Semantic Information Retrieval on Medical Texts

The explosive growth and widespread accessibility of medical information on the Internet have led to a surge of research activity in a wide range of scientific communities including health informatics and information retrieval (IR). One of the common concerns of this research, across these disciplines, is how to design either clinical decision support systems or medical search engines capable of providing adequate support for both novices (e.g., patients and their next-of-kin) and experts (e.g., physicians, clinicians) tackling complex tasks (e.g., search for diagnosis, search for a treatment). However, despite the significant multi-disciplinary research advances, current medical search systems exhibit low levels of performance. This survey provides an overview of the state of the art in the disciplines of IR and health informatics, and bridging these disciplines shows how semantic search techniques can facilitate medical IR. First,we will give a broad picture of semantic search and medical IR and then highlight the major scientific challenges. Second, focusing on the semantic gap challenge, we will discuss representative state-of-the-art work related to feature-based as well as semantic-based representation and matching models that support medical search systems. In addition to seminal works, we will present recent works that rely on research advancements in deep learning. Third, we make a thorough cross-model analysis and provide some findings and lessons learned. Finally, we discuss some open issues and possible promising directions for future research trends.

Differentially Private Medical Texts Generation Using Generative Neural Networks

Technological advancements in data science have offered us affordable storage and efficient algorithms to query a large volume of data. Our health records are a significant part of this data, which is pivotal for healthcare providers and can be utilized in our well-being. The clinical note in electronic health records is one such category that collects a patient’s complete medical information during different timesteps of patient care available in the form of free-texts. Thus, these unstructured textual notes contain events from a patient’s admission to discharge, which can prove to be significant for future medical decisions. However, since these texts also contain sensitive information about the patient and the attending medical professionals, such notes cannot be shared publicly. This privacy issue has thwarted timely discoveries on this plethora of untapped information. Therefore, in this work, we intend to generate synthetic medical texts from a private or sanitized (de-identified) clinical text corpus and analyze their utility rigorously in different metrics and levels. Experimental results promote the applicability of our generated data as it achieves more than 80\% accuracy in different pragmatic classification problems and matches (or outperforms) the original text data.

Acceptability and User Experiences of a Patient-Held Smart Card for Antenatal Services in Nigeria: A Qualitative Study

Background Poor maternal, newborn and child health outcomes remain a major public health challenge in Nigeria. Mobile health (mHealth) interventions such as patient-held smart cards have been proposed as effective solutions to improve maternal health outcomes. Our objectives were to assess the acceptability and experiences of pregnant women with the use of a patient-held smartcard for antenatal services in Nigeria. Methods Using focus group discussions, qualitative data were obtained from 35 pregnant women attending antenatal services in four Local Government Areas (LGAs) in Benue State, Nigeria. The audio-recorded data were transcribed and analyzed using framework analysis techniques such as the PEN-3 cultural model as a guide. Results The participants were 18-44 years of age (median age: 24 years), all were married and the majority were farmers. Most of the participants had accepted and used the smartcards for antenatal services. The most common positive perceptions about the smartcards were their ability to be used across multiple health facilities, the preference for storage of the women’s medical information on the smartcards compared to the usual paper-based system, and shorter waiting times at the clinics. Notable facilitators to using the smartcards were its provision at the “Baby showers” which were already acceptable to the women, access to free medical screenings, and ease of storage and retrieval of health records from the cards. Costs associated with health services was reported as a major barrier to using the smartcards. Support from health workers, program staff and family members, particularly spouses, encouraged the participants to use the smartcards. Conclusion These findings revealed that patient-held smart card for maternal health care services is acceptable by women utilizing antenatal services in Nigeria. Understanding perceptions, barriers, facilitators, and supportive systems that enhance the use of these smart cards may facilitate the development of lifesaving mobile health platforms that have the potential to achieve antenatal, delivery, and postnatal targets in a resource-limited setting.

Pattern recognition in data as a diagnosis tool

Medical data often appear in the form of numerical matrices or sequences. We develop mathematical tools for automatic screening of such data in two medical contexts: diagnosis of systemic lupus erythematosus (SLE) patients and identification of cardiac abnormalities. The idea is first to implement adequate data normalizations and then identify suitable hyperparameters and distances to classify relevant patterns. To this purpose, we discuss the applicability of Plackett-Luce models for rankings to hyperparameter and distance selection. Our tests suggest that, while Hamming distances seem to be well adapted to the study of patterns in matrices representing data from laboratory tests, dynamic time warping distances provide robust tools for the study of cardiac signals. The techniques developed here may set a basis for automatic screening of medical information based on pattern comparison.

A prediction rule for severe adverse events in all inpatients with community-acquired pneumonia: a multicenter observational study

Background Prediction of inpatients with community-acquired pneumonia (CAP) at high risk for severe adverse events (SAEs) requiring higher-intensity treatment is critical. However, evidence regarding prediction rules applicable to all patients with CAP including those with healthcare-associated pneumonia (HCAP) is limited. The objective of this study is to develop and validate a new prediction system for SAEs in inpatients with CAP. Methods Logistic regression analysis was performed in 1334 inpatients of a prospective multicenter study to develop a multivariate model predicting SAEs (death, requirement of mechanical ventilation, and vasopressor support within 30 days after diagnosis). The developed ALL-COP-SCORE rule based on the multivariate model was validated in 643 inpatients in another prospective multicenter study. Results The ALL-COP SCORE rule included albumin (< 2 g/dL, 2 points; 2–3 g/dL, 1 point), white blood cell (< 4000 cells/μL, 3 points), chronic lung disease (1 point), confusion (2 points), PaO2/FIO2 ratio (< 200 mmHg, 3 points; 200–300 mmHg, 1 point), potassium (≥ 5.0 mEq/L, 2 points), arterial pH (< 7.35, 2 points), systolic blood pressure (< 90 mmHg, 2 points), PaCO2 (> 45 mmHg, 2 points), HCO3− (< 20 mmol/L, 1 point), respiratory rate (≥ 30 breaths/min, 1 point), pleural effusion (1 point), and extent of chest radiographical infiltration in unilateral lung (> 2/3, 2 points; 1/2–2/3, 1 point). Patients with 4–5, 6–7, and ≥ 8 points had 17%, 35%, and 52% increase in the probability of SAEs, respectively, whereas the probability of SAEs was 3% in patients with ≤ 3 points. The ALL-COP SCORE rule exhibited a higher area under the receiver operating characteristic curve (0.85) compared with the other predictive models, and an ALL-COP SCORE threshold of ≥ 4 points exhibited 92% sensitivity and 60% specificity. Conclusions ALL-COP SCORE rule can be useful to predict SAEs and aid in decision-making on treatment intensity for all inpatients with CAP including those with HCAP. Higher-intensity treatment should be considered in patients with CAP and an ALL-COP SCORE threshold of ≥ 4 points. Trial registration This study was registered with the University Medical Information Network in Japan, registration numbers UMIN000003306 and UMIN000009837.

Evaluation of rare-earth sesquioxides nanoparticles as a bottom-up strategy toward the formation of functional structures

Background: The strategy to form functional structures based on powder technology relies on the concept of nanoparticles characteristics. Rare-earth sesquioxides (RE2O3; RE as Y, Tm, Eu) exhibit remarkable properties, and their fields of application cover energy, astronomy, environmental, medical, information technology, industry, and materials science. The purpose of this paper is to evaluate the RE2O3 nanoparticles characteristics as a bottom-up strategy to form functional materials for radiation dosimetry. Methods: The RE2O3 nanoparticles were characterized by the following techniques: XRD, SEM, PCS, FTIR, ICP, EPR, and zeta potential. Results: All RE2O3 samples exhibited cubic C-type structure in accordance with the sesquioxide diagram, chemical composition over 99.9%, monomodal mean particle size distribution, in which (d50) was inferior than 130nm. Among all samples, only yttrium oxide exhibited EPR signal, in which the most intense peak was recorded at 358mT and g 1.9701. Conclusion: The evaluation of nanoparticle characteristics is extremely important taking into account a bottom-up strategy to form functional materials. The RE2O3 nanoparticles exhibited promising characteristics for application in radiation dosimetry.

РОЗРОБКА МЕДИЧНОЇ ІНФОРМАЦІЙНОЇ СИСТЕМИ ДЛЯ МЕДИЧНИХ ЗАКЛАДІВ ПЕРВИННОЇ ЛАНКИ

Purpose. Development of a web application with a functional module for conducting prescriptions according to the ICPC2 standard for primary care facilities.Methodology. The C # 8.0 language and the ASP.Net Core 5.0 framework were chosen to implement a server application with the RESTful architecture. The MySql database is selected as the database. HTML5 SASS, JavaScript, React and Redux were used to develop the client part.Findings. Theoretical bases and business processes of medical information systems are investigated. The basic principles of building a modern information system are studied. A medical information system with a high rate of reliability and speed has been designed and implemented. Developed a web application with a client-server architectureOriginality. Features of modern applied medical information systems are revealed. Possibilities of medical information as the main means of medical data storage are considered. The process of conducting medical reception according to the ICPC2 standard for primary care facilities has been worked out. Theoretical bases of construction of software information system for polyclinic and outpatient clinic are investigated.Practical value. A medical information system with a high level of reliability and speed, an interface understandable for all age groups of users has been designed and implemented. Developed a web application with client-server architecture.

Utility of Systemic Inflammatory Syndrome Score in Predicting Healthcare-Associated Infections in Critically Ill Patients: A Matched Case-Control Study

Background Effective prevention of healthcare-associated infections (HAIs) requires early identification of at-risk patients. There is no score designed to predict HAIs. The present study was aimed to explore an available score, Systemic inflammatory syndrome (SIRS) score, on admission in predicting HAIs among critically ill patients. Methods This study was based on the Medical Information Mart for Intensive Care III (MIMIC III) version 1.4. Patients with HAIs were matched with control patients who had no HAIs in a 1:1 ratio based on age, gender, mechanical ventilation, deep venous catheterization, urethral catheterization, and surgical operation. Subgroup analyses were conducted according to various variables including infection likelihood on admission. The prognostic values of SIRS and infectious SIRS on admission in predicting HAIs were analyzed using logistic regression. Results A total of 2437 patients with HAIs and 2437 matched controls were enrolled in the final analysis. Adjusted odds ratio (ORs) (95% confidence interval [CI]) for HAIs of SIRS scores (1 to 4) on admission was 1.48 (0.77-2.83), 1.86 (0.99-3.47), 2.14 (1.15-3.98), and 2.58 (1.39-4.80). Adjusted ORs (95%CI) for HAIs of SIRS (score≥2) and infectious SIRS were 1.57 (1.27-1.94) and 1.78 (1.52-2.09), respectively. Subgroup analyses showed that SIRS on admission was an independent risk factor for HAIs in patients admitted without definite and probable infection likelihood (OR=1.54, 95%CI 1.28-1.93). However, it was not a risk factor for HAIs inpatients admitted with infection, in non-white patients, and in patients with liver disease or obesity, and in patients who received total parenteral nutrition (TPN) (all P>0.05). In addition, it was showed that infectious SIRS on admission was not a risk factor for HAIs in black patients and in patients with obesity, and those received TPN (all P>0.05). Conclusions Infectious SIRS on admission significantly predicts HAIs among critical illness patients. SIRS on admission was a predictor of HAIs in ICU patients admitted without infection but not in patients admitted with infection.

Risk factor analysis and nomogram for predicting in-hospital mortality in ICU patients with sepsis and lung infection

Background Lung infection is a common cause of sepsis, and patients with sepsis and lung infection are more ill and have a higher mortality rate than sepsis patients without lung infection. We constructed a nomogram prediction model to accurately evaluate the prognosis of and provide treatment advice for patients with sepsis and lung infection. Methods Data were retrospectively extracted from the Medical Information Mart for Intensive Care (MIMIC-III) open-source clinical database. The definition of Sepsis 3.0 [10] was used, which includes patients with life-threatening organ dysfunction caused by an uncontrolled host response to infection, and SOFA score ≥ 2. The nomogram prediction model was constructed from the training set using logistic regression analysis, and was then internally validated and underwent sensitivity analysis. Results The risk factors of age, lactate, temperature, oxygenation index, BUN, lactate, Glasgow Coma Score (GCS), liver disease, cancer, organ transplantation, Troponin T(TnT), neutrophil-to-lymphocyte ratio (NLR), and CRRT, MV, and vasopressor use were included in the nomogram. We compared our nomogram with the Sequential Organ Failure Assessment (SOFA) score and Simplified Acute Physiology Score II (SAPSII), the nomogram had better discrimination ability, with areas under the receiver operating characteristic curve (AUROC) of 0.743 (95% C.I.: 0.713–0.773) and 0.746 (95% C.I.: 0.699–0.790) in the training and validation sets, respectively. The calibration plot indicated that the nomogram was adequate for predicting the in-hospital mortality risk in both sets. The decision-curve analysis (DCA) of the nomogram revealed that it provided net benefits for clinical use over using the SOFA score and SAPSII in both sets. Conclusion Our new nomogram is a convenient tool for accurate predictions of in-hospital mortality among ICU patients with sepsis and lung infection. Treatment strategies that improve the factors considered relevant in the model could increase in-hospital survival for these ICU patients.

Patient Centricity Driving Formulation Innovation: Improvements in Patient Care Facilitated by Novel Therapeutics and Drug Delivery Technologies

Innovative formulation technologies can play a crucial role in transforming a novel molecule to a medicine that significantly enhances patients’ lives. Improved mechanistic understanding of diseases has inspired researchers to expand the druggable space using new therapeutic modalities such as interfering RNA, protein degraders, and novel formats of monoclonal antibodies. Sophisticated formulation strategies are needed to deliver the drugs to their sites of action and to achieve patient centricity, exemplified by messenger RNA vaccines and oral peptides. Moreover, access to medical information via digital platforms has resulted in better-informed patient groups that are requesting consideration of their needs during drug development. This request is consistent with health authority efforts to upgrade their regulations to advance age-appropriate product development for patients. This review describes formulation innovations contributingto improvements in patient care: convenience of administration, preferred route of administration, reducing dosing burden, and achieving targeted delivery of new modalities.