Performance and emission characteristics analysis of a CI engine fueled with distilled pyrolytic waste plastic oil/ethanol/diesel blends.

The current energy challenges in agriculture, industry, and transportation are aggravated by insufficient liquid petroleum fuels, strained by rapid depletion, and higher demand in the international market. Existing environmental pollution due to higher fossil fuel consumption, certainly draws the attention of many researchers to identify a better alternative fuel concerning engine efficiency and exhaust emissions. Waste plastic oil (WPO) derived by thermo-catalytic pyrolysis is found to be a promising alternative fuel due to it's similar fuel properties to diesel. WPO contains long-chain hydrocarbons and high-molecular-weight aromatics which can be eliminated by fractional distillation, resulting in the production of distilled waste plastic oil (DPO). Ethanol is added in addition to DPO in the diesel fuel mixture in order to improve combustion for better performance and reduce emissions. The current study focused on the preparation of homogenous fuel mixtures (DPO/ethanol/diesel) to evaluate it's engine efficiency and exhaust emissions as compared to pure diesel and confirmed that it has the potential to be an alternate fuel for the CI engine. Test engine trials were performed to determine the potential engine characteristics, for instance, thermal efficiency, specific fuel consumptions, and exhaust temperature, by using various fuel mixtures (80D10DPO10E, 70D15DPO15E, 60D20DPO20E, 50D25DPO25E) under different loading conditions of the test engine. Major pollutants including unburned hydrocarbon, carbon monoxide, and nitrogen oxides were measured by a standard emission analyzer. The BTE was increased by 3.7%, and the BSFC was 16.67% less for the 60D20DPO20E mixture so as to diesel at full load. CO emission was found to comparatively increase at higher concentrations and decrease at higher loads. Compared to diesel, the NOx and HC emission were shown to be lowered at low loads and increased at higher loads. The study concluded that the fuel mixture of 60D20DPO20E showed the best engine performance and reduced emissions as compared to diesel.

Prediction modeling using artificial neural network (ANN) for the performance and emission characteristics of catalytic co-pyrolytic fuel blended with diesel in a CI engine.

In the present research work, artificial neural network (ANN) is used to model the performance and emission parameters in a four-stroke, single-cylinder diesel engine combusting a blended fuel of diesel and catalytic co-pyrolysis oil produced from seeds of Pongamia pinnata, waste LDPE, and calcium oxide catalyst. The optimum yield of oil obtained was 92.5% at 500 °C temperature. Physical properties of the obtained oil, such as calorific value (44.85 MJ/kg) and density (797 kg/m3), level it by that of diesel while the flash point and fire point were found to be lower than that of pure diesel. An ANN model was then generated for the prediction of performance characteristics (BTE and BSFC) and emission characteristics (NOx and smoke) under varying loads, braking power, brake mean effective pressure, and torque as inputs using the Levenberg-Marquardt back-propagation training technique. The regression coefficients (R2) for BTE, BSFC, smoke, and NOx predictions were determined to be close to unity at 0.99859, 0.99814, 0.96129, and 0.92505, respectively (all values being close to unity). It has been discovered that ANN makes an effective simulation and prediction tool for blended fuels in CI engines. It is also suggested to predict the mechanical efficiency, volumetric efficiency, and CO, CO2, HC emissions using ANN in its future work.

Enhanced remediation of polyaromatic hydrocarbon using agro-industrial waste for biofuel production and environmental pollution mitigation.

In the present study, attention has been paid to the development of economically feasible strategies for enhanced remediation of anthracene and its conversion into biofuels. The strategies developed (B1, B2, B3, and B4) include bagasse and lipid-producing strain Rhodotorula mucilagenosa IIPL32 synthesizing surface active metabolites. The results indicate the highest production of surface-active metabolites in strategies B2, B3, and B4 along with a maximum biodegradation rate. GC-MS analysis affirmed the conversion of anthracene into phthalic acid in all the strategies. Biofuel quality of the lipid produced by the strain showed higher cetane number and improved cold flow property indicating the efficiency of the developed strategies for the production of commercial grade biodiesel. Furthermore, the phytotoxicity study of the spent wash revealed that 50% and 75% diluted spent wash were non-toxic and can be employed for ferti-irrigation. Thus, the study signifies the development of an economically feasible process that can be commercially employed in biofuel industries.

Hospitalization Among Patients Treated With Molnupiravir: A Retrospective Study of Administrative Data.

PURPOSE: Molnupiravir is an oral antiviral agent authorized for emergency use to treat mild to moderate cases of coronavirus disease 2019 (COVID-19) in adults at high risk for progression to severe clinical outcomes. This study aimed to describe patient characteristics and health outcomes in a cohort of adult patients treated with molnupiravir in an outpatient setting in the United States. METHODS: This was a retrospective cohort study of adults identified in the HealthVerity database with a pharmacy claim for molnupiravir between December 24, 2021, and April 14, 2022. Hospitalization and health care use were assessed over the 28 days after the molnupiravir pharmacy claim. FINDINGS: Among 26,554 patients identified, 71.1% were aged ≥50 years and 58.9% were female. A total of 8794 patients (33.1%) had received at least 1 dose of the COVID-19 vaccine. The most prevalent risk factors for severe COVID-19 identified were hypertension (45.1%), steroid and/or immunosuppressant use (39.6%), and being obese or overweight (24.6%), with 79.1% of patients having ≥1 risk factor. The majority (61.0%) of patients were prescribed comedications contraindicated with or had the potential for major drug-drug interactions with ritonavir-containing regimens. Within 28 days after initiating molnupiravir, 3.3% of patients were hospitalized for any cause and 1.7% for COVID-19-related reasons. Among all hospitalized patients, 9.2% were admitted to an intensive care unit, 3.9% received oxygen, and 3.8% required mechanical ventilation. IMPLICATIONS: The majority of patients treated with molnupiravir in early 2022 had at least one risk factor for severe COVID-19 and had comedications that could require treatment modification or monitoring if given a ritonavir-containing regimen. Hospitalization was uncommon after treatment with molnupiravir, with COVID-19-related inpatient admission in <2% of patients. Among those hospitalized, patient use of intensive care and oxygen-based resources was infrequent. The study design, however, does not permit any conclusions regarding the effectiveness of molnupiravir.

Semantically enabling clinical decision support recommendations.

BACKGROUND: Clinical decision support systems have been widely deployed to guide healthcare decisions on patient diagnosis, treatment choices, and patient management through evidence-based recommendations. These recommendations are typically derived from clinical practice guidelines created by clinical specialties or healthcare organizations. Although there have been many different technical approaches to encoding guideline recommendations into decision support systems, much of the previous work has not focused on enabling system generated recommendations through the formalization of changes in a guideline, the provenance of a recommendation, and applicability of the evidence. Prior work indicates that healthcare providers may not find that guideline-derived recommendations always meet their needs for reasons such as lack of relevance, transparency, time pressure, and applicability to their clinical practice. RESULTS: We introduce several semantic techniques that model diseases based on clinical practice guidelines, provenance of the guidelines, and the study cohorts they are based on to enhance the capabilities of clinical decision support systems. We have explored ways to enable clinical decision support systems with semantic technologies that can represent and link to details in related items from the scientific literature and quickly adapt to changing information from the guidelines, identifying gaps, and supporting personalized explanations. Previous semantics-driven clinical decision systems have limited support in all these aspects, and we present the ontologies and semantic web based software tools in three distinct areas that are unified using a standard set of ontologies and a custom-built knowledge graph framework: (i) guideline modeling to characterize diseases, (ii) guideline provenance to attach evidence to treatment decisions from authoritative sources, and (iii) study cohort modeling to identify relevant research publications for complicated patients. CONCLUSIONS: We have enhanced existing, evidence-based knowledge by developing ontologies and software that enables clinicians to conveniently access updates to and provenance of guidelines, as well as gather additional information from research studies applicable to their patients' unique circumstances. Our software solutions leverage many well-used existing biomedical ontologies and build upon decades of knowledge representation and reasoning work, leading to explainable results.

Predicting Measles Outbreaks in the United States: Evaluation of Machine Learning Approaches.

BACKGROUND: Measles, a highly contagious viral infection, is resurging in the United States, driven by international importation and declining domestic vaccination coverage. Despite this resurgence, measles outbreaks are still rare events that are difficult to predict. Improved methods to predict outbreaks at the county level would facilitate the optimal allocation of public health resources. OBJECTIVE: We aimed to validate and compare extreme gradient boosting (XGBoost) and logistic regression, 2 supervised learning approaches, to predict the US counties most likely to experience measles cases. We also aimed to assess the performance of hybrid versions of these models that incorporated additional predictors generated by 2 clustering algorithms, hierarchical density-based spatial clustering of applications with noise (HDBSCAN) and unsupervised random forest (uRF). METHODS: We constructed a supervised machine learning model based on XGBoost and unsupervised models based on HDBSCAN and uRF. The unsupervised models were used to investigate clustering patterns among counties with measles outbreaks; these clustering data were also incorporated into hybrid XGBoost models as additional input variables. The machine learning models were then compared to logistic regression models with and without input from the unsupervised models. RESULTS: Both HDBSCAN and uRF identified clusters that included a high percentage of counties with measles outbreaks. XGBoost and XGBoost hybrid models outperformed logistic regression and logistic regression hybrid models, with the area under the receiver operating curve values of 0.920-0.926 versus 0.900-0.908, the area under the precision-recall curve values of 0.522-0.532 versus 0.485-0.513, and F2 scores of 0.595-0.601 versus 0.385-0.426. Logistic regression or logistic regression hybrid models had higher sensitivity than XGBoost or XGBoost hybrid models (0.837-0.857 vs 0.704-0.735) but a lower positive predictive value (0.122-0.141 vs 0.340-0.367) and specificity (0.793-0.821 vs 0.952-0.958). The hybrid versions of the logistic regression and XGBoost models had slightly higher areas under the precision-recall curve, specificity, and positive predictive values than the respective models that did not include any unsupervised features. CONCLUSIONS: XGBoost provided more accurate predictions of measles cases at the county level compared with logistic regression. The threshold of prediction in this model can be adjusted to align with each county's resources, priorities, and risk for measles. While clustering pattern data from unsupervised machine learning approaches improved some aspects of model performance in this imbalanced data set, the optimal approach for the integration of such approaches with supervised machine learning models requires further investigation.

Optimization of diesel engine performance and emission using waste plastic pyrolytic oil by ANN and its thermo-economic assessment.

The current study focuses on the engine performance and emission analysis of a 4-stroke compression ignition engine powered by waste plastic oil (WPO) obtained by the catalytic pyrolysis of medical plastic wastes. This is followed by their optimization study and economic analysis. This study demonstrates the use of artificial neural networks (ANN) to forecast a multi-component fuel mixture, which is novel and reduces the amount of experimental effort required to determine the engine output characteristics. The engine tests were conducted using WPO blended diesel at various proportions (10%, 20%, 30% by volume) to acquire the required data for training the ANN model, which enables better prediction for the engine performance by making use of the standard back-propagation algorithm. Considering supervised data obtained from repeated engine tests, an artificial intelligence-based model of ANN was designed to select different parameters of performance and emission as output layers; at the same time, engine loading and different blending ratios of the test fuels were taken as the input layers. The ANN model was built up making use of 80% of testing outcomes for training. The ANN model forecasted engine performance and exhaust emission with regression coefficients (R) at 0.989-0.998 intervals and a mean relative error from 0.002 to 0.348%. Such results illustrated the effectiveness of the ANN model for estimating emissions and the performance of diesel engines. Moreover, the economic viability of the use of 20WPO as an alternative to diesel was justified by thermo-economic analysis.

Prediction of persistent chronic cough in patients with chronic cough using machine learning.

Introduction: The aim of this study was to develop and validate prediction models for risk of persistent chronic cough (PCC) in patients with chronic cough (CC). This was a retrospective cohort study. Methods: Two retrospective cohorts of patients 18-85 years of age were identified for years 2011-2016: a specialist cohort which included CC patients diagnosed by specialists, and an event cohort which comprised CC patients identified by at least three cough events. A cough event could be a cough diagnosis, dispensing of cough medication or any indication of cough in clinical notes. Model training and validation were conducted using two machine-learning approaches and 400+ features. Sensitivity analyses were also conducted. PCC was defined as a CC diagnosis or any two (specialist cohort) or three (event cohort) cough events in year 2 and again in year 3 after the index date. Results: 8581 and 52 010 patients met the eligibility criteria for the specialist and event cohorts (mean age 60.0 and 55.5 years), respectively. 38.2% and 12.4% of patients in the specialist and event cohorts, respectively, developed PCC. The utilisation-based models were mainly based on baseline healthcare utilisations associated with CC or respiratory diseases, while the diagnosis-based models incorporated traditional parameters including age, asthma, pulmonary fibrosis, obstructive pulmonary disease, gastro-oesophageal reflux, hypertension and bronchiectasis. All final models were parsimonious (five to seven predictors) and moderately accurate (area under the curve: 0.74-0.76 for utilisation-based models and 0.71 for diagnosis-based models). Conclusions: The application of our risk prediction models may be used to identify high-risk PCC patients at any stage of the clinical testing/evaluation to facilitate decision making.

Planning and Monitoring Equitable Clinical Trial Enrollment Using Goal Programming.

Randomized clinical trial (RCT) studies are the gold standard for scientific evidence on treatment benefits to patients. RCT outcomes may not be generalizable to clinical practice if the trial population is not representative of the patients for which the treatment is intended. Specifically, enrollment plans may not adequately include groups of patients with protected attributes, such as gender, race, or ethnicity. Inequities in RCTs are a major concern for funding agencies such as the National Institutes of Health (NIH) and for policy makers. We address this challenge by proposing a goal-programming approach, explicitly integrating measurable enrollment goals, to design equitable enrollment plans for RCTs. We evaluate our model in both single and multisite settings using the enrollment criteria and study population from the Systolic Blood Pressure Intervention Trial (SPRINT) study. Our model can successfully generate equitable enrollment plans that satisfy multiple goals such as sample representativeness and minimum total financial cost. Our model can detect deviations from a target plan during the enrollment process and update the plan to reduce deviations in the remaining process. Finally, through appropriate site selection in the planning stage, the model can demonstrate the possibility of enrolling a nationally representative study population if geographic constraints exist in multisite recruitment (e.g., clinical centers in a particular region). Our model can be used to prospectively produce and retrospectively evaluate how equitable enrollment plans are based on subjects' protected attributes, and it allows researchers to provide justifications on validity of scientific analysis and evaluation of subgroup disparities.

Efficient valorization of feather waste by Bacillus cereus IIPK35 for concomitant production of antioxidant keratin hydrolysate and milk-clotting metallo-serine keratinase.

Keratinase production by Bacillus cereus IIPK35 was investigated under solid-state fermentation (SSF) and the maximum titer of 648.28 U/gds was revealed. Feather hydrolysates obtained from SSF exhibited paramount antioxidant properties in ABTS [2,2'-azinobis-(3-ethylbenzothiazoline)-6-sulfonic acid], FRAP [Ferric ion reducing antioxidant power], and DPPH [2,2,-Diphenyl-1-picrylhydrazyl] assay. The keratinase was purified up to homogeneity have a molecular weight of 42 kDa, and showed its stability between pH 6.5-10.0 and temperature 35-60 °C with optimum enzyme activity at pH 9.0 and 55 °C. The catalytic indices viz. Km of 9.8 mg/ml and Vmax of 307.7 µmol/min for keratin were determined. Besides keratin, the enzyme displayed broad and proteolytic activity towards other proteinaceous substrates such as casein, skim milk, gelatin, and bovine serum albumin. Pure keratinase activity was stimulated in presence of Ca2+ and Mg2+ ions, while it was strongly inhibited by both iodoacetamide and EDTA, indicating it to be a metallo-serine protease in nature. Circular dichroism study endorses the structural stability of the secondary structure at the said range of pH and temperature. The IIPK35 keratinase is non-cytotoxic in nature, shows remarkable storage stability and is stable in presence of Tween 80, Triton X 100, and sodium sulfite. Furthermore, it showed excellent milk clotting potential (107.6 Soxhlet Unit), suggesting its usefulness as an alternative milk clotting agent in the dairy industry. This study unlocks a new gateway for keratinase investigation in SSF using chicken feathers as substrate and biochemical and biophysical characterization of keratinase for better understanding and implication in industrial applications.

Assessing the Association Between Network-based Provider Communities and Patient Mortality in the Medicare Population with Multiple Chronic Conditions.

Understanding the complexity of care delivery and care coordination for patients with multiple chronic conditions is challenging. Network analysis can model the relationship between providers and patients to find factors associated with patient mortality. We constructed a network by connecting the providers through shared patients, which was then partitioned into tightly connected communities using a community detection algorithm. After adjusting for patient characteristics, the odds ratio of death for one standard deviation increase in degree centrality ratio between primary care providers (PCPs) and non-PCPs was 0.95 (0.92-0.98). Our result suggest that the centrality of PCPs may be a modifiable factor for improving care delivery. We demonstrated that network analysis can be used to find higher order features associated with health outcomes in addition to patient-level features.

Computer vision syndrome, musculoskeletal, and stress-related problems among visual display terminal users in Nepal.

BACKGROUND: The use of computers and other Visual Display Terminal (VDT) screens is increasing in Nepal. However, there is a paucity of evidence on the prevalence of Computer Vision Syndrome (CVS) and other occupational health concerns among employees working in front of VDT screens in the Nepalese population. OBJECTIVES: This study aims to estimate the prevalence of CVS, musculoskeletal and work-related stress among VDT screen users in the office, as well as their understanding and usage of preventive measures. METHODS: The study was a cross-sectional descriptive study among 319 VDT users in office settings in Kathmandu Metropolitan City, Nepal, using a semi-structured self-administered questionnaire. Multivariate logistic regression analysis was conducted to identify the associated factors at 95% CI. P-value <0.05 was considered as statistically significant. RESULTS: The prevalence of CVS was 89.4%. More than eight out of ten study participants reported at least one visual and musculoskeletal symptom. Work-related stress, which was moderate-difficult to handle, was present in 36.7% of the study population. The mean±SD computer usage per day was 7.9±1.9 hours. Tired eye (63.3%), feeling of dry eye (57.8%), headache (56.9%) were the common visual symptoms of CVS reported. Total computer use/day > = 8 hours OR 2.6, improper viewing distance OR 3.2, Not using an anti-glare screen OR 2.6, not using eye-drops, and not wearing protective goggles OR 3.1 were significantly associated with the presence of CVS. There was no statistically significant association between visual symptoms of CVS, musculoskeletal symptoms, and stress with gender. CONCLUSION: CVS was substantially related to not employing preventive measures, working longer hours, and having an incorrect viewing distance. With more hours per day spent in front of a VDT screen, work-related stress and musculoskeletal complaints were also found to be important correlates. Similarly, work-related stress was found more among those who had less than five years of job.

Remediation and detoxification of oil contaminated marine intertidal sites through lipopeptide assisted washing strategy: An experimental and kinetic validation approach.

This paper presents a tightly coupled experimental and kinetic approach for efficient remediation of oil spill from contaminated marine intertidal zone surface through a methodical strategy that deals with biosurfactant mediated washing strategy. The study deals with production, optimization and characterization of lipopeptide biosurfactant from Bacillus subtilis T1 and its application in remediation of oil contaminants from mimic model system of various marine intertidal zone i.e. woodland-Group1, saltmarsh-Group2, mangrove-Group3 and mudflats-Group4. Results demonstrates enhanced washing performance with oil desorption rate of 35 % in Group 4, 17.22 %, 15.6 % and 11 % in Group 3, 2 and 1 along with bio surfactant recovery rate of 41 %, 48.7 %, 51.71 % and 50.3 % respectively. Further, the washing strategy was efficient in soil detoxification with highest rate in Group 4. The kinetic validation depicts good match among experimental data and Lagergren pseudo second order data.

Risk Factors for Persistent Chronic Cough During Consecutive Years: A Retrospective Database Analysis.

BACKGROUND: The identification of patients at high risk for diseases provides clinicians essential information to better manage such patients. Persistent chronic cough (PCC) is a condition with high clinical burden and limited knowledge of the risk factors that drive the persistent symptoms. OBJECTIVE: To understand the risk factors of PCC in patients with CC diagnosed by specialists. METHODS: In this retrospective study, adults aged 18 to 85 years diagnosed with CC by a pulmonologist, allergist, otolaryngologist, or gastroenterologist in the period 2011 to 2016 were identified. PCC was defined by another CC code or at least 2 cough events at least 8 weeks but no more than 4 months apart in each of the 2 consecutive years beginning 1 year after the original CC diagnosis. Unadjusted and adjusted risk ratios with 95% CI for patient characteristics at baseline in relationship to PCC were estimated by Poisson regression models with robust error variance. RESULTS: Of the adults with CC, 3270 (27.4%) had PCC and 5302 (44.5%) did not have CC during follow-up; 3341 (28.1%) had CC in only 1 follow-up year and were excluded from the analysis. Compared with patients without PCC, patients with PCC were noted to have significantly increased adjusted risk ratios for the following baseline features: (1) demographic characteristics (elderly, females, and less educated); (2) comorbidities (chronic obstructive pulmonary disease, chronic sinusitis, bronchiectasis, pulmonary fibrosis, hypertension, depression, and cough complications); (3) medication dispensed (inhaled corticosteroids/long-acting beta-agonists, leukotriene modifiers, nasal corticosteroids, nasal short-acting muscarinic antagonists, proton pump inhibitors, antitussives with narcotics, and neuromodulators); and (4) specialist care, particularly with pulmonologists. CONCLUSIONS: Knowledge of the independent risk factors associated with PCC should aid clinicians in identifying such patients and improve their management.

Bioremediation of petroleum contaminated soil through biosurfactant and Pseudomonas sp. SA3 amended design treatments.

Toxicity of agricultural soil due to petroleum contamination has become a serious issue in recent times. Petrol oil exhibits toxic effects in agricultural crops due to the presence of various hazardous hydrocarbons. The degradation of petroleum hydrocarbon has been widely studied by the researchers that signify the requirement of effective treatments for the detoxification of petroleum contaminated soil and their reuse for growing crops. Hence, with this intention in the present study secondary metabolites "biosurfactant" (natural surfactant) along with the potent plant growth promoting (PGP) bacterial strain Pseudomonas sp. SA3 was used in the designed treatments for growing agricultural crop. The biosurfactant produced by the strain has the emulsification capacity of 43% and surface tension reduction ability to 34.5 mN/m whereas the plant growth promoting traits demonstrates 93.46 µg/mL phosphate solubilisation ability, siderophores (iron chelating compound) production upto 69.41% units and 81.41 µg/mL indole acetic acid  (IAA) production ability. Further, the results of the design treatments signifies that treatments amended with the strain SA3 and biosurfactant is effective in the management of petroleum contaminated soil indicating treatment EX 5 (1 kg soil + 1 L water + Pseudomonas sp. SA3 + 300 mL crude biosurfactant), as an efficient treatment in increment of phytochemical constituents and 10-15% enhancement in growth parameters as compared to negative control. Hence, the developed treatments can be efficaciously used for the management of petroleum contaminated soil for agronomy.

An Audio Personal Health Library of Clinic Visit Recordings for Patients and Their Caregivers (HealthPAL): User-Centered Design Approach.

BACKGROUND: Providing digital recordings of clinic visits to patients has emerged as a strategy to promote patient and family engagement in care. With advances in natural language processing, an opportunity exists to maximize the value of visit recordings for patients by automatically tagging key visit information (eg, medications, tests, and imaging) and linkages to trustworthy web-based resources curated in an audio-based personal health library. OBJECTIVE: This study aims to report on the user-centered development of HealthPAL, an audio personal health library. METHODS: Our user-centered design and usability evaluation approach incorporated iterative rounds of video-recorded sessions from 2016 to 2019. We recruited participants from a range of community settings to represent older patient and caregiver perspectives. In the first round, we used paper prototypes and focused on feature envisionment. We moved to low-fidelity and high-fidelity versions of the HealthPAL in later rounds, which focused on functionality and use; all sessions included a debriefing interview. Participants listened to a deidentified, standardized primary care visit recording before completing a series of tasks (eg, finding where a medication was discussed in the recording). In the final round, we recorded the patients' primary care clinic visits for use in the session. Findings from each round informed the agile software development process. Task completion and critical incidents were recorded in each round, and the System Usability Scale was completed by participants using the digital prototype in later rounds. RESULTS: We completed 5 rounds of usability sessions with 40 participants, of whom 25 (63%) were women with a median age of 68 years (range 23-89). Feedback from sessions resulted in color-coding and highlighting of information tags, a more prominent play button, clearer structure to move between one's own recordings and others' recordings, the ability to filter recording content by the topic discussed and descriptions, 10-second forward and rewind controls, and a help link and search bar. Perceived usability increased over the rounds, with a median System Usability Scale of 78.2 (range 20-100) in the final round. Participants were overwhelmingly positive about the concept of accessing a curated audio recording of a clinic visit. Some participants reported concerns about privacy and the computer-based skills necessary to access recordings. CONCLUSIONS: To our knowledge, HealthPAL is the first patient-centered app designed to allow patients and their caregivers to access easy-to-navigate recordings of clinic visits, with key concepts tagged and hyperlinks to further information provided. The HealthPAL user interface has been rigorously co-designed with older adult patients and their caregivers and is now ready for further field testing. The successful development and use of HealthPAL may help improve the ability of patients to manage their own care, especially older adult patients who have to navigate complex treatment plans.

Quantifying representativeness in randomized clinical trials using machine learning fairness metrics.

OBJECTIVE: We help identify subpopulations underrepresented in randomized clinical trials (RCTs) cohorts with respect to national, community-based or health system target populations by formulating population representativeness of RCTs as a machine learning (ML) fairness problem, deriving new representation metrics, and deploying them in easy-to-understand interactive visualization tools. MATERIALS AND METHODS: We represent RCT cohort enrollment as random binary classification fairness problems, and then show how ML fairness metrics based on enrollment fraction can be efficiently calculated using easily computed rates of subpopulations in RCT cohorts and target populations. We propose standardized versions of these metrics and deploy them in an interactive tool to analyze 3 RCTs with respect to type 2 diabetes and hypertension target populations in the National Health and Nutrition Examination Survey. RESULTS: We demonstrate how the proposed metrics and associated statistics enable users to rapidly examine representativeness of all subpopulations in the RCT defined by a set of categorical traits (eg, gender, race, ethnicity, smoking status, and blood pressure) with respect to target populations. DISCUSSION: The normalized metrics provide an intuitive standardized scale for evaluating representation across subgroups, which may have vastly different enrollment fractions and rates in RCT study cohorts. The metrics are beneficial complements to other approaches (eg, enrollment fractions) used to identify generalizability and health equity of RCTs. CONCLUSION: By quantifying the gaps between RCT and target populations, the proposed methods can support generalizability evaluation of existing RCT cohorts. The interactive visualization tool can be readily applied to identified underrepresented subgroups with respect to any desired source or target populations.

Natural language processing for automated annotation of medication mentions in primary care visit conversations.

OBJECTIVES: The objective of this study is to build and evaluate a natural language processing approach to identify medication mentions in primary care visit conversations between patients and physicians. MATERIALS AND METHODS: Eight clinicians contributed to a data set of 85 clinic visit transcripts, and 10 transcripts were randomly selected from this data set as a development set. Our approach utilizes Apache cTAKES and Unified Medical Language System controlled vocabulary to generate a list of medication candidates in the transcribed text and then performs multiple customized filters to exclude common false positives from this list while including some additional common mentions of the supplements and immunizations. RESULTS: Sixty-five transcripts with 1121 medication mentions were randomly selected as an evaluation set. Our proposed method achieved an F-score of 85.0% for identifying the medication mentions in the test set, significantly outperforming existing medication information extraction systems for medical records with F-scores ranging from 42.9% to 68.9% on the same test set. DISCUSSION: Our medication information extraction approach for primary care visit conversations showed promising results, extracting about 27% more medication mentions from our evaluation set while eliminating many false positives in comparison to existing baseline systems. We made our approach publicly available on the web as an open-source software. CONCLUSION: Integration of our annotation system with clinical recording applications has the potential to improve patients' understanding and recall of key information from their clinic visits, and, in turn, to positively impact health outcomes.

Comparison of Methods to Reduce Bias From Clinical Prediction Models of Postpartum Depression.

Importance: The lack of standards in methods to reduce bias for clinical algorithms presents various challenges in providing reliable predictions and in addressing health disparities. Objective: To evaluate approaches for reducing bias in machine learning models using a real-world clinical scenario. Design, Setting, and Participants: Health data for this cohort study were obtained from the IBM MarketScan Medicaid Database. Eligibility criteria were as follows: (1) Female individuals aged 12 to 55 years with a live birth record identified by delivery-related codes from January 1, 2014, through December 31, 2018; (2) greater than 80% enrollment through pregnancy to 60 days post partum; and (3) evidence of coverage for depression screening and mental health services. Statistical analysis was performed in 2020. Exposures: Binarized race (Black individuals and White individuals). Main Outcomes and Measures: Machine learning models (logistic regression [LR], random forest, and extreme gradient boosting) were trained for 2 binary outcomes: postpartum depression (PPD) and postpartum mental health service utilization. Risk-adjusted generalized linear models were used for each outcome to assess potential disparity in the cohort associated with binarized race (Black or White). Methods for reducing bias, including reweighing, Prejudice Remover, and removing race from the models, were examined by analyzing changes in fairness metrics compared with the base models. Baseline characteristics of female individuals at the top-predicted risk decile were compared for systematic differences. Fairness metrics of disparate impact (DI, 1 indicates fairness) and equal opportunity difference (EOD, 0 indicates fairness). Results: Among 573 634 female individuals initially examined for this study, 314 903 were White (54.9%), 217 899 were Black (38.0%), and the mean (SD) age was 26.1 (5.5) years. The risk-adjusted odds ratio comparing White participants with Black participants was 2.06 (95% CI, 2.02-2.10) for clinically recognized PPD and 1.37 (95% CI, 1.33-1.40) for postpartum mental health service utilization. Taking the LR model for PPD prediction as an example, reweighing reduced bias as measured by improved DI and EOD metrics from 0.31 and -0.19 to 0.79 and 0.02, respectively. Removing race from the models had inferior performance for reducing bias compared with the other methods (PPD: DI = 0.61; EOD = -0.05; mental health service utilization: DI = 0.63; EOD = -0.04). Conclusions and Relevance: Clinical prediction models trained on potentially biased data may produce unfair outcomes on the basis of the chosen metrics. This study's results suggest that the performance varied depending on the model, outcome label, and method for reducing bias. This approach toward evaluating algorithmic bias can be used as an example for the growing number of researchers who wish to examine and address bias in their data and models.

Evaluating artificial intelligence in medicine: phases of clinical research.

Increased scrutiny of artificial intelligence (AI) applications in healthcare highlights the need for real-world evaluations for effectiveness and unintended consequences. The complexity of healthcare, compounded by the user- and context-dependent nature of AI applications, calls for a multifaceted approach beyond traditional in silico evaluation of AI. We propose an interdisciplinary, phased research framework for evaluation of AI implementations in healthcare. We draw analogies to and highlight differences from the clinical trial phases for drugs and medical devices, and we present study design and methodological guidance for each stage.