Biomedical Manufacturing Research Articles

Recent advances in shape memory polymeric nanocomposites for biomedical applications and beyond.

Shape memory polymers (SMPs), which initiate shape transformation in response to environmental stimuli, have attracted significant attention in both academic research and technological innovation. The combination of functional nanomaterials and SMPs has led to the emergence of a variety of shape memory polymeric nanocomposites (SMPNs) with multifunctional properties. This has injected new vitality and vigor into fields such as tissue engineering, biomedicine, optical sensing, aerospace and mechanical engineering. In this review article, we present a brief introduction to the fundamentals of SMPs and SMPNs, followed by a discussion of the recent advances in their multifunctional applications in biomedical manufacturing, drug delivery devices, mechanical sensing, micro-engines, etc. The opportunities and challenges in the future development of SMPs are also discussed.

A Cleaner Milling Process Replacing Emulsion Coolant by Cryogenics CO2

AbstractIn manufacturing sector, looking for a balance between environmental and technical efficiency taking into account productivity is mandatory. Some sectors, such as the biomedical manufacturing sector, also needs to consider the cleanness inherent to prosthesis manufacturing processes for avoiding pathogens transfer to the human body, that is, neither chemicals, bacteria, nor uncontrolled metals can be introduced during the surgical intervention. This work here presented stems from the idea of analyzing the cleanness of cryogenic cooling to be applied to medical pieces. For this, several samples were machined using CO2 cryogenic technology and oil emulsions, respectively. In particular, a modified milling tool was used to apply not only efficiently as cutting fluid but also as cleaner fluid. Afterwards, they were analyzed by Scanning Electron Microscope (SEM) with the aim of looking for biological remains. Finally, with the aim of validating the modified tool in which CO2 is introduced axially as internal coolant, its tool life was tested in comparison with a conventional one. The results shown that the use of CO2 as internal coolant significantly improves the cleanness of current machining processes in comparison with the use of oil emulsions and the way in which is injected does not affect to machining performance.

HPR87 Patient Assistance Programs for Genetic Testing: Closing the Underinsurance Gap or Widening Disparities?

Genetic testing has become more efficient and cost-effective, but the cost of genetic services remains a barrier for many patients and contributes to access disparities. In the United States, biomedical manufacturers and charitable patient advocacy programs administer patient assistance programs (PAPs) to help patients pay for higher-priced medical care, including genetic tests. However, there is limited research on the effectiveness of PAPs in reaching patients most in need of financial assistance. This study is among the first to examine how individuals without adequate insurance coverage or the financial capability to pay for testing navigate are able to access PAPs.

Preface

The 6th International Conference on Intelligent Manufacturing and Automation (IMA 2023) took place in Guangzhou, China from January 13th to 15th, 2023 (virtual form). It is committed to bringing professionals and scholars to deliberate on the future of Intelligent Manufacturing and Automation, and bring new horizons and insights to the related researchers and practitioners.With the successful experience of the past 5 years, the 6th International Conference on Intelligent Manufacturing and Automation was an even greater success in 2023. Focusing on “Intelligent Manufacturing and Automation” and related research areas, IMA 2023 brought together leading personnel from all over the world to share views and experiences and exchange ideas, promoted the research and developmental activities in Intelligent Manufacturing and Automation, and facilitated future business or research contacts among all the participants.After months of well preparation and hard work, the proceedings of IMA 2023 covering a bunch of papers, having been checked through rigorous review and processes to meet the requirements of publication, are smoothly published. These papers feature but are not limited to the following topics: Biomedical Manufacturing, Rapid Manufacturing Technologies, Electric Automation, Mechanical Manufacturing and Automation, etc.We had about 80 participations both as speakers and participants, including researchers, teachers, students, industrial experts, and professionals. During the keynote speech part, each keynote speaker was given 30-40 minutes for keynote speech. Among them, Professor Zongmin Ma from North University of China, China performed a keynote speech: Research on the Development Progress and Application of NV Solid-State Atomic Magnetometer. He mainly discussed about the magnetic measurement principle, key measurement technology and integration technology of NV color center in quantum sensing, and put forward the technical development direction for the current technical problems. In addition, he also summarized the preliminary practical applications of NV magnetometers in the fields of geomagnetic detection, nondestructive testing, biomedicine and other fields in recent years. The insightful speeches of each keynote speakers triggered interesting discussions and a good number of informal talks between all the participants.We would like to thank all the participants in the 6th International Conference on Intelligent Manufacturing and Automation. Besides, our special acknowledgement goes to the Journal of Physics: Conference Series, for the endeavor of all its colleagues in publishing this paper volume. May this venture be a spark that ignites many new inventions in the fields of Intelligent Manufacturing and Automation.The Committee of IMA 2023List of Committee Member is available in this pdf.

4D-printed bilayer hydrogel with adjustable bending degree for enteroatmospheric fistula closure.

Recently, four-dimensional (4D) shape-morphing structures, which can dynamically change shape over time, have attracted much attention in biomedical manufacturing. The 4D printing has the capacity to fabricate dynamic construction conforming to the natural bending of biological tissues, superior to other manufacturing techniques. In this study, we presented a multi-responsive, flexible, and biocompatible 4D-printed bilayer hydrogel based on acrylamide-acrylic acid/cellulose nanocrystal (AAm-AAc/CNC) network. The first layer was first stretched and then formed reversible coordination with Fe3+ to maintain this pre-stretched length; it was later combined with a second layer. The deformation process was actuated by the reduction of Fe3+ to Fe2+ in the first layer which restored it to its initial length. The deformation condition was to immerse the 4D construct in sodium lactate (LA-Na) and then expose it to ultraviolet (UV) light until maximal deformation was realized. The bending degree of this 4D construct can be programmed by modifying the pre-stretched lengths of the first layer. We explored various deformation steps in simple and complex constructs to verify that the 4D bilayer hydrogel can mimic the curved morphology of the intestines. The bilayer hydrogel can also curve in deionized water due to anisotropic volume change yet the response time and maximum bending degree was inferior to deformation in LA-Na and UV light. Finally, we made a 4D-printed bilayer hydrogel stent to test its closure effect for enteroatmospheric fistulas (EAFs) in vitro and in vivo. The results illustrate that the hydrogel plays a role in the temporary closure of EAFs. This study offers an effective method to produce curved structures and expands the potential applications of 4D printing in biomedical fields.

Biomedical Machine Maintenance Scheduling

Tissue banks procure approximately 45,000 tissue donations per year, providing nearly 9,000,000 individuals (about half the population of New York) with life-enhancing and life-saving medical procedures. Proper biobank machine maintenance is imperative to this process. Mandatory forms of maintenance are critical to avoid unexpected malfunctions, which can halt operations and render samples unusable. Each machine has a unique reliability rate within the system; although some can quickly be repaired or replaced, many processes rely on limited machinery where even planned downtime can significantly influence the tissue processing. AlloSource, one of the largest tissue manufacturers in the United States, too often schedules these preventive events unnecessarily or inconveniently, resulting in machines breaking down at inopportune times. In response to these inefficiencies we ask, “What is the best consolidated and standardized equipment maintenance schedule that maximizes monthly maintenance events to ensure increased equipment availability while meeting the demand of the biomedical manufacturing network?” We use an optimization model to consider equipment reliability, downtime, availability, and demand to develop a preventive maintenance schedule. Our model focuses on scheduling the maximum number of events the maintenance crew can conduct each month to ensure vital equipment to the allograft process is available, which provides more opportunities for tissue therapies. In doing so, the maintenance crew is also able to complete more events, driving up annual throughput while driving down equipment downtime.

Industry Payments to Nephrologists in the United States.

BackgroundIndustry payments to physicians raise concerns about conflicts of interest that have the potential to impact patient care. In this study, we explored nonresearch and nonownership payments from industry to nephrologists to identify trends in compensation.MethodologyUsing data from the Centers for Medicare and Medicaid Services (CMS), we explored financial relationships between industry and US nephrologists from 2014 to 2018. We analyzed payment characteristics including payment categories, payment distribution among physicians, regional trends, and biomedical manufacturers.ResultsIn this retrospective study, a total of $75,174,999 was paid to nephrologists in the United States during the study period (i.e., 2014-2018). The number of board-certified nephrologists receiving payment from the industry increased from 11,642 in 2014 to 13,297 in 2018. Among board-certified nephrologists, 56% to 63% received industry payments during the study period. The total payments to nephrologists increased from $13,113,512 in 2014 to $16,467,945 in 2017, with consulting fees (24%) and compensation for services other than consulting (35%) being the highest-paid categories. The top 10% of physician beneficiaries collected 90% of the total industry payments.ConclusionsA small proportion of US nephrologists consistently received the majority of industry payments, the value of which grew over the study period.

Beyond the Fingerstick: Complications of Diabetes in the Acutely Ill Patient with Covid-19 with Lessons from Translation Biology and Therapeutics

The affliction that the Coronavirus Disease 2019 (COVID-19) pandemic has placed on the infrastructure of healthcare institutions across the globe permeates to the level of the provider, hampering clinical decision-making capacity and capability. Associated with the latter has been unprecedented, sweeping changes in biomedical equipment manufacturing, triage dynamics, and implementation of medical interventions in a landscape replete with clinical literature attempting to characterize features in COVID-19 patients. Preliminary assessments into the elements of the SARS-CoV-2 virus (the strain of coronavirus responsible for COVID-19) in addition to the delineation of patient flux pertaining to COVID-19 has identified diabetes as a prevalent comorbidity with increased mortality and increased disease burden in the acutely ill. The volume of patients with COVID-19 superimposed upon complicated diabetes exemplifies that insight into this association offers an expanded perspective of diabetes mellitus. Moreover, given the extensive organ compromise seen in COVID-19 in addition to the established notion that diabetes is a systemic syndrome of metabolism, an appraisal of the literature of medical management and precursory findings serve as bearings that help render clinical principles into viable treatments. In this review we investigate the array of contemporary literature surrounding COVID-19 with a perspective centered upon the management of acute diabetes complications, namely diabetic ketoacidosis and hyperosmolar hyperglycemic state, with emphases into translational biology and pharmacotherapeutics.

Plastic residues produced with confirmatory testing for COVID-19: Classification, quantification, fate, and impacts on human health

In March 2020, several international organizations started making recommendations regarding the need for prompt coronavirus-based diagnosis in order to prevent its spread among the world's population. The most widely used test for confirmation of COVID-19 is real-time PCR (RT-PCR). This technique uses plastic supplies in its procedures, which are 100% disposable to avoid cross-contamination and biological risks. The scientific community has become increasingly worried because of the environmental impacts associated with the current COVID-19 pandemic, such as medical plastic residues. We classified and estimated the amount of plastic residues generated as a consequence of COVID-19 diagnostic tests and analyzed the relationships of the plastics generated with number of confirmed cases, population size, and gross domestic product in each country. We evidenced that the RT-PCR generates 37.27 g of plastic residues per sample. All patients COVID-19 tested with RT-PCR have generated 15,439.59 tons of plastic residue worldwide, until August 2020. The plastic residues generated by the COVID-19 tests have no relation with size population or gross domestic product of the countries. There is also no relationship between the plastic residues generated by the COVID-19 tests and the confirmed cases. About 97% of the plastic residues from diagnostic tests for coronavirus are incinerated due to their hazardous nature to humans, but toxic chemicals are released into the environment during the process. In the short term, there is a need to reduce plastic waste and improve controls of gas emissions from incineration plants in countries where there is a deficit. In the long term, biodegradable biomedical manufacturing that are free of releasing toxic chemicals when they are incinerated, must be considered.

Biomedical Manufacturing: A Review of the Emerging Research and Applications

Abstract Biomedical manufacturing, which has seen rapid growth over the past decade, is an emerging research area for the manufacturing community. This growth trajectory is exemplified and coupled with a broadening scope of applications with biomedical manufacturing technology, including advancements in the safety, quality, cost, efficiency, and speed of healthcare service and research. The goal of this topical review is to offer a comprehensive survey of the current state-of-the-art in biomedical manufacturing and to summarize existing opportunities and challenges as a basis to guide future research activities in this emerging area. This article categorizes the key manufacturing process types that are currently being leveraged for the biomedical field of use, including machining, joining, additive manufacturing, and micro-/multi-scale manufacturing. For each of these manufacturing processes, notable applications are cited and discussed to provide insights and perspectives into how manufacturing processes can play an integral role in creating new and more sophisticated healthcare services and products.

Effect of Lack of Fusion Formed during Electron Beam Powder Bed Fusion of Ti-6Al-4V Alloy on Impact Toughness

Selective electron beam melting (EBM), a powder bed-based fusion process of Ti-6Al-4V alloy, is now being applied more and more widely particularly in biomedical and aerospace manufacturing industries. However, how Charpy impact energy (IE) of Ti-6Al-4V is affected by the build direction and lack of fusion (LOF) formed during the EBM process are not sufficiently understood. This information is generally very important in the applications of EBM. In this study, the build direction (BD) and LOF on IE have been studied and the effective factors have been found depending on the notch direction (ND) and thus the crack propagation direction in the microstructure. In this study, the influence of the BD and LOF on Charpy IE has been studied. Three effective factors have been found associated with the ND and thus crack propagation direction. The first factor is the BD which is the IE increases as the angle between the ND and the BD increases. This leads to the result of cracks propagating readily along with the α (hcp) grain boundaries, absorbing less energy. The second factor is LOF to assist crack propagation and this effect is maximized when the ND and the BD coincide. The last factor is the microstructural variances. In vertical samples, the crack has been found to propagate mostly through the α + β colonies and barely propagate in the prior β grain boundaries which leads to an increase in IE. While in the horizontal and 45° built directed samples, the crack propagates in both α + β colonies and the prior β grain boundaries which lead to lower the IE.

The Race for Immunity

MM speaks to the boss of a new state-of-the-art biomedical manufacturing centre about the challenges of developing and producing a viable cure for COVID-19

Industry Payment to Vascular Neurologists: A 6-Year Analysis of the Open Payments Program From 2013 Through 2018.

Background and Purpose- Industry payments to physicians raise concerns regarding conflicts of interest that could impact patient care. We explored nonresearch and nonownership payments from industry to vascular neurologists to identify trends in compensation. Methods- Using Centers for Medicare and Medicaid Services and American Board of Psychiatry and Neurology data, we explored financial relationships between industry and US vascular neurologists from 2013 to 2018. We analyzed payment characteristics, including payment categories, payment distribution among physicians, regional trends, and biomedical manufacturers. Furthermore, we analyzed the top 1% (by compensation) of vascular neurologists with detailed payment categories, their position, and their contribution to stroke guidelines. Results- The number of board certified vascular neurologist increased from 1169 in 2013 to 1746 in 2018. The total payments to vascular neurologist increased from $99 749 in 2013 to $1 032 302 in 2018. During the study period, 16% to 17% of vascular neurologists received industry payments. Total payments from industry and mean physician payments increased yearly over this period, with consulting fee (31.1%) and compensation for services other than consulting (30.7%) being the highest paid categories. The top 10 manufacturers made the majority of the payments, and the top 10 products changed from drug or biological products to devices. Physicians from south region of the United States received the highest total payment (38.72%), which steadily increased. Payments to top 1% vascular neurologists increased from 64% to 79% over the period as payments became less evenly distributed. Among the top 1%, 42% specialized in neuro intervention, 11% contributed to American Heart Association/American Stroke Association guidelines, and around 75% were key leaders in the field. Conclusions- A small proportion of US vascular neurologists consistently received the majority of industry payments, the value of which grew over the study period. Only 11% of the top 1% receiving industry payments have authored American Heart Association/American Stroke Association guidelines, but ≈75% seem to be key leaders in the field. Whether this influences clinical practice and behavior requires further investigation.

Experimental and numerical investigation of cutting forces in micro-milling of polycarbonate glass

Polycarbonates have found important applications in various types of industries including optical, automotive, aerospace, biomedical, and defense manufacturing industries. Conventional mechanical machining has the capability to create complex multi-scale parts and components for various materials including polymeric materials. This study investigates the cutting forces generated during the machining of polycarbonate glass using the micro-milling process. The goal of this research is to machine high quality micro-channels in polycarbonates for microfluidic applications. Both experimental investigation and numerical simulations using the Finite Element Method (FEM) have been carried out to assess the cutting forces generated in three directions during machining of polycarbonate. The effectiveness of tool coating on the reduction of cutting forces has been investigated. It was found that with the careful combination of depth of cut and feed rate, the ductile mode machining of polycarbonate can be achieved, which produces lower cutting forces, that could result in improved surface finish and low tool wear. Both lower and higher of depths of cut were found to generate higher cutting forces due to dragging action and higher tool-workpiece contact area respectively. The Finite Element Method (FEM) was found to be effective in simulating the cutting forces with acceptable range of errors, and thus, could be used to predict cutting forces at the parametric combinations beyond the capacity of the machine or without carrying out further expensive experimentation, for which the chances of tool failure are higher.

IntelliMaV: A cloud computing measurement and verification 2.0 application for automated, near real-time energy savings quantification and performance deviation detection

Energy conservation measures (ECMs) are implemented in all sectors with the objective of improving the efficiency with which energy is consumed. Measurement and verification (M&V) is required to verify the performance of every ECM to ensure its successful implementation and operation. The methodologies implemented to achieve this are currently evolving to a more dynamic state, known as measurement and verification 2.0, through the use of automated and advanced analytics. The primary barrier to the adoption of M&V 2.0 practices are the tools available to practitioners. This paper aims to populate the knowledge gap in the industrial buildings sector by presenting a novel cloud computing-based application, IntelliMaV, that applies advanced machine learning techniques on large datasets to automatically verify the performance of ECMs in near real-time. Additionally, a performance deviation detection system is incorporated, ensuring persistence of savings beyond the typical period of analysis in M&V.IntelliMaV allows M&V practitioners to quantify energy savings with minimum levels of uncertainty by applying powerful analytics to data readily available in industrial facilities. The use of a cloud computing-based architecture reduces the resources required on-site and decreases the time required to train the baseline energy model through the use of parallel processing. The robust nature of the application ensures it is applicable across the broad spectrum of ECMs in the industrial buildings sector. A case study carried out in a large biomedical manufacturing facility demonstrates the ease of use of the application and the benefits realised through its adoption. The energy savings from an ECM were calculated to be 2,353,225 kWh/yr with 25.5% uncertainty at a 90% confidence interval.

Evaluation of bioink printability for bioprinting applications

Three-dimensional (3D) bioprinting, as a freeform biomedical manufacturing approach, has been increasingly adopted for the fabrication of constructs analogous to living tissues. Generally, materials printed during 3D bioprinting are referred as bioinks, which may include living cells, extracellular matrix materials, cell media, and/or other additives. For 3D bioprinting to be an enabling tissue engineering approach, the bioink printability is a critical requirement as tissue constructs must be able to be printed and reproduce the complex micro-architecture of native tissues in vitro in sufficient resolution. The bioink printability is generally characterized in terms of the controllable formation of well-defined droplets/jets/filaments and/or the morphology and shape fidelity of deposited building blocks. This review presents a comprehensive overview of the studies of bioink printability during representative 3D bioprinting processes, including inkjet printing, laser printing, and micro-extrusion, with a focus on the understanding of the underlying physics during the formation of bioink-based features. A detailed discussion is conducted based on the typical time scales and dimensionless quantities for printability evaluation during bioprinting. For inkjet printing, the Z (the inverse of the Ohnesorge number), Weber, and capillary numbers have been employed for the construction of phase diagrams during the printing of Newtonian fluids, while the Weissenberg and Deborah numbers have been utilized during the printing of non-Newtonian bioinks. During laser printing of Newtonian solutions, the jettability can be characterized using the inverse of the Ohnesorge number, while Ohnesorge, elasto-capillary, and Weber numbers have been utilized to construct phase diagrams for typical non-Newtonian bioinks. For micro-extrusion, seven filament types have been identified including three types of well-defined filaments and four types of irregular filaments. During micro-extrusion, the Oldroyd number has been used to characterize the dimensions of the yielded areas of Herschel-Bulkley fluids. Non-ideal jetting behaviors are common during the droplet-based inkjet and laser printing processes due to the local nonuniformity and nonhomogeneity of cell-laden bioinks.

Additive Manufacturing for Health: State of the Art, Gaps and Needs, and Recommendations

Additive manufacturing (AM) involves using computer-controlled machines to fabricate three-dimensional (3D) structural and functional parts layer by layer. To date, ample AM application opportunities exist in the health field. Based on the outcomes at the 2016 National Science Foundation AM for Health workshop, this paper summarizes the current state, gaps and research needs, and recommendations related to AM for health, in particular, hard structure and medical product printing and soft construct bioprinting. Manufacturing-related knowledge gaps and needs mainly fall into the materials, design, process innovation, part characterization, and policy and education categories. Hard structures and medical products can be designed to integrate with tissues, and their gaps and needs are typically related to the material-process-property-functionality relationship. Bioprinting-specific gaps and needs include build material selection and construct design, printed construct preservation, process selection, scalability and modeling, bioprinting-induced cell injury management, postprinting tissue fusion and maturation, and printed construct evaluation. Research recommendations encompass aspects ranging from fundamental research support to development of suitable standards for clinical use of AM products and are summarized in terms of materials, design, process innovation, modeling, characterization, and policy and education. Hard structure and medical product-specific recommendations are mainly related to build materials and structure design. For bioprinting, recommendations are summarized based on preparation, bioprinting process, and postbioprinting treatment. Furthermore, a biomedical manufacturing landscape is proposed, the potential of bioprinting as transformative research is introduced, and manufacturing-related scientific challenges are listed.

Development and application of a machine learning supported methodology for measurement and verification (M&V) 2.0

The foundations of all methodologies for the measurement and verification (M&V) of energy savings are based on the same five key principles: accuracy, completeness, conservatism, consistency and transparency. The most widely accepted methodologies tend to generalise M&V so as to ensure applicability across the spectrum of energy conservation measures (ECM’s). These do not provide a rigid calculation procedure to follow. This paper aims to bridge the gap between high-level methodologies and the practical application of modelling algorithms, with a particular focus on the industrial buildings sector. This is achieved with the development of a novel, machine learning supported methodology for M&V 2.0 which enables accurate and reliable quantification of savings.A novel and computationally efficient feature selection algorithm and powerful machine learning regression algorithms are employed to maximise the effectiveness of available data. The baseline period energy consumption is modelled using artificial neural networks, support vector machines, k-nearest neighbours and multiple ordinary least squares regression. Improved knowledge discovery and an expanded boundary of analysis allow more complex energy systems be analysed, thus increasing the applicability of M&V. A case study in a large biomedical manufacturing facility is used to demonstrate the methodology’s ability to accurately quantify the savings under real-world conditions. The ECM was found to result in 604,527 kWh of energy savings with 57% uncertainty at a confidence interval of 68%. 20 baseline energy models are developed using an exhaustive approach with the optimal model being used to quantify savings. The range of savings estimated with each model are presented and the acceptability of uncertainty is reviewed. The case study demonstrates the ability of the methodology to perform M&V to an acceptable standard in challenging circumstances.

Experimental tests on new titanium alloy interbody cervical cages

Degenerative diseases of the spine, when not solvable with clinical treatments or with suitable stabilization systems, can be cured by means of the technique of arthrodesis through the interbody fusion of two or more vertebrae. The paper deals with the tests carried out on commercial and innovative cervical cages, used in the primary stabilization of the vertebrae, able to maintain the right distance and to assure the interbody fusion. Additive manufacturing (AM) is a powerful new tool offering the necessary competitiveness to the biomedical manufacturing companies, having the possibility to create materials with controlled porosity combined with solid parts, providing to the workpiece excellent capacity in the subsequent phases of osseointegration. Based on the knowledge developed either in the biomechanics of the spine or in the properties of biocompatibility and osseointegration of titanium alloys, MT Ortho has developed some models of cervical cage made from modern additive printing techniques with titanium alloy. Three different cervical cage made of different materials were subjected to static compression test: a commercial cervical intervertebral cage in PEEK and two cervical intervertebral cages in Ti alloy produced by the EBM process by MT Ortho.Tests on the innovative cage produced by EBM have shown encouraging results. From this first preliminary analysis its showed that the mechanical and functional failure of the innovative devices made in melted Ti alloy by EBM is achieved by load values greater than physiological ones of the cervical spine.

The suitability of machine learning to minimise uncertainty in the measurement and verification of energy savings

Accurate energy modelling is a critical step in the measurement and verification (M&V) of energy savings, as a model for consumption in the baseline period is required. Machine learning (ML) algorithms offer an alternative approach to train these models with data-driven techniques. Industrial buildings offer the most challenging environment for the completion of M&V due to their complex energy systems. This paper investigates the novel use of ML algorithms for M&V of energy savings in industrial buildings. This approach enables the extension of the traditional project boundary also. The ML techniques applied consist of bi-variable and multi-variable ordinary least squares regression, decision trees, k-nearest neighbours, artificial neural networks and support vector machines. The prediction performances of the models are validated in the context of a biomedical manufacturing facility to find the optimal model parameters.Results show that models constructed using ML algorithms are more accurate than the conventional approach. A 51.09% reduction in error was achieved using the optimal model algorithm and parameters. The use of a higher measurement frequency reduced the spread of error across the six models. However, further analysis proved the use of more granular data did not always benefit model performance. Results of the sensitivity analysis showed the proposed ML approach to be beneficial in circumstances where missing baseline data limits the model training period length.