Hasil untuk "Pharmacy and materia medica"

Ritik Singh Rana, Yogita Ale, Pankaj Pant et al.

Background: Colonic administration of drugs may enhance drug absorption, reduce adverse reactions, and facilitate delivery to specific therapeutic targets. Objective: Delivering pharmaceuticals to the colon poses challenges that require innovative formulation strategies. Methodology: Various formulation approaches have been explored for colon-targeted drug delivery systems. These approaches target the colon using formulation components that interact with GI physiology parameters such as pH, colonic flora, and enzymes. Result and Discussion: The article discussed the various research studies conducted for colon targeting involving novel strategies such as pH-dependent, enzyme-dependent, Ligand-Receptor-based, new technologies, Phloral, and magnetically derived approaches. It also explored the translational technologies, such as in vivo, in vitro, and in silico, which expedite the transition from fundamental research to clinical application and enhance therapeutic outcomes. Conclusion: In conclusion, the most relevant preclinical studies, encompassing in vitro, in vivo, and in silico research, are delineated to facilitate the strategic advancement of novel colon-targeted therapeutics.

Nauman Ismat Butt

Diabetic foot ulcers are moderately severe complications in patients with type 2 Diabetes Mellitus, with peripheral neuropathy and angiopathy often serving as risk factors. This study aimed to examine the clinical characteristics and risk factors linked to diabetic foot ulcers in type 2 diabetes mellitus individuals within the Pakistani demographic. A retrospective cross-sectional design was used, to analyze the medical files of 68 diabetic foot ulcer patients. Data were collected from the Departments of Medicine and Surgery at Chaudhary Muhammad Akram Teaching and Research Hospital, Lahore Pakistan from Sept. to Dec. 2024. Patients’ clinical profiles, including demographic data, diabetes duration, diabetes control, HbA1c levels, and the presence of comorbidities were all evaluated. Out of the 68 patients, 70.6% were male having a mean age of 55.6±11.7 years, and 55.9% had diabetes for seven years or more. With regard to clinical factors, 61.8% had peripheral neuropathy, 58.8% had hypertension, 47.1% had retinopathy, 26.5% had nephropathy, 20.6% had ischemic stroke, 8.8% had ischemic heart disease, and 2.9% had hypothyroidism, with 97.1% showing poor glycemic control. This study identified a high rate of comorbidities in patients with diabetic foot ulcers, with inadequate diabetes control being a major contributing factor. Timely detection and management of diabetes and its complications are crucial to alleviating the impact of diabetic foot ulcers.

Peter Jenniskens, Gerardo J. Soto, Gabriel Goncalves Silva et al.

The Aguas Zarcas (Costa Rica) CM2 carbonaceous chondrite fell during night time in April 2019. Security and dashboard camera video of the meteor were analyzed to provide a trajectory, lightcurve, and orbit of the meteoroid. The trajectory was near vertical, 81° steep, arriving from an ~109° (WNW) direction with apparent entry speed of 14.6 +/- 0.6 km/s. The meteoroid penetrated to ~25 km altitude (5 MPa dynamic pressure), where the surviving mass shattered, producing a flare that was detected by the Geostationary Lightning Mappers on GOES-16 and GOES-17. The cosmogenic radionuclides were analyzed in three recovered meteorites by either gamma-ray spectroscopy or accelerator mass spectrometry (AMS), while noble gas concentrations and isotopic compositions were measured in the same fragment that was analyzed by AMS. From this, the pre-atmospheric size of the meteoroid and its cosmic-ray exposure age were determined. The studied samples came from a few cm up to 30 cm deep in an object with an original diameter of ~60 cm, that was ejected from its parent body 2.0 +/- 0.2 Ma ago. The ejected material had an argon retention age of 2.9 Ga. The object was delivered most likely by the 3:1 or 5:2 mean motion resonances and, without subsequent fragmentation, approached Earth from a low i < 2.8° inclined orbit with perihelion distance q = 0.98 AU close to Earth orbit. The steep entry trajectory and high strength resulted in deep penetration in the atmosphere and a relatively large fraction of surviving mass.

Rana Abu-Farha, Lobna Gharaibeh, Karem H. Alzoubi et al.

Background: Antibiotics have significantly reduced mortality and improved outcomes across various medical fields; however, the rise of antibiotic resistance poses a major challenge, causing millions of deaths annually. Deprescribing, a process that involves discontinuing unnecessary antibiotics, is crucial for combating this threat. This study was designed to assess the knowledge, perceptions, and practices of physicians regarding antibiotic deprescribing in Jordan.Methods: A cross-sectional survey was conducted between January-February 2024 to assess the knowledge, perceptions, and practices of physicians regarding antibiotic deprescribing in Jordan. An electronic questionnaire served as the data collection tool. Descriptive analysis was performed using SPSS software version 26. Additionally, logistic regression analysis was carried out to identify independent factors associated with physicians’ willingness to deprescribe antibiotics.Results: The study involved 252 physicians, primarily male (n = 168, 67.7%), with a median age of 33 years. Regarding antibiotics deprescribing, 21.8% (n = 55) expressed willingness to deprescribe inappropriate antibiotics.High awareness of deprescribing was evident, with 92.9% (n = 234) familiar with the concept, 94% (n = 237) knowledgeable about appropriate situations, and 96.8% (n = 244) recognising its potential benefits. Furthermore, 81.8% (n = 205) reported having received formal training in antibiotics deprescribing, and 85.3% (n = 215) were informed about the availability of deprescribing tools.Physicians highlighted challenges including insufficient time (44.4%, n = 112) and resistance from patients (41.3%, n = 104) and colleagues (42.1%, n = 106). Despite challenges, a significant proportion regularly assessed antibiotic necessity (46.9%, n = 117) and educated patients about antibiotic-related harms (40.5%, n = 102). Logistic regression analysis revealed no significant demographic factors influencing physicians’ willingness to deprescribe antibiotics (p > 0.05).Conclusion: Physicians in Jordan exhibit high awareness of antibiotics deprescribing and recognise its benefits. Challenges such as time constraints and communication barriers need to be addressed to facilitate effective deprescribing practices. Comprehensive guidelines and interdisciplinary collaboration are essential for promoting judicious antibiotic use and combating antimicrobial resistance.

Molham Sakkal, Mosab Arafat, Priya Yuvaraju et al.

Background: Drug release from controlled release delivery systems is influenced by various factors, including the polymer’s grade and the drug’s hydration form. This study aimed to investigate the impact of these factors on the controlled release of theophylline (THN). This research compares the monohydrate form found in branded products with the anhydrous form in generic equivalents, each formulated with different polymer grades. Methods: Quality control assessment was conducted alongside in vitro evaluation, complemented by various analytical techniques such as X-ray diffraction (XRD) and scanning electron microscopy (SEM). Additionally, thermal analyses using differential scanning calorimetry (DSC) and thermogravimetric analysis (TGA) were employed. Results: Quality control assessments demonstrated that the generic tablets exhibited lower average weight and resistance force compared to the branded ones. In vitro tests revealed that generic tablets released contents within 120 min, compared to 720 min for the branded counterpart. Characterization using XRD and SEM identified disparities in crystallinity and particle distribution between the three samples. Additionally, the thermal analysis indicated consistent endothermic peaks across all samples, albeit with minor variations in heat flow and decomposition temperatures between the two products. Conclusions: This study demonstrated that variations in polymer grade and hydration form significantly impact THN release.

Jasmine L. King, Alain Valdivia, Shawn D. Hingtgen et al.

Background/Objectives: Glioblastoma multiforme (GBM) is the most common high-grade primary brain cancer in adults. Despite efforts to advance treatment, GBM remains treatment resistant and inevitably progresses after first-line therapy. Induced neural stem cell (iNSC) therapy is a promising, personalized cell therapy approach that has been explored to circumvent challenges associated with the current GBM treatment. Methods: Herein, we developed a chitosan-based (CS) injectable, biodegradable, in situ forming thermo-responsive hydrogel as a cell delivery vehicle for the treatment of GBM. Tumoricidal neural stem cells were encapsulated in the injectable CS hydrogel as stem cell therapy for treatment of post-surgical GBM. In this report, we investigated the safety of the injectable CS hydrogel in an immune-competent mouse model. Furthermore, we evaluated the persistence and efficacy of iNSC-laden CS hydrogels in a post-surgical GBM mouse model. Results: The injectable CS hydrogel was well tolerated in mice with no signs of chronic local inflammation. Induced neural stem cells (iNSCs) persisted in the CS hydrogels for over 196 days in comparison to 21 days for iNSCs (cell injection) only. GBM recurrence was significantly slower in mice treated with iNSC-laden CS hydrogels with a 50% increase in overall median survival in comparison to iNSCs (cell injection) only. Conclusions: Collectively, we demonstrated the ability to encapsulate, retain, and deliver iNSCs in an injectable CS hydrogel that is well tolerated with better survival rates than iNSCs alone.

Divya Ravikumar, Chaitra R, Shabari Shetty et al.

Background: Alcoholic liver disease (ALD) is a major cause of chronic liver disease worldwide, and it significantly contributes to liver-related mortality on a global scale. These patients often require drug treatment either for liver disease and its complications or for other comorbid conditions. Due to compromised hepatic function and the prevalence of polypharmacy-associated comorbidities, liver disease significantly increases the risk of drug-drug interactions (DDIs) and adverse drug reactions (ADRs). Aims and Objectives: The aim of the study was to determine the potential drug interactions in the pharmacological management of patients with alcoholic liver disease undergoing conservative treatment. Materials and Methods: A descriptive and cross-sectional study was conducted at Victoria Hospital attached to Bangalore Medical College and Research Institute over a period of 3 months. The study analyzed 200 cases of alcoholic liver disease for the presence of potential drug interactions using the LEXICOMP computer program. Results: The study included 200 subjects with alcoholic liver disease. About 92% were males, and 35% were from the age group of 41 to 50 years followed by 28% from 31 to 40 years. Cirrhosis was identified in 53% of the cases. The median number of drugs per patient was 8.8. A total of 118 potential DDIs (pDDIs) were identified averaging 2.5 pDDIs per patient. The common pDDIs were seen with ondansetron, metronidazole, propranolol, rifaximin, and ranitidine. It was noted that polypharmacy exhibited a robust association with the occurrence of drug interactions. The findings highlight a significant association between polypharmacy and the incidence of pDDIs. Conclusion: The complexity of pharmacotherapy in alcoholic liver disease stems from compromised liver function. It is crucial for physicians to be cognizant of the significant DDIs associated with medications used in liver disease treatment, given the heightened susceptibility of these patients to ADRs. [Natl J Physiol Pharm Pharmacol 2024; 14(10.000): 2085-2091]

Rajasekar Rakesh, Shanmugam Rajeshkumar, Anandan Jayasree

IntroductionThe green synthesis of metal oxide nanoparticles using plant extracts has emerged as an eco-friendly method. Titanium dioxide nanoparticles (TiO2NPs) were synthesized using Cissus rotundifolia in this study. Titanium dioxide nanoparticles were utilized in restorative medicine for enhanced medicinal properties and in dental composites for their antimicrobial activities. Cissus rotundifolia is recognized as a medicinal plant due to its diverse properties, including mild laxatives, anti-inflammatory, and hyperglycemic activities. Materials and MethodsThe antimicrobial activity of the prepared nanoparticles against Lactobacillus Sp. and Streptococcus mutans was evaluated using agar well diffusion method. The bactericidal and bacteriostatic activity of the prepared TiO2NPs was examined using time-kill kinetic analysis. ResultsThe prepared nanoparticles exhibited potential antimicrobial activity against Lactobacillus sp. (12 mm) at the highest concentration of 100 µg/mL. The prepared nanoparticles also exhibited excellent bactericidal activity against Lactobacillus Sp. and mild bacteriostatic activity against Staphylococcus mutans at the highest concentration of 100 µg/mL. ConclusionThe synthesized TiO2NPs showed significant antimicrobial activity against dental pathogens. The observed anticariogenic activity shows the potential of nanoparticles for dental applications. Hence, the prepared nanoparticles can be used in the field of dentistry as an antimicrobial agent instead of synthetic drugs causing more side effects.

A. H. Halstian, A. S. Hasanova, H. V. Tarasenko

2-Hydroxybenzyl alcohol is an important active pharmaceutical ingredient for the production of many drugs, in particular gastrodin, which has a wide range of beneficial effects on epilepsy, Alzheimer’s disease, Parkinson’s disease, affective disorders, cerebral ischemia, cognitive disorders. It is known that 2- and 4-hydroxybenzyl alcohols and mixtures of both compounds are obtained by the interaction of phenol with formaldehyde in the presence of basic catalysts. Due to its high reactivity with formaldehyde, the isolation of pure compounds from the reaction mixtures obtained during the interaction of phenol with formaldehyde is a big problem. Isolation of 2-hydroxybenzyl alcohol in pure form from reaction mixtures is possible only using processes that cannot be carried out on an industrial scale and is accompanied by low yields of the target product. It is possible to get rid of these problems by means of the process of direct oxidation of the 2-hydroxytoluene with ozone in the liquid phase since methods of selective ozonation of methylbenzene to the oxygen derivatives are already known. Therefore, the development of a new low-temperature synthesis of 2-hydroxybenzyl alcohol using ozone is an urgent task. The aim of the work is to study the reaction of the oxidation of 2-hydroxytoluene by ozone in a solution of a stop reagent and catalytic impurities of compounds of transition metals and mineral acids for the development of a new method of synthesis of 2-hydroxybenzyl alcohol. Materials and methods. For the experiments, acetic anhydride of p. a. qualification was used; glacial acetic acid of puriss. qualification, which before use was purified by distillation under vacuum in the presence of potassium permanganate, 2-hydroxytoluene of puriss. Qualification, manganese (II) acetate of pur. Qualification, sulfuric and phosphoric acids of puriss. qualification. To determine the concentration of ozone in the gas phase, a spectrophotometric method was used, based on the measurement of the optical density of the gas flow in the UV region. For this purpose, a spectrophotometer SF-46 LOMO was used, in the measuring chamber of which a flow cuvette with quartz windows was installed. The material of the cuvette was Teflon. Continuous monitoring of the current concentration of ozone, with the recording of the analysis results in the form of a kinetic curve, was carried out when ozone-containing gas passed through the curette at a certain wavelength of a monochromatic light source. Results. The reaction of oxidation of 2-hydroxytoluene by ozone in a solution of the stop reagent – acetic anhydride was studied. It was shown that in the presence of sulfuric acid, it was possible to carry out direct ozonation of 2-hydroxytoluene to 2-hydroxybenzyl alcohol, which was formed in the kind of 2-acetoxybenzyl acetate with a yield of 13.0 %. The main products of the reaction under these conditions are aliphatic compounds, which are formed after the destruction of the aromatic ring. The selectivity of oxidation by alcohol was significantly increased when a catalyst – manganese (II) acetate – was added to the system. In its presence, a catalytic system As2O – H2SO4 – Mn(III) was created, which prevents ozonolysis and directed oxidation mainly to the methyl group of the substrate with the formation of 2-acetoxybenzyl acetate with a yield of 63.2 %. Conclusions. An environmentally friendly, low-temperature method for the synthesis of 2-hydroxybenzyl alcohol was developed by conducting the oxidation of 2-hydroxytoluene with ozone in a solution of the stop reagent – acetic anhydride in the presence of sulfuric acid and manganese (II) acetate.

Vanita Dattatraya Revankar, Chitra Ponnusamy, Anbarasu Subramanian et al.

Background: The objective of study was to assess the knowledge and awareness of the management of biological waste (BMW) among undergraduate students of Dental College, Tamilnadu state. Materials and Methods: Among the students of Dental College in Tamilnadu state, India, a cross-sectional observational research was conducted. A pre-designed questionnaire was distributed to the students. Their expertise and awareness of managing biomedical waste were the variables that were investigated. Results: One hundred and eighty students were participated. The male to female ratio was 1:2, and the average age of responders was 19.76 ± 1.03 years. When it comes to information concerning the management of biomedical waste, an average of 60.33% were correct and 39.57% were incorrect. For their knowledge of the same, 81.35% were correct and 18.65% were incorrect. Conclusion: The findings indicated that students had a high degree of knowledge and understanding regarding the management of biomedical waste.

Em-on Chaiprateep, Sabrina Wiemann, Ralph W. Eckert et al.

The influence of size, particle concentration and applied dose (finite vs. infinite dose) on the dermal penetration efficacy of curcumin was investigated in this study. For this, curcumin suspensions with different particle sizes (approx. 20 µm and approx. 250 nm) were produced in different concentrations (0.625–5% (<i>w</i>/<i>w</i>)). The dermal penetration efficacy was determined semi-quantitatively on the ex vivo porcine ear model. The results demonstrated that the presence of particles increases the dermal penetration efficacy of the active compounds being dissolved in the water phase of the formulation. The reason for this is the formation of an aqueous meniscus that develops between particles and skin due to the partial evaporation of water from the vehicle after topical application. The aqueous meniscus contains dissolved active ingredients, and therefore creates a small local spot with a locally high concentration gradient that leads to improved dermal penetration. The increase in penetration efficacy depends on the number of particles in the vehicle, i.e., higher numbers of particles and longer contact times lead to higher penetration efficacy. Therefore, nanocrystals with a high particle concentration were found to be the most suitable formulation principle for efficient and deep dermal penetration of poorly water-soluble active ingredients.

Mesay Dechasa, Legese Chelkeba, Amente Jorise et al.

Background An irrational antibiotic use is a common problem in developing countries like Ethiopia, which makes empiric antibiotics use difficult. It is considered to be the greatest health problem in our time and future unless intervened. Therefore, this study aimed to assess the patterns of antibiotics use among hospitalized adult patients to pave the way for antimicrobial stewardship. Methods A hospital-based prospective observational study was conducted at Jimma Medical Center, southwestern Ethiopia, from 30 October 2020 to 29 January 2021 with 360 adult hospitalized patients participating. A semi-structured questionnaire and consecutive sampling technique was used for data collection. The data were collected through medical record reviews and patient interviews. The collected data were entered into Epi-data and exported to SPSS® version 23.0 for analysis. Days of therapy (DOT) and essential medicine lists “Access, Watch, and Reserve (AWaRe)” antibiotics classification were used to assess antibiotic use pattern among participants. Results The majority of study participants were females (55.3%), attended formal education (59.4%), and live in rural areas (61.4%) with mean age ± (SD) of 37.65 ± (16.75). The overall rate of antibiotics consumption during the study was 111 days of therapy per 100 bed-days and about two-thirds (66%) of the prescribed antibiotics were from the “Watch” group antibiotics. The indicator level of antibiotics use for “Access” group antibiotics was 34% in this study based on the World Health Organization Essential Medicine List. Cephalosporins were the most commonly used class of antibiotics (93.9%). Conclusion Higher antibiotics exposure and their consumption frequently observed among adult hospitalized patients in the study setting. There was a rapid increase in “Watch” group antibiotics use and about two-thirds of the prescribed antibiotics were from this group. The third-generation cephalosporin were the most commonly used class of antibiotics. Generally, higher consumption and inappropriate antibiotics use among hospitalized adult patients showed the need for urgent interventions by implementing Antimicrobial Stewardship Programs in hospitals.

Bo Li, Ali Mostafavi

Improving hurricane preparedness is essential to reduce hurricane impacts. Inherent in traditional methods for quantifying and monitoring hurricane preparedness are significant lags. This study establishes a methodological framework to quantify the extent, timing, and spatial variation of hurricane preparedness at the CBG level using high-resolution location intelligence data. Anonymized cell phone data on visits to POIs for each CBG before 2017 Hurricane Harvey were used to examine hurricane preparedness. Four categories of POI, grocery stores, gas stations, pharmacies and home improvement stores, were identified as having close relationship with hurricane preparedness, and the daily number of visits from each CBG to these four categories of POIs were calculated during preparation period. Two metrics, extent of preparedness and proactivity, were calculated based on the daily visit percentage change compared to the baseline period. The results show that peak visits to pharmacies often occurred in the early stage, whereas the peak of visits to gas stations happened closer to landfall. The spatial and temporal patterns of visits to grocery stores and home improvement stores were quite similar. However, correlation analysis demonstrates that extent of preparedness and proactivity are independent of each other. Combined with synchronous evacuation data, CBGs were divided into four clusters in terms of extent of preparedness and evacuation rate. The clusters with low preparedness and low evacuation rate were identified as hotspots of vulnerability for shelter-in-place households that would need urgent attention during response. The study advances data-driven understanding of human protective actions and provide emergency response managers with novel insights to proactively monitor disaster preparedness, facilitating identifying under-prepared areas and better allocating resources timely.

Armando Silva-Cunha

There have been major advances in the treatment of eye diseases over the last years [...]

Alice C Ceacareanu, Zachary A. P. Wintrob

Identification of the severe acute respiratory syndrome coronavirus 2 in humans toward the end of 2019 triggered a rapid, intensive effort to develop a vaccine. Among the first three COVID-19 vaccines granted emergency use authorization by the U. S. Food and Drug Administration (FDA) were two mRNA vaccines, never used on a large scale in humans, and one replication-incompetent human adenovirus vector vaccine. Since the beginning of the vaccination efforts in December 2020, almost 220,000 adverse events (AEs) have been reported through the Vaccine Adverse Event Reporting System, a reporting platform administered jointly by the FDA and the Centers for Disease Control to monitor vaccine-related AEs. We queried this database twice (04/23/21 and 05/14/21) and identified the AE reports with valid manufacturer-specific lot numbers (n = 76,336), a subset representing 33.54% of the total reported AEs. Using vaccine and demographic characteristics at the time of each query date, a model was generated to predict significant AEs, such as death. Our regression analysis revealed that the average age (IRR 1.08) and the number of doses administered in an assisted living facility (IRR 1.01) were significantly associated with the number of deaths observed in each lot, whereas the proportion of remaining vaccine shelf-life (IRR 1.30) and the vaccine manufacturer (IRR 1.09) were not. Studies such as this one are vital, as one of the best answers to vaccine hesitancy is reliable data confirming that the available COVID-19 vaccines are safe and not associated with a significantly higher risk of AEs than vaccines for other conditions.

Seeprarani Rath, Ashmita Ramanah, Charles Bon et al.

Purpose: The main aim of the current research was to develop and apply a dermatopharmacokinetic (DPK) approach for the bioequivalence assessment of metronidazole (MTZ) topical cream products, indicated in the treatment of rosacea. Methods: A DPK methodology using tape stripping (TS) technique was developed by investigating the factors that may influence the TS results viz. tapes, dose durations, number of tapes to be used, pressure application, dose applied and gravimetric analysis of the tapes. An initial dose duration study was performed on 6 healthy participants to determine an appropriate application time duration using the Emax model. The SC thickness was normalised between participants using TEWL measurements. A pivotal study was conducted using both the arms of 10 healthy human participants to demonstrate the ability of the TS method for bioequivalence assessment by comparing the reference product to itself as a positive control and including products with higher and lower strengths of MTZ to serve as negative controls in order to confirm bioinequivalence. Results: Whereas the reference was found to be bioequivalent when compared to itself, the creams containing 0.56% and 0.95% MTZ (negative controls) were not bioequivalent (bioinequivalent). Furthermore, another product containing 0.75% MTZ was also assessed and was found to be bioequivalent to the reference product. In addition, the use of both forearms of each participant offered an important advantage of significantly reducing the number of human subjects required to demonstrate BE with a high statistical power of > 80%. Conclusion: The data obtained provides compelling evidence that the developed TS method has the potential to be a cost-effective surrogate alternative for lengthy and expensive clinical trials. Consequently, its application can facilitate faster development of generic products which would, in turn, lower the economic burden of healthcare.

Mohammad Amin Morid, Olivia R. Liu Sheng, Kensaku Kawamoto et al.

Objective: To design and assess a method to leverage individuals' temporal data for predicting their healthcare cost. To achieve this goal, we first used patients' temporal data in their fine-grain form as opposed to coarse-grain form. Second, we devised novel spike detection features to extract temporal patterns that improve the performance of cost prediction. Third, we evaluated the effectiveness of different types of temporal features based on cost information, visit information and medical information for the prediction task. Materials and methods: We used three years of medical and pharmacy claims data from 2013 to 2016 from a healthcare insurer, where the first two years were used to build the model to predict the costs in the third year. To prepare the data for modeling and prediction, the time series data of cost, visit and medical information were extracted in the form of fine-grain features (i.e., segmenting each time series into a sequence of consecutive windows and representing each window by various statistics such as sum). Then, temporal patterns of the time series were extracted and added to fine-grain features using a novel set of spike detection features (i.e., the fluctuation of data points). Gradient Boosting was applied on the final set of extracted features. Moreover, the contribution of each type of data (i.e., cost, visit and medical) was assessed. Conclusions: Leveraging fine-grain temporal patterns for healthcare cost prediction significantly improves prediction performance. Enhancing fine-grain features with extraction of temporal cost and visit patterns significantly improved the performance. However, medical features did not have a significant effect on prediction performance. Gradient Boosting outperformed all other prediction models.

Mohammad Amin Morid, Olivia R. Liu Sheng, Kensaku Kawamoto et al.

Objective: To develop an effective and scalable individual-level patient cost prediction method by automatically learning hidden temporal patterns from multivariate time series data in patient insurance claims using a convolutional neural network (CNN) architecture. Methods: We used three years of medical and pharmacy claims data from 2013 to 2016 from a healthcare insurer, where data from the first two years were used to build the model to predict costs in the third year. The data consisted of the multivariate time series of cost, visit and medical features that were shaped as images of patients' health status (i.e., matrices with time windows on one dimension and the medical, visit and cost features on the other dimension). Patients' multivariate time series images were given to a CNN method with a proposed architecture. After hyper-parameter tuning, the proposed architecture consisted of three building blocks of convolution and pooling layers with an LReLU activation function and a customized kernel size at each layer for healthcare data. The proposed CNN learned temporal patterns became inputs to a fully connected layer. Conclusions: Feature learning through the proposed CNN configuration significantly improved individual-level healthcare cost prediction. The proposed CNN was able to outperform temporal pattern detection methods that look for a pre-defined set of pattern shapes, since it is capable of extracting a variable number of patterns with various shapes. Temporal patterns learned from medical, visit and cost data made significant contributions to the prediction performance. Hyper-parameter tuning showed that considering three-month data patterns has the highest prediction accuracy. Our results showed that patients' images extracted from multivariate time series data are different from regular images, and hence require unique designs of CNN architectures.

Ilya V. Derevitskii, Daria A. Savitskaya, Alina Y. Babenko et al.

Thyrotoxicosis (TT) is associated with an increase in both total and cardiovascu-lar mortality. One of the main thyrotoxicosis risks is Atrial Fibrillation (AF). Right AF predicts help medical personal prescribe the correct medicaments and correct surgical or radioiodine therapy. The main goal of this study is creating a method for practical treatment and diagnostic AF. This study proposes a new method for assessing the risk of occurrence atrial fibrillation for patients with TT. This method considers both the features of the complication and the specifics of the chronic disease. A model is created based on case histories of patients with thyrotoxicosis. We used Machine Learning methods for creating several models. Each model has advantages and disadvantages depending on the diagnostic and medical purposes. The resulting models show high results in the different metrics of the prediction of AF. These models interpreted and simple for use. Therefore, models can be used as part of the support and decision-making system (DSS) by medical specialists in the treatment and diagnostic of AF.

José M. Maisog, Wenhong Li, Yanchun Xu et al.

Due to escalating healthcare costs, accurately predicting which patients will incur high costs is an important task for payers and providers of healthcare. High-cost claimants (HiCCs) are patients who have annual costs above $\$250,000$ and who represent just 0.16% of the insured population but currently account for 9% of all healthcare costs. In this study, we aimed to develop a high-performance algorithm to predict HiCCs to inform a novel care management system. Using health insurance claims from 48 million people and augmented with census data, we applied machine learning to train binary classification models to calculate the personal risk of HiCC. To train the models, we developed a platform starting with 6,006 variables across all clinical and demographic dimensions and constructed over one hundred candidate models. The best model achieved an area under the receiver operating characteristic curve of 91.2%. The model exceeds the highest published performance (84%) and remains high for patients with no prior history of high-cost status (89%), who have less than a full year of enrollment (87%), or lack pharmacy claims data (88%). It attains an area under the precision-recall curve of 23.1%, and precision of 74% at a threshold of 0.99. A care management program enrolling 500 people with the highest HiCC risk is expected to treat 199 true HiCCs and generate a net savings of $\$7.3$ million per year. Our results demonstrate that high-performing predictive models can be constructed using claims data and publicly available data alone, even for rare high-cost claimants exceeding $\$250,000$. Our model demonstrates the transformational power of machine learning and artificial intelligence in care management, which would allow healthcare payers and providers to introduce the next generation of care management programs.