reduced access to in-person medical consultations. Furthermore, various symptom checkers specialised in the assessment of COVID-19 infection have been produced. OBJECTIVES: Assess the correlation between COVID-19 risk assessments from an online symptom checker and current trends in COVID-19 infections. Analyse whether those correlations are reflective of various country-wise quality of life measures. Lastly, determine whether the trends found in symptom checker assessments predict or lag relative to those of the COVID-19 infections. MATERIALS AND METHODS: In this study, we compile the outcomes of COVID-19 risk assessments provided by the symptom checker Symptoma (www.symptoma.com) in 18 countries with suitably large user bases. We analyse this dataset's spatial and temporal features compared to the number of newly confirmed COVID-19 cases published by the respective countries. RESULTS: We find an average correlation of 0.342 between the number of Symptoma users assessed to have a high risk of a COVID-19 infection and the official COVID-19 infection numbers. Further, we show a significant relationship between that correlation and the self-reported health of a country. Lastly, we find that the symptom checker is, on average, ahead (median +3 days) of the official infection numbers for most countries. CONCLUSION: We show that online symptom checkers can capture the national-level trends in coronavirus infections. As such, they provide a valuable and unique information source in policymaking against pandemics, unrestricted by conventional resources.

Symptoms associated with a COVID-19 infection among a non-hospitalized cohort in Vienna.

BACKGROUND: Most clinical studies report the symptoms experienced by those infected with coronavirus disease 2019 (COVID-19) via patients already hospitalized. Here we analyzed the symptoms experienced outside of a hospital setting. METHODS: The Vienna Social Fund (FSW; Vienna, Austria), the Public Health Services of the City of Vienna (MA15) and the private company Symptoma collaborated to implement Vienna's official online COVID-19 symptom checker. Users answered 12 yes/no questions about symptoms to assess their risk for COVID-19. They could also specify their age and sex, and whether they had contact with someone who tested positive for COVID-19. Depending on the assessed risk of COVID-19 positivity, a SARS-CoV­2 nucleic acid amplification test (NAAT) was performed. In this publication, we analyzed which factors (symptoms, sex or age) are associated with COVID-19 positivity. We also trained a classifier to correctly predict COVID-19 positivity from the collected data. RESULTS: Between 2 November 2020 and 18 November 2021, 9133 people experiencing COVID-19-like symptoms were assessed as high risk by the chatbot and were subsequently tested by a NAAT. Symptoms significantly associated with a positive COVID-19 test were malaise, fatigue, headache, cough, fever, dysgeusia and hyposmia. Our classifier could successfully predict COVID-19 positivity with an area under the curve (AUC) of 0.74. CONCLUSION: This study provides reliable COVID-19 symptom statistics based on the general population verified by NAATs.

Photodynamic antimicrobial chemotherapy coupled with the use of the photosensitizers methylene blue and temoporfin as a potential novel treatment for Staphylococcus aureus in burn infections.

Photodynamic antimicrobial chemotherapy (PACT) is a novel alternative antimicrobial therapy that elicits a broad mechanism of action and therefore has a low probability of generating resistance. Such properties make PACT ideally suited for utilization in localized applications such as burn wounds. The aim of this study was to determine the antimicrobial activity of MB and temoporfin against both a S. aureus isolate and a P. aeruginosa isolate in light (640 nm) and dark conditions at a range of time points (0-20 min). A Staphylococcus aureus isolate and a Pseudomonas aeruginosa isolate were treated in vitro with methylene blue (MB) and temoporfin under different conditions following exposure to light at 640 nm and in no-light (dark) conditions. Bacterial cell viability [colony-forming units (c.f.u.) ml-1] was then calculated. Against P. aeruginosa , when MB was used as the photosensitizer, no phototoxic effect was observed in either light or dark conditions. After treatment with temoporfin, a reduction of less than one log (7.00×107 c.f.u. ml-1) was observed in the light after 20 min of exposure. However, temoporfin completely eradicated S. aureus in both light and dark conditions after 1 min (where a seven log reduction in c.f.u. ml-1 was observed). Methylene blue resulted in a loss of S. aureus viability, with a two log reduction in bacterial viability (c.f.u. ml-1) reported in both light and dark conditions after 20 min exposure time. Temoporfin demonstrated greater antimicrobial efficacy than MB against both the S. aureus and P. aeruginosa isolates tested. At 12.5 µM temoporfin resulted in complete eradication of S. aureus . In light of this study, further research into the validity of PACT, coupled with the photosensitizers (such as temoporfin), should be conducted in order to potentially develop alternative antimicrobial treatment regimes for burn wounds.

Landscapes of cellular phenotypic diversity in breast cancer xenografts and their impact on drug response.

The heterogeneity of breast cancer plays a major role in drug response and resistance and has been extensively characterized at the genomic level. Here, a single-cell breast cancer mass cytometry (BCMC) panel is optimized to identify cell phenotypes and their oncogenic signalling states in a biobank of patient-derived tumour xenograft (PDTX) models representing the diversity of human breast cancer. The BCMC panel identifies 13 cellular phenotypes (11 human and 2 murine), associated with both breast cancer subtypes and specific genomic features. Pre-treatment cellular phenotypic composition is a determinant of response to anticancer therapies. Single-cell profiling also reveals drug-induced cellular phenotypic dynamics, unravelling previously unnoticed intra-tumour response diversity. The comprehensive view of the landscapes of cellular phenotypic heterogeneity in PDTXs uncovered by the BCMC panel, which is mirrored in primary human tumours, has profound implications for understanding and predicting therapy response and resistance.

An artificial intelligence-based first-line defence against COVID-19: digitally screening citizens for risks via a chatbot.

To combat the pandemic of the coronavirus disease 2019 (COVID-19), numerous governments have established phone hotlines to prescreen potential cases. These hotlines have struggled with the volume of callers, leading to wait times of hours or, even, an inability to contact health authorities. Symptoma is a symptom-to-disease digital health assistant that can differentiate more than 20,000 diseases with an accuracy of more than 90%. We tested the accuracy of Symptoma to identify COVID-19 using a set of diverse clinical cases combined with case reports of COVID-19. We showed that Symptoma can accurately distinguish COVID-19 in 96.32% of clinical cases. When considering only COVID-19 symptoms and risk factors, Symptoma identified 100% of those infected when presented with only three signs. Lastly, we showed that Symptoma's accuracy far exceeds that of simple "yes-no" questionnaires widely available online. In summary, Symptoma provides unparalleled accuracy in systematically identifying cases of COVID-19 while also considering over 20,000 other diseases. Furthermore, Symptoma allows free text input, furthered with disease-specific follow up questions, in 36 languages. Combined, these results and accessibility give Symptoma the potential to be a key tool in the global fight against COVID-19. The Symptoma predictor is freely available online at https://www.symptoma.com .

Diagnostic Accuracy of Web-Based COVID-19 Symptom Checkers: Comparison Study.

BACKGROUND: A large number of web-based COVID-19 symptom checkers and chatbots have been developed; however, anecdotal evidence suggests that their conclusions are highly variable. To our knowledge, no study has evaluated the accuracy of COVID-19 symptom checkers in a statistically rigorous manner. OBJECTIVE: The aim of this study is to evaluate and compare the diagnostic accuracies of web-based COVID-19 symptom checkers. METHODS: We identified 10 web-based COVID-19 symptom checkers, all of which were included in the study. We evaluated the COVID-19 symptom checkers by assessing 50 COVID-19 case reports alongside 410 non-COVID-19 control cases. A bootstrapping method was used to counter the unbalanced sample sizes and obtain confidence intervals (CIs). Results are reported as sensitivity, specificity, F1 score, and Matthews correlation coefficient (MCC). RESULTS: The classification task between COVID-19-positive and COVID-19-negative for "high risk" cases among the 460 test cases yielded (sorted by F1 score): Symptoma (F1=0.92, MCC=0.85), Infermedica (F1=0.80, MCC=0.61), US Centers for Disease Control and Prevention (CDC) (F1=0.71, MCC=0.30), Babylon (F1=0.70, MCC=0.29), Cleveland Clinic (F1=0.40, MCC=0.07), Providence (F1=0.40, MCC=0.05), Apple (F1=0.29, MCC=-0.10), Docyet (F1=0.27, MCC=0.29), Ada (F1=0.24, MCC=0.27) and Your.MD (F1=0.24, MCC=0.27). For "high risk" and "medium risk" combined the performance was: Symptoma (F1=0.91, MCC=0.83) Infermedica (F1=0.80, MCC=0.61), Cleveland Clinic (F1=0.76, MCC=0.47), Providence (F1=0.75, MCC=0.45), Your.MD (F1=0.72, MCC=0.33), CDC (F1=0.71, MCC=0.30), Babylon (F1=0.70, MCC=0.29), Apple (F1=0.70, MCC=0.25), Ada (F1=0.42, MCC=0.03), and Docyet (F1=0.27, MCC=0.29). CONCLUSIONS: We found that the number of correctly assessed COVID-19 and control cases varies considerably between symptom checkers, with different symptom checkers showing different strengths with respect to sensitivity and specificity. A good balance between sensitivity and specificity was only achieved by two symptom checkers.

Metabolic Imaging Detects Resistance to PI3Kα Inhibition Mediated by Persistent FOXM1 Expression in ER+ Breast Cancer.

PIK3CA, encoding the PI3Kα isoform, is the most frequently mutated oncogene in estrogen receptor (ER)-positive breast cancer. Isoform-selective PI3K inhibitors are used clinically but intrinsic and acquired resistance limits their utility. Improved selection of patients that will benefit from these drugs requires predictive biomarkers. We show here that persistent FOXM1 expression following drug treatment is a biomarker of resistance to PI3Kα inhibition in ER+ breast cancer. FOXM1 drives expression of lactate dehydrogenase (LDH) but not hexokinase 2 (HK-II). The downstream metabolic changes can therefore be detected using MRI of LDH-catalyzed hyperpolarized 13C label exchange between pyruvate and lactate but not by positron emission tomography measurements of HK-II-mediated trapping of the glucose analog 2-deoxy-2-[18F]fluorodeoxyglucose. Rapid assessment of treatment response in breast cancer using this imaging method could help identify patients that benefit from PI3Kα inhibition and design drug combinations to counteract the emergence of resistance.

Landscape of G-quadruplex DNA structural regions in breast cancer.

Response and resistance to anticancer therapies vary due to intertumor and intratumor heterogeneity1. Here, we map differentially enriched G-quadruplex (G4) DNA structure-forming regions (∆G4Rs) in 22 breast cancer patient-derived tumor xenograft (PDTX) models. ∆G4Rs are associated with the promoters of highly amplified genes showing high expression, and with somatic single-nucleotide variants. Differences in ΔG4R landscapes reveal seven transcription factor programs across PDTXs. ∆G4R abundance and locations stratify PDTXs into at least three G4-based subtypes. ∆G4Rs in most PDTXs (14 of 22) were found to associate with more than one breast cancer subtype, which we also call an integrative cluster (IC)2. This suggests the frequent coexistence of multiple breast cancer states within a PDTX model, the majority of which display aggressive triple-negative IC10 gene activity. Short-term cultures of PDTX models with increased ∆G4R levels are more sensitive to small molecules targeting G4 DNA. Thus, G4 landscapes reveal additional IC-related intratumor heterogeneity in PDTX biopsies, improving breast cancer stratification and potentially identifying new treatment strategies.

Shieldin complex promotes DNA end-joining and counters homologous recombination in BRCA1-null cells.

BRCA1 deficiencies cause breast, ovarian, prostate and other cancers, and render tumours hypersensitive to poly(ADP-ribose) polymerase (PARP) inhibitors. To understand the resistance mechanisms, we conducted whole-genome CRISPR-Cas9 synthetic-viability/resistance screens in BRCA1-deficient breast cancer cells treated with PARP inhibitors. We identified two previously uncharacterized proteins, C20orf196 and FAM35A, whose inactivation confers strong PARP-inhibitor resistance. Mechanistically, we show that C20orf196 and FAM35A form a complex, 'Shieldin' (SHLD1/2), with FAM35A interacting with single-stranded DNA through its C-terminal oligonucleotide/oligosaccharide-binding fold region. We establish that Shieldin acts as the downstream effector of 53BP1/RIF1/MAD2L2 to promote DNA double-strand break (DSB) end-joining by restricting DSB resection and to counteract homologous recombination by antagonizing BRCA2/RAD51 loading in BRCA1-deficient cells. Notably, Shieldin inactivation further sensitizes BRCA1-deficient cells to cisplatin, suggesting how defining the SHLD1/2 status of BRCA1-deficient tumours might aid patient stratification and yield new treatment opportunities. Highlighting this potential, we document reduced SHLD1/2 expression in human breast cancers displaying intrinsic or acquired PARP-inhibitor resistance.

The prescribable drugs with efficacy in experimental epilepsies (PDE3) database for drug repurposing research in epilepsy.

OBJECTIVE: Current antiepileptic drugs (AEDs) have several shortcomings. For example, they fail to control seizures in 30% of patients. Hence, there is a need to identify new AEDs. Drug repurposing is the discovery of new indications for approved drugs. This drug "recycling" offers the potential of significant savings in the time and cost of drug development. Many drugs licensed for other indications exhibit antiepileptic efficacy in animal models. Our aim was to create a database of "prescribable" drugs, approved for other conditions, with published evidence of efficacy in animal models of epilepsy, and to collate data that would assist in choosing the most promising candidates for drug repurposing. METHODS: The database was created by the following: (1) computational literature-mining using novel software that identifies Medline abstracts containing the name of a prescribable drug, a rodent model of epilepsy, and a phrase indicating seizure reduction; then (2) crowdsourced manual curation of the identified abstracts. RESULTS: The final database includes 173 drugs and 500 abstracts. It is made freely available at www.liverpool.ac.uk/D3RE/PDE3. The database is reliable: 94% of the included drugs have corroborative evidence of efficacy in animal models (for example, evidence from multiple independent studies). The database includes many drugs that are appealing candidates for repurposing, as they are widely accepted by prescribers and patients-the database includes half of the 20 most commonly prescribed drugs in England-and they target many proteins involved in epilepsy but not targeted by current AEDs. It is important to note that the drugs are of potential relevance to human epilepsy-the database is highly enriched with drugs that target proteins of known causal human epilepsy genes (Fisher's exact test P-value < 3 × 10-5 ). We present data to help prioritize the most promising candidates for repurposing from the database. SIGNIFICANCE: The PDE3 database is an important new resource for drug repurposing research in epilepsy.

Predicted relative prevalence estimates for obstructive sleep apnoea and the associated healthcare provision across the UK.

We surveyed the UK distribution of five factors commonly associated with obstructive sleep apnoea (OSA) to produce an overall risk map that could be used to predict relative prevalence estimates. The weighting and mapping of selected risk factors associated with OSA highlighted significant regional variation in predicted prevalence estimates. These data provide the first attempt to systematically map the UK for OSA and identify areas where the condition is likely to be more prevalent. The data show a significant mismatch between areas identified as having a high predicted prevalence estimate and the distribution of existing sleep centres.

Variation and decomposition of the partial molar volume of small gas molecules in different organic solvents derived from molecular dynamics simulations.

The partial molar volumes, V(i), of the gas solutes H2, CO, and CO2, solvated in acetone, methanol, heptane, and diethylether are determined computationally in the limit of infinite dilution and standard conditions. Solutions are described with molecular dynamics simulations in combination with the OPLS-aa force field for solvents and customized force field for solutes. V(i) is determined with the direct method, while the composition of V(i) is studied with Kirkwood-Buff integrals (KBIs). Subsequently, the amount of unoccupied space and size of pre-formed cavities in pure solvents is determined. Additionally, the shape of individual solvent cages is analyzed. Calculated V(i) deviate only 3.4 cm(3) mol(-1) (7.1%) from experimental literature values. Experimental V(i) variations across solutions are reproduced qualitatively and also quantitatively in most cases. The KBI analysis identifies differences in solute induced solvent reorganization in the immediate vicinity of H2 (<0.7 nm) and solvent reorganization up to the third solvation shell of CO and CO2 (<1.6 nm) as the origin of V(i) variations. In all solutions, larger V(i) are found in solvents that exhibit weak internal interactions, low cohesive energy density and large compressibility. Weak internal interactions facilitate solvent displacement by thermal solute movement, which enhances the size of solvent cages and thus V(i). Additionally, attractive electrostatic interactions of CO2 and the solvents, which do not depend on internal solvent interactions only, partially reversed the V(i) trends observed in H2 and CO solutions where electrostatic interactions with the solvents are absent. More empty space and larger pre-formed cavities are found in solvents with weak internal interactions, however, no evidence is found that solutes in any considered solvent are accommodated in pre-formed cavities. Individual solvent cages are found to be elongated in the negative direction of solute movement. This wake behind the moving solute is more pronounced in case of mobile H2 and in solvents with weaker internal interactions. However, deviations from a spherical solvent cage shape do not influence solute-solvent radial distribution functions after averaging over all solvent cage orientations and hence do not change V(i). Overall, the applied methodology reproduces V(i) and its variations reliably and the used V(i) decompositions identify the underlying reasons behind observed V(i) variations.