Pharmaceutical manufacturing scheduling is characterised by batch-based production, strict recipe constraints, and high energy intensity, while existing scheduling approaches often rely on deterministic assumptions and neglect energy-cost considerations. This creates a gap in decision-support tools capable of jointly addressing production efficiency, energy cost, and uncertainty in realistic industrial settings. This work introduces a Constraint Programming (CP) scheduling model to minimise the makespan and electrical energy cost of a batch pharmaceutical manufacturing facility. The model considered uncertainties in processing time, electrical energy consumption and used time-of-use electricity pricing. Uncertainties in processing time and electrical energy consumption were modelled using triangular distribution and linear regression model including normally distributed error term respectively. The problem was formulated as multi-objective optimisation problem. Simulation-optimisation approach utilising Monte Carlo simulation and CP was used to generate a Pareto front between the two objective functions using weighted sum method. The Pareto front was generated by running simulations differed in the processing time, electrical energy consumption and weight of each objective function on parallel CPU cores. Using an industrial case study, the proposed approach identifies schedules with both reduced makespan and substantially lower electrical energy cost compared to the executed production schedule, which represented over 90% of the maximum energy cost on the generated Pareto front. The model can significantly improve the makespan and electrical energy cost compared to the actual schedule, and it can be used to predict the electrical energy cost for a given makespan.

Introduction/Background: Glycaemic Variability (GV) is a widely used measure in managing type 1 diabetes mellitus, describing the fluctuations in blood glucose (BG) levels over time. High GV is linked to chronic complications like micro- and macrovascular diseases. Factors contributing to GV include both external factors (diet, activity, medications) and internal factors (glucose absorption, insulin sensitivity). High GV has also been linked to an increased risk of hypoglycaemia and reduced quality of life. Therefore, minimising GV is an important goal in diabetes management. GV can be measured using various statistics, such as standard deviation, coefficient of variation (CV%), glucose management indicator (GMI), which estimates lab-tested HbA1c, average daily risk range (ADRR) measuring daily risk, high BG index (HBGI) and low BG index (LBGI) for hyperglycaemia hypoglycaemia risk, J-index for glucose control quantification, time in range (TIR), time outside range (TOR), and Glycaemia Risk Index (GRI) summarising glycaemia quality, among other methods. Methods: This study analyses the OhioT1DM dataset using GV metrics from continuous glucose monitoring (CGM), employing a rolling window approach. Each metric assesses a different aspect of GV, quantifying BG control. GMI estimates average BG over 3 months, while ADRR, LBGI, and HBGI classify hypoglycaemia and hyperglycaemia risks into different levels. Additionally, the J-index assesses glucose control using mean and standard deviation, while time in range measures the duration within the target range. GRI provides a comprehensive risk summary. Analysing these metrics collectively offers insights into type 1 diabetes management for individuals using CGM and insulin pump therapy. Each statistic is calculated over a 14-day rolling window, shifting one day at a time. This method captures trends and trajectories for individual statistics effectively. Subsequently, various time series forecasting algorithms are explored including Autoregressive Integrated Moving Average (ARIMA), Seasonal Autoregressive Integrated Moving-Average with Exogenous Regressors (SARIMAX) and Support Vector Regression (SVR) to predict future values, followed by a comparative assessment of these algorithms. Results: Subjects present conflicting results in various diabetes management statistics. While some show GMI within the target range, indicating satisfactory medium to long-term control, the J-index and HBGI suggest inadequate control and high hyperglycaemia risk. This demonstrates the necessity for a comprehensive assessment of metrics for diabetes control evaluation. The conflicting results might stem from statistical biasness towards hypoglycaemia or hyperglycaemia. GRI resolves this by combining both risks of hypoglycaemia and hyperglycaemia. Additionally, analysis by rolling window reveals trends towards an increased risk of hypoglycaemia and hyperglycaemia among specific subjects. Closer examination of the trend lines demonstrates similar trajectories between several metrics. Conclusion: This study holds potential to significantly influence diabetes self-management by offering valuable insights into disease management. Employing various measures of GV allows for a comprehensive analysis of BG control and enhances the understanding of self-management practices. The utilisation of a rolling window not only reveals trends and trajectories but also aids in predicting future values and assessing the risk of complications among individuals with diabetes. The comparison of foundational forecasting algorithms serves as a crucial basis for further investigations and analyses in the respective field.

Background: End-stage liver disease (ESLD) patients carry heavy symptom burdens and risk receiving aggressive and sometimes unwanted care at end of life. Palliative care (PC), which aims to alleviate symptoms and facilitate goal-concordant care in serious illness, may offer substantial benefits for ESLD patients but is not widely provided. Objectives: To assess the impact of PC integrated within hepatology (PCIH) services on health care utilization, advance care planning (ACP), and hospice enrollment. Design: We compared patients who received PCIH (n = 55) to a retrospective cohort (n = 57) receiving usual care in an outpatient hepatology clinic. Setting/Subjects: From June 2016 to November 2017, we enrolled patients receiving care in a U.S. public hospital clinic who met the following inclusion criteria: (1) ESLD with a Model for End-Stage Liver Disease score ≥20, (2) hepatology approval for PC referral, and (3) at least one advanced complication of ESLD. Measurements: We assessed patient demographics, clinical information, health care insurance status, health care utilization, completion of psychosocial assessments, and ACP using two-sided Fisher's exact test and Mann-Whitney U tests. Results: Patients receiving PCIH more frequently had goals of care discussions (87.3% vs. 21.2% p ≤ 0.01), completed ACP documentation (56.4% vs. 7.0%, p ≤ 0.01), psychosocial assessments (98.2% vs. 35.1%, p ≤ 0.01), and hospice enrollment (25.5% vs. 7.0%, p = 0.01). Patients receiving PCIH who were hospitalized also had fewer mean hospitalization days (13 vs. 19.7 days, p ≤ 0.01). Conclusions: Embedding PC services in a hepatology clinic is a promising strategy to improve care for ESLD patients in public hospitals.

A critical strategy of motivating students and improving performance in higher education is communicating timely and personalized feedback (Koenka et al., 2019). The language used to deliver students' progress and what specific intervention can support their learning is hugely impactful especially for students who are struggling. This can also be challenging for the academic community

This work introduces a constraint programming (CP) model to minimise the makespan of a large scheduling problem in batch pharmaceutical manufacturing facilities. The model included campaign manufacturing, sequence-dependent changeover, forbidden product-equipment assignment, non-working periods, limited renewable resources, finite intermediate/non-intermediate storage policies and preemptive and non-preemptive operations. The model was tested by scheduling two real examples. Each example consisted of two cases. Case A used the actual number of workers per shift. Case B involved reorganising the shift pattern of the workers. The results from the model were qualitatively validated and compared with the baseline schedules. The makespan of the first example decreased by 24.35% for case 1.A and 38.63% for case 1.B. The second example reported a 2.17% decrease in makespan for case 2.A and 16.67% decrease for case 2.B. This demonstrates the success of the proposed model as a simulation tool to identify the manufacturing bottlenecks by running what-if scenarios. (c) 2021 Elsevier Ltd. All rights reserved.

PLA (polylactide) is a bioresorbable polymer used in implantable medical and drug delivery devices. Like other bioresorbable polymers, PLA needs to be processed carefully to avoid degradation. In this work we combine in-process temperature, pressure, and NIR spectroscopy measurements with multivariate regression methods for prediction of the mechanical strength of an extruded PLA product. The potential to use such a method as an intelligent sensor for real-time quality analysis is evaluated based on regulatory guidelines for the medical device industry. It is shown that for the predictions to be robust to processing at different times and to slight changes in the processing conditions, the fusion of both NIR and conventional process sensor data is required. Partial least squares (PLS), which is the established 'soft sensing' method in the industry, performs the best of the linear methods but demonstrates poor reliability over the full range of processing conditions. Conversely, both random forest (RF) and support vector regression (SVR) show excellent performance for all criteria when used with a prior principal component (PC) dimension reduction step. While linear methods currently dominate for soft sensing of mixture concentrations in highly conservative, regulated industries such as the medical device industry, this work indicates that nonlinear methods may outperform them in the prediction of mechanical properties from complex physicochemical sensor data. The nonlinear methods show the potential to meet industrial standards for robustness, despite the relatively small amount of training data typically available in high-value material processing.

Monitoring the control of persons with type 1 diabetes based on their history of blood glucose levels is essential for self-management. Persons with diabetes must keep their blood glucose levels in a very narrow glycaemic region (70–180 mg/dl) to avoid hypoglycaemia and hyperglycaemia. An extended period of time in the hypoglycaemic or hyperglycaemic region can lead to short-term and long-term complications, respectively. Many measures have been proposed for the management of diabetes, such as the Glucose Management Indicator (GMI) and the Average Daily Risk Range (ADRR). A major drawback of these measures is that they only address acute (ADRR) or chronic (GMI) complications and provide no information on the trend. This paper proposes a rolling window to calculate ADRR and GMI. Calculating ADRR and GMI using a rolling window results in new data, which provide information on the efficacy of self-management of an individual and their risk trend. Use of a rolling window for the risk analysis provides novel information about the glycaemic variability and can be used for improved personal diabetes management plans. Furthermore, ADRR and GMI are combined to propose four new risk levels, which represents the lowest to the highest probable risk of complications. The analysis was performed on 12 subjects from the OhioT1DM data set. The results presented include a detailed examination and summary of all risks to the subjects and the information about their ADRR and GMI trend.

Determining the uniformity and consistency of droplet size in the dispersed phase is key to emulsion stability. Conventional methods, which include manual microscopic evaluation and laser diffraction, have presented many challenges to achieve an accurate evaluation of droplet dispersion in pharmaceutical emulsions. Artificial intelligence techniques have demonstrated potential in overcoming the subjectivity and time-consumption associated with the manual approaches in industry. A new automated machine learning approach is presented in this study to predict in-process emulsion quality from micrographs. Droplet characteristics are extracted from emulsion micrographs using a histogram-based image segmentation technique. Machine learning classification models are developed, with a selected set of droplet characteristics as predictors, via Random Forest, Multinomial Logistic Regression and Vanilla Neural Network to classify the micrographs into four categories. The hyper-parameters of the models are tuned using 10-fold cross validation. A pixel-based Convolutional Neural Network model is also investigated. Random Forest presented the best accuracy of 99.78% compared to the deep learning models, which presented a bias towards the high frequency classes. The automated machine learning approach demonstrated promising potential for inline emulsion quality evaluation. (C) 2020 The Author(s). Published by Elsevier B.V. on behalf of Institution of Chemical Engineers.

Objectives Although numerous studies have looked at the numeric rating scale (NRS) in chronic pain patients and several studies have evaluated objective pain scales, no known studies have assessed an objective pain scale for use in the evaluation of adult chronic pain patients in the outpatient setting. Subjective scales require patients to convert a subjective feeling into a quantitative number. Meanwhile, objective pain scales utilize, for the most part, the patient's behavioral component as observed by the provider in addition to the patient's subjective perception of pain. This study aims to examine the reliability and validity of an objective Chronic Pain Behavioral Pain Scale for Adults (CBPS) as compared to the traditional NRS. Methods In this cross-sectional study, patients were assessed before and after an interventional pain procedure by a researcher and a nurse using the CBPS and the NRS. Interrater reliability, concurrent validity, and construct validity were analyzed. Results Interrater reliability revealed a fair-good agreement between the nurse's and researcher's CBPS scores, weighted kappa values of 0.59 and 0.65, preprocedure and postprocedure, respectively. Concurrent validity showed low positive correlation for the preprocedure measurements, 0.34 (95% CI 0.16–0.50) and 0.47 (95% CI 0.31–0.61), and moderate positive correlation for the postprocedure measurements, 0.68 (95% CI 0.56–0.77) and 0.67 (95% CI 0.55–0.77), for the nurses and researchers, respectively. Construct validity demonstrated an equally average significant reduction in pain from preprocedure to postprocedure, CBPS and NRS median (IQR) scores preprocedure (4 (2–6) and 6 (4–8)) and postprocedure (1 (0–2) and 3 (0–5)), p < 0.001. Discussion. The CBPS has been shown to have interrater reliability, concurrent validity, and construct validity. However, further testing is needed to show its potential benefits over other pain scales and its effectiveness in treating patients with chronic pain over a long-term. This study was registered with ClinicalTrial.gov with National Clinical Trial Number NCT02882971.

Sustainable manufacturing practices are a dominating consideration for legacy factories. Major attention is being applied to improving current practices to more sustainable ones. This research provides a case study of a batch manufacturing pharmaceutical facility and compares a number of approaches to modelling the electrical energy consumption in the plant. An accurate model of the electrical energy in the facility will allow more sustainable approaches to be developed. This can be achieved by improving current processes to reduce the electrical load. Historical electrical energy data were modelled using traditional time series methods. Historical manufacturing data and the electrical energy data were used to develop machine learning models using a feedforward neural network and a random forest. All of the approaches were then compared. The major challenge posed in model development and validation was acquiring data suitable for machine learning. The manufacturing data were stored in hand-written records. These records needed to be digitised and then go through a number of transformative steps before the data were suitable for modelling. The random forest model successfully modelled the energy profile of the facility. The model can be used to predict and better manage the plant electrical energy load.

Existing techniques in emulsion quality evaluation are found to be highly subjective, time-consuming, and prone to overprocessing. Other conventional droplet analysis techniques such as laser diffraction, which require dilution of samples, introduce an additional complexity to industrial processes. The possibility of developing a fully automated technique for droplet characterization during emulsification holds remarkable potential for overcoming the existing challenges. In this article, a histogram-based image segmentation technique detects droplets from emulsion micrographs. The evolution of droplet characteristics and their significance are studied by performing statistical analysis, and the significant characteristics are selected. The principal component analysis is applied to obtain a reduced set of uncorrelated components from the selected characteristics. The linear discriminant analysis classifies the micrographs into a set of quality categories called target, acceptable, marginal, and unacceptable. The model accuracy is validated using stratified five-fold cross-validation and is successful in classifying the micrographs obtained from two different manufacturing facilities with high accuracy up to 100%. The histogram-based technique is successful in detecting smaller droplets than previously reflected in the literature. The current approach is fully automated and is implemented as a soft-sensor, which supports its real-time deployment into an industrial environment. The entire approach has promising potential in the in-line prediction of emulsion quality leading to more efficient and sustainable manufacturing.

•Describe the design of an embedded palliative care service for non-transplant-eligible end-stage liver disease patients incorporating group visits and case-management.•Discuss the impact of this palliative care delivery strategy on key markers of quality care for end-stage liver disease patients in a safety-net system.•Apply lessons learned from collaboration with a transplant referral service and working with a vulnerable population with exceptionally complex psychosocial needs. Patients with end-stage liver disease (ESLD) in safety-net systems are often ineligible for liver transplantation due to immigration status, lack of insurance, inadequate social support, or active substance misuse. These patients facing terminal illness would benefit from the symptom management, intensive psychosocial support, and advance care planning (ACP) that palliative care (PC) offers. In collaboration with the hepatology department, we embedded PC services in the hepatology clinic of a large safety-net hospital. Assess the impact of PC services on healthcare utilization, ACP, hospice enrollment, and patient/family support. From June 2016 to November 2017, we identified patients meeting the following inclusion criteria: 1) ESLD with MELD-NA score ≥20, 2) approval by a hepatologist for PC referral, 3) at least one serious complication of ESLD (i.e. hepatorenal syndrome, refractory ascites, refractory encephalopathy, history of serious infections). Patients were followed by a PC social worker and a PC nurse practitioner, they attended an ACP group visit, and received case-management by the PC social worker. We compared patients that received PC (n=55) to a retrospective cohort of patients seen in the hepatology clinic (n=57) receiving usual care. More PC patients had goals of care discussions (87% vs. 21% p= <0.0001), completed advance directives or POLST forms (56% vs. 7%, p= <0.0001), had psychosocial assessments (98% vs. 35%, p= <0.0001), and enrolled in hospice (25% vs. 7%, p=0.01). For patients who were hospitalized, the mean number of hospitalization days was lower in the PC group (13 vs. 20 days, p=0.0065). Patients with ESLD who received PC had fewer hospitalization days, more advance care planning, and more hospice utilization compared to usual care.

In pharmaceutical industries, the quality assessment of emulsions is typically based on subjective examination of these samples under the microscope by trained analysts. The major drawbacks of such manual quality assessment include inter-observer variability, intra-observer variability, lack of speed and poor accuracy. In order to address these challenges, an automated approach, based on machine vision and machine learning, is investigated in this study. Micrographs, obtained during an emulsification process, are classified into four quality-based categories named TAMU (target, acceptable, marginal and unacceptable). A machine learning approach using principal component–based discriminant analysis is employed in this study for the classification. This approach is compared with manual classification results obtained for the same set of micrographs using attribute agreement analysis, which is a methodology of assessing the accuracy and precision of an evaluation system. The automated approach is demonstrated to be repeatable, 40% more accurate compared to the least performing analyst and 10% more accurate than the best performing analyst. The results show that the automated classification is superior to manual classification of micrographs with respect to speed (180 times faster), greater accuracy and repeatability. The automated approach, implemented as a soft sensor, integrated with real-time image acquisition can be applied for in situ process monitoring of emulsions. The real-time approach can be used to predict the instantaneous product quality as well as optimum process time required to achieve the desirable droplet characteristics, which will avoid over-processing and wastage of resources in pharmaceutical industries.

A soft sensor has been designed to accurately predict the yield stress of extruded Polylactide (PLA) sheet inline, during extrusion processing using an instrumented slit die. A number of experiments over a wide range of processing conditions have been carried out to develop the soft sensor model. The instrumented slit die had a number of embedded sensors monitoring pressure and temperature. The data collected from the slit die sensors was then used to predict the yield stress of the extruded PLA sheet using machine learning algorithms. The yield stress of the extruded sheet, which was measured offline, is compared to the model predictions to check the performance of the model. The soft sensor has the potential to provide real time feedback into the process and become a Quality Assurance (QA) tool which indicates if a product is going out of specification. This model can lead to reduced scrap rates and lower manufacturing costs by reducing machine downtime and making the process more energy efficient. Soft sensors have the potential to be introduced as part of a smart manufacturing process in keeping with the developments of Industry 4.0.

Sustainable manufacturing is of increasing interest to a large number of batch production facilities. Energy efficiencies achieved through optimized scheduling is a desired target for such facilities. To achieve these energy efficiencies, the initial step is accurately modelling plant energy profiles from historical production schedule data. This poses several challenges as the data required to model plant energy is stored in various sources and does not conform to a common sampling rate or data type. Also, separating the energy consumption caused by plant production from the base load of lighting and HVAC systems is difficult unless each production process is metered adequately. This paper focuses on developing a methodology to deal with the complexities of data collection, data processing and modelling within a pharmaceutical batch production facility. Historical energy and scheduling data have been utilized to generate a model for the site's energy profile. The approach incorporates data science and machine learning tools which pose a possible solution to the problem outlined. The results from this work can feed into an overarching goal of more sustainable manufacturing processes by allowing site energy engineers to predict and better manage plant energy load.

Emulsion quality evaluation using machine vision techniques depends on the efficiency of the image segmentation algorithms. Two different machine vision techniques are investigated to determine their competency in detecting droplets from in-process microscopic images of a cream emulsion. Histogram-based segmentation shows promising potential compared to edge and symmetry detection. A statistical study of the droplet characteristics was conducted. The results demonstrate that the histogram-based approach is more proficient in the progressive analysis of droplet evolution during emulsification. A real-time integration of the technique is proposed, as a soft sensor, to predict the optimum process time and to increase manufacturing efficiency in chemical industries.