A Roadmap for Improving Medicare's Application of Coverage With Evidence Development.

The Centers for Medicare and Medicaid Services' coverage with evidence development (CED) policy allows the agency to provide coverage for an item or service through a National Coverage Determination (NCD), conditional upon an agreement to collect evidence designed to address specific questions or uncertainties. The goals of this policy are to expedite beneficiary access to new items and services and to generate additional evidence on the impact of these items or services for Medicare beneficiaries. However, these goals have not been fully realized because of several issues with the way the policy has been implemented, including (1) a lack of clear criteria for when CED will be applied, (2) examples of CED data collection activities placing unnecessary burdens on clinicians and the potential for undue inducement on beneficiaries, and (3) a lack of clarity around the process and timeline for reconsidering and ending CED requirements. Additionally, there are cases in which the application of CED has failed to improve access to services for certain Medicare beneficiaries because no data collection activity was implemented in response to the CED requirement or because the NCD only allows the technology to be provided and studied in certain centers of excellence. We describe a roadmap for addressing these issues, which includes, for example, developing a framework to guide the application of coverage constraints in NCDs with CED requirements. Once these issues are addressed, the Centers for Medicare and Medicaid Services could consider expanding the use of CED to technologies that are not subject to NCDs.

[An overview of investments in the development of the Russian Medtech market and the prospects for the impact of digitalization in medicine on the economic performance of companies until 2030].

Today, the topic of digitalization, the introduction of innovations based on Big Data, the complexity of technologies due to the introduction of artificial intelligence in medicine and healthcare is one of the most relevant in this industry, undoubtedly contributing to its rapid development. As a result of this development, there is a huge number of services and applications. Internet resources, not only for health tracking (more than 3,500 applications are available by the end of 2023), but also the development of diagnostic resources, telemedicine, etc. Quite quickly, it was the pandemic and its consequences that changed the format of interaction between doctors, communication in the community of doctors, and their interaction with patients. Saving time when making an appointment with a doctor, visiting him, constant monitoring of the condition of patients, becoming better and more multidirectional day by day, make it possible to provide timely, relevant care to more people. The use of artificial intelligence technologies and digital solutions in the field of Russian healthcare opens up great prospects for both doctors and patients, as well as for many government agencies, since the development of regulatory and legal regulation and state control and management of innovations in the field of medicine and healthcare is important. An important factor is that not only government programs for the development of healthcare, but also investments are extremely important for the development of digital medicine.

The Value of Medical Innovation Versus Industry Rewards.

OBJECTIVES: This article provides systematic evidence on the share of the value of health generated by drugs and other healthcare goods and services that accrue to patients on the demand side versus the manufacturers on the supply side. METHODS: We exploit a large data set with > 9000 cost-effectiveness measures for various interventions, which we convert into measures of the shares of the value of improved health appropriated by the supply side using literature estimates of how patients value gains in health. RESULTS: We find that if patients value a quality-adjusted life-year at $450 000 the median share appropriated for drugs on the supply side is approximately 6% and has declined at 0.1% per year between 1997 and 2019. This compares with other healthcare interventions, such as screenings or medical procedures, which have a median value of 9% but decline at 0.3% per year over the same period. If patients value a quality-adjusted life-year at $150 000, the median share appropriated for drugs and other healthcare interventions on the supply side is approximately 18% and 27%, respectively. Our estimates of appropriations are upper bounds, partly due to QALYs not capturing full producer value. CONCLUSIONS: Many policy debates center on the idea that the supply side is capturing too much of the value of the medical innovation that they generate. We find that, for these interventions, a large share of the value of medical innovation accrues to patients on the demand side given that the revenue to innovators is often far less than the patient's value of these medical innovations.

Using early health economic modeling to inform medical innovation development: a soft robotic sock in poststroke patients in Singapore.

OBJECTIVES: Based on a real-world collaboration with innovators in applying early health economic modeling, we aimed to offer practical steps that health technology assessment (HTA) researchers and innovators can follow and promote the usage of early HTA among research and development (R&D) communities. METHODS: The HTA researcher was approached by the innovator to carry out an early HTA ahead of the first clinical trial of the technology, a soft robotic sock for poststroke patients. Early health economic modeling was selected to understand the potential value of the technology and to help uncover the information gap. Threshold analysis was used to identify the target product profiles. Value-of-information analysis was conducted to understand the uncertainties and the need for further research. RESULTS: Based on the expected price and clinical effectiveness by the innovator, the new technology was found to be cost-saving compared to the current practice. Risk reduction in deep vein thrombosis and ankle contracture, the incidence rate of ankle contracture, the compliance rate of the new technology, and utility scores were found to have high impacts on the value-for-money of the new technology. The value of information was low if the new technology can achieve the expected clinical effectiveness. A list of parameters was recommended for data collection in the impending clinical trial. CONCLUSIONS: This work, based on a real-world collaboration, has illustrated that early health economic modeling can inform medical innovation development. We provided practical steps in order to achieve more efficient R&D investment in medical innovation moving forward.

Technical Difficulties: Teaching Critical Philosophical Orientations toward Technology.

Issue: Technological innovation is accelerating, creating less time to reflect on the impact new technologies will have on the medical profession. Modern technologies are becoming increasingly embedded in routine medical practice with far-reaching impacts on the patient-physician relationship and the very essence of the health professions. These impacts are often difficult to predict and can create unintended consequences for medical education. This article is driven by a main question: How do we prepare trainees to critically assess technologies that we cannot foresee and effectively use technology to support equitable and compassionate care? Evidence: We translate insights from the philosophy of technology into a proposal for integrating critical technical consciousness in medical curricula. We identify three areas required to develop critical consciousness with regard to emerging technologies. The first area is technical literacy, which involves not just knowing how to use technology, but also understanding its limitations and appropriate contexts for use. The second area is the ability to assess the social impact of technology. This practice requires understanding that while technification creates new possibilities it can also have adverse, unintended consequences. The third area is critical reflection on the relationship between 'the human' and 'the technical' as it relates to the values of the medical profession and professional identity formation. Human and technology are two sides of the same coin; therefore, thinking critically about technology also forces us to think about what we consider 'the human side of medicine'. Implications: Critical technical consciousness can be fostered through an educational program underpinned by the recognition that, although technological innovation can create new possibilities for healing, technology is never neutral. Rather, it is imperative to emphasize that technology is interwoven with the social fabric that is essential to healing. Like medication, technology can be both potion and poison.

The CASPER preparation program innovation: increasing self-perceived competence and confidence of underrepresented applicants on the novel CASPER Snapshot and CanMEDS roles.

BACKGROUND: Underrepresented Minorities in Medicine (URMMs) may face financial and social limitations when matriculating into medical schools. Performance on situational judgment tests such as Computer-based Assessment for Sampling Personal Characteristics (CASPER) can be enhanced by coaching and mentorship. The CASPER Preparation Program (CPP) coaches URMMs to prepare for the CASPER test. During the coronavirus 2019 pandemic (COVID-19), CPP implemented novel curricula on the CASPER Snapshot and CanMEDS roles. METHODS: Pre and post-program questionnaires were completed by the students, which assessed their: 1) confidence in understanding the CanMEDS roles, and 2) perceived confidence in performing well and their familiarity and preparedness with the CASPER Snapshot. With a second post-program questionnaire, participants' scores on the CASPER test as well as medical school application outcome were also assessed. RESULTS: Participants reported a significant increase in the URMMs' knowledge, self-perceived competency to complete the CASPER Snapshot, and their anxiety significantly decreased. The level of confidence in understanding CanMEDS roles for a career in healthcare increased as well. The majority (91%) agreed that the feedback received from tutors was adequate and the virtual component of the program was beneficial during COVID-19. 51% of students scored in the highest quartile on the CASPER test and 35% received an offer of admission from CASPER-requiring medical schools. CONCLUSION: Pathway coaching programs have the potential to increase confidence and familiarity amongst URMMs for the CASPER tests and CanMEDS roles. Similar programs should be developed with the aim to increase the chances of URMMs matriculating into medical schools.

Overcoming financial and social barriers during COVID-19: A medical student-led medical education innovation.

Background: Underrepresented minorities in medicine (URMM) may face financial and social limitations when applying to medical schools. The computer-based assessment for sampling personal characteristics (CASPER) test is used by many medical schools to assess the nonacademic competencies of applicants. Performance on CASPER can be enhanced by coaching and mentorship, which URMMs often lack, for affordability reasons, when applying to medical schools. Methods: The CASPER Preparation Program (CPP) is a free, online, 4-week program to help URMM prepare for the CASPER test. CPP features free medical ethics resources, homework and practice tests, and feedback from tutors. Two of CPPs major objectives include relieving URMM of financial burdens and increasing their accessibility to mentorship during the COVID-19 pandemic. A program evaluation was conducted using anonymous, voluntary postprogram questionnaires to assess CPPs efficacy in achieving the aforementioned objectives. Results: Sixty URMMs completed the survey. The majority of the respondents strongly agreed or agreed that CPP relieves students of financial burden (97%), is beneficial for applicants with low-socioeconomic statuses (98%), provides students with resources they could not afford (n = 55; 92%), and enables access to mentors during the pandemic (90%). Discussion: Pathway coaching programs, such as the CASPER Preparation Program, have the potential to offer URMMs mentorship and financial relief, and increase their confidence and familiarity with standardized admission tests to help them matriculate into medical schools.

Innovation in crisis: The role of 'exaptive relations' for medical device development in response to COVID-19.

The COVID-19 pandemic has resulted in huge disruption to the healthcare sector. In response to this, there have been collaborative efforts between many different public and private organizations to foster medical innovations. The effect of crisis upon innovation, particularly medical innovation, remains a debatable subject. In addition, the role of inter-personal relations is becoming more widely acknowledged as a critical feature of innovation. Drawing upon exaptation literature, the study aims to understand the nature of the micro-relations within medical innovations that are undertaken in response to COVID-19. The findings of this paper contribute to the limited literature that examines the performance of medical innovation in response to crisis. In addition to confirming the importance of exaptive pools, exaptive events, and exaptive forums in fostering serendipitous developments, the study makes a contribution to theory by identifying a further form of serendipitous encounter that is 'exaptive relations'.

Anthropology of new chronicities: illness experiences under the promise of medical innovation as long-term treatment.

In the introduction to the special issue, Greco and Graber discuss the concept of chronicity and the ways it is used in the contributions to the special issue. Historians have shown that the concept of chronic disease has its origins in policy and has always been fluid and vague; however, the classic literature in sociology and nursing has focused on modelling the evolution of chronic disease rather than on examining the concept itself. In the introduction, chronicity is explored in the ways in which it is transformed by medical innovation. Innovations in biomedicine promise to turn terminal and acute conditions in chronic and to render chronic conditions curable. Even when such promises are not fulfilled, they change the context of the illness and the experiences of patients. In such a context a specific work is required from patients, in terms of adherence to the treatments, but also in terms of pursuing experimental treatments that could make their condition chronic. The introduction offers a critical exploration of the concept of chronicity, highlighting both its fluid definition and the changes linked to medical innovation, and the ways in which it shapes the temporalities and experiences of illness in complex ways that cannot be reduced to simplified schemas and trajectories.

Innovation in emergency medicine; a perspective from a low middle income country, Pakistan.

Creativity and innovation are essential life skills in the 21st century. These skills are even more important in the healthcare sector of a resource limited country like Pakistan. The acquisition and implementation of innovation is necessary in the field of emergency medicine in Pakistan to troubleshoot challenges like rising emergency room visits while facing lack of resources. This article highlights the need of innovation in the field of emergency medicine and some of the activities that took place in our local context to bring innovation to the surface.

Business-as-Usual will not Deliver the COVID-19 Vaccines We Need.

Governments must become active shapers of medical innovation and drive the development of critical health technologies as global health commons. The 'race' for COVID-19 vaccines is exposing the deficiencies of a business-as-usual medical innovation ecosystem driven by corporate interests, not health outcomes. Instead of bolstering collective intelligence, it relies on competition between proprietary vaccines and allows the bar on safety and efficacy to be lowered, risking people's health and undermining their trust.

Innovative Practice, Clinical Research, and the Ethical Advancement of Medicine.

Innovative practice occurs when a clinician provides something new, untested, or nonstandard to a patient in the course of clinical care, rather than as part of a research study. Commentators have noted that patients engaged in innovative practice are at significant risk of suffering harm, exploitation, or autonomy violations. By creating a pathway for harmful or nonbeneficial interventions to spread within medical practice without being subjected to rigorous scientific evaluation, innovative practice poses similar risks to the wider community of patients and society as a whole. Given these concerns, how should we control and oversee innovative practice, and in particular, how should we coordinate innovative practice and clinical research? In this article, I argue that an ethical approach overseeing innovative practice must encourage the early transition to rigorous clinical research without delaying or deferring the development of beneficial innovations or violating the autonomy rights of clinicians and their patients.

Drug-Induced Sedation Endoscopy (DISE) DATA FUSION system: clinical feasibility study.

Drug-induced sleep endoscopy (DISE) is a diagnostic technique for 3D dynamic anatomical visualisation of upper airway obstruction during sedated sleep. There is a lack of standardised procedure and objective measurement associated with information capture, information management, evaluation of DISE findings, treatment planning, and treatment outcomes. The objective of this study is to present clinical feasibility results using a DISE DATA FUSION system for capturing, merging, displaying and storing anatomical data from an endoscopic imaging system and cardiorespiratory data from an anaesthesiological monitoring system simultaneously in real-time during DISE. This prospective cohort study included 20 patients presenting with symptoms of sleep related breathing disorders undergoing drug-induced sedation endoscopy and had volunteered for DISE DATA FUSION system to be used during their DISE assessment. The DISE DATA FUSION system was used to capture, merge, display, and store anatomical changes from an endoscopic imaging system and cardiorespiratory changes from an anaesthesiological monitoring system simultaneously in real time during drug-induced sedation endoscopy assessment. In all 20 patients, anatomical obstructions at different levels of the pharyngeal lumen (soft palate, velum, tonsils, oropharynx lateral wall, base of tongue, and epiglottis) with a different obstruction configuration and severity were captured simultaneously in real time with its associated cardiorespiratory parameters. Furthermore, a composite video consisting of an anatomical image, blood oxygen level, pulse rate, blood pressure, and timestamp was created for every obstructive event. Our system provides a useful and better way of capturing, merging, visualising, and storing anatomical data/physiological data simultaneously during DISE in real time. Furthermore, it enhances the understanding of the impact of the anatomical severity due to the simultaneous display of the cardiovascular parameters at that specific time of anatomical obstruction for optimising surgical decision based on DISE.

Institutionalizing healthcare hackathons to promote diversity in collaboration in medicine.

BACKGROUND: Medical students and healthcare professionals can benefit from exposure to cross-disciplinary teamwork and core concepts of medical innovation. Indeed, to address complex challenges in patient care, diversity in collaboration across medicine, engineering, business, and design is critical. However, a limited number of academic institutions have established cross-disciplinary opportunities for students and young professionals within these domains to work collaboratively towards diverse healthcare needs. METHODS: Drawing upon best practices from computer science and engineering, healthcare hackathons bring together interdisciplinary teams of students and professionals to collaborate, brainstorm, and build solutions to unmet clinical needs. Over the course of six months, a committee of 20 undergraduates, medical students, and physician advisors organized Stanford University's first healthcare hackathon (November 2016). Demographic data from initial applications were supplemented with responses from a post-hackathon survey gauging themes of diversity in collaboration, professional development, interest in medical innovation, and educational value. In designing and evaluating the event, the committee focused on measurable outcomes of diversity across participants (skillset, age, gender, academic degree), ideas (clinical needs), and innovations (projects). RESULTS: Demographic data (n = 587 applicants, n = 257 participants) reveal participants across diverse academic backgrounds, age groups, and domains of expertise were in attendance. From 50 clinical needs presented representing 19 academic fields, 40 teams ultimately formed and submitted projects spanning web (n = 13) and mobile applications (n = 13), artificial intelligence-based tools (n = 6), and medical devices (n = 3), among others. In post-hackathon survey responses (n = 111), medical students and healthcare professionals alike noted a positive impact on their ability to work in multidisciplinary teams, learn from individuals of different backgrounds, and address complex healthcare challenges. CONCLUSIONS: Healthcare hackathons can encourage diversity across individuals, ideas, and projects to address clinical challenges. By providing an outline of Stanford's inaugural event, we hope more universities can adopt the healthcare hackathon model to promote diversity in collaboration in medicine.

An Extended Hackathon Model for Collaborative Education in Medical Innovation.

To support the next generation of healthcare innovators - whether they be engineers, designers, clinicians, or business experts by training - education in the emerging field of medical innovation should be made easily and widely accessible to undergraduate students, graduate students, and young professionals, early in their careers. Currently, medical innovation curricula are taught through semester-long courses or year-long fellowships at a handful of universities, reaching only a limited demographic of participants. This study describes the structure and preliminary outcomes of a 1-2 week "extended hackathon" course that seeks to make medical innovation education and training more accessible and easily adoptable for academic medical centers. Eight extended hackathons were hosted in five international locations reaching 245 participants: Beijing (June 2015 and August 2016), Hong Kong (June 2016, 2017, and 2018), Curitiba (July 2016), Stanford (October 2017), and São Paulo (May 2018). Pre- and post-hackathon surveys asking respondents to self-assess their knowledge in ten categories of medical innovation were administered to quantify the perceived degree of learning. Participants hailed from a diverse range of educational backgrounds, domains of expertise, and academic institutions. On average, respondents (n = 161) saw a greater than twofold increase (114.1%, P < 0.001) from their pre- to post-hackathon scores. In this study, the extended hackathon is presented as a novel educational model to teach undergraduate and graduate students a foundational skillset for medical innovation. Participants reported gaining significant knowledge across all ten categories assessed. To more robustly assess the educational value of extended hackathons, a standardized assessment for medical innovation knowledge needs to be developed, and a larger sample size of participants surveyed.

Research Translation and Emerging Health Technologies: Synthetic Biology and Beyond.

New health technologies are rapidly emerging from various areas of bioscience research, such as gene editing, regenerative medicine and synthetic biology. These technologies raise promising medical possibilities but also a range of ethical considerations. Apart from the issues involved in considering whether novel health technologies can or should become part of mainstream medical treatment once established, the process of research translation to develop such therapies itself entails particular ethical concerns. In this paper I use synthetic biology as an example of a new and largely unexplored area of health technology to consider the ways in which novel health technologies are likely to emerge and the ethical challenges these will present. I argue that such developments require us to rethink conventional attitudes towards clinical research, the roles of doctors/researchers and patients/participants with respect to research, and the relationship between science and society; and that a broader framework is required to address the plurality of stakeholder roles and interests involved in the development of treatments based on novel technologies.

Administration of oral medication by parents at home.

AIMS AND OBJECTIVE: The objective of this study was to determine parents' experiences and problems with administering medication to their children at home. BACKGROUND: Parents' experiences and access to information for the treatment of their children's illnesses at home is necessary for their children's safety. DESIGN: A descriptive cross-sectional study. METHODS: Four hundred parents from children's hospital outpatient clinics were included. A questionnaire was used to determine parents' experiences and problems with administering medication to their children at home. Descriptive statistical analyses were performed using the spss software package (version 22.00). RESULTS: Antipyretics (59%) and antibiotics (25%) were the most commonly used medicines by parents without prescription. Nearly half of the parents stated that they gave liquid medicine with a household spoon. It was found that 54% of the parents whose children refused to take tablets or liquid medicine mixed these medications into foods. Treatment was delayed in 20·7% of the children who refused to take tablets and in 29·1% of the children who refused to take liquid medicine. As a result of the project, a form and device were developed as a solution to the problems experienced by parents while administering oral medication in the home environment. CONCLUSION: The results of the study showed that a significant percentage of the parents did not use the correct equipment to administer medications, used non-prescription medicines, did not administer medications at correct intervals and mixed medication into foods. RELEVANCE TO CLINICAL PRACTICE: Healthcare professionals, especially nurses, should continually evaluate medication administration by parents at home and the readmission rate in the emergency department to further improve children's health.

A Clinically Immersive Medical Innovation Program for US MD Students: Curricular Description and Program Outcomes.

Background: There is growing need for physician-innovators to address the mounting challenges within the US healthcare system. Despite this, there remains a significant gap in understanding of the efficacy of innovation programs for US MD candidates. We present initial program outcomes of a novel, clinically immersive medical innovation program offered to MD candidates at the David Geffen School of Medicine (DGSOM) at UCLA. Methods: A novel clinically immersive medical innovation curriculum was developed based on existing and reputable medical innovation frameworks and tailored for medical students. Curricular topics broadly included clinical ethnography, interviewing techniques, mind mapping, needs formulation and prioritization, quality improvement, intellectual property, reimbursement pathways, solution landscaping and prioritization, regulatory processes. The program was trialed during an unscheduled summer with voluntary enrollees from DGSOM Class of 2024. The traditional four-level Kirkpatrick model was employed to assess program outcomes. Results: Program outcomes were positive on all four Kirkpatrick levels. Students rated enjoyment at 9.5/10 for lectures and 9.1/10 for clinical immersion. Student-perceived confidence in key skills increased by 43%, and 75% of faculty directly perceived improvement in ethnographic skills. Students were highly engaged in both didactics and clinical immersion, discovering on average 2.6 faculty-verified needs per week. Faculty largely felt their students discovered important unmet clinical needs and added value to their clinical practice. Conclusion: We developed and trialed a novel clinically immersive medical innovation curriculum tailored for medical students. This program achieved positive outcomes on all four levels of the Kirkpatrick model. Our findings have driven the local adoption of this program into our institution's medical school curriculum. We hope that the program efficacy demonstrated herein catalyzes more institutions to trial similar medical innovation programs.

We conducted this investigation after recent literature identified a significant gap in our understanding of the role of innovation and entrepreneurship (I&E) programs in the United States (US) medical education. I&E programs are meant to teach the skills necessary to identify and assess ongoing challenges in health care and subsequently formulate a solution for such challenges. The rate of adoption of I&E programs into US medical education has been unexplainably slow, despite a strong reported interest among medical students in learning the associated topics. We sought to answer the question: how effectively can an I&E curriculum be integrated into the traditional US medical doctorate (M.D). curriculum? We designed a novel medical innovation program tailored for medical students and offered this six-week program to 16 M.D. candidates at UCLA during an unscheduled summer. By describing the curriculum in detail and presenting our holistic assessment of program outcomes including learners' feeling, learnings, transference of knowledge, and the program's real-world impact, we demonstrate methods by which medical innovation can effectively be taught to medical students and the impact this may have on our future physician workforce. Our implementation of a quality improvement conceptual framework examining multiple process measures enabled iterative and real-time improvement of the program throughout its offering. Our surveys were administered at regular intervals through the course, thereby allowing iterative feedback from enrolled students to drive course improvement, similar to how quality improvement frameworks incrementally improve outcomes through closed-loop feedback in health care settings. We posit that analogous medical innovation curricula should be increasingly integrated into MD curricula more broadly.

Exploring the Impact of Batch Size on Deep Learning Artificial Intelligence Models for Malaria Detection.

Introduction Malaria is a major public health concern, especially in developing countries. Malaria often presents with recurrent fever, malaise, and other nonspecific symptoms mistaken for influenza. Light microscopy of peripheral blood smears is considered the gold standard diagnostic test for malaria. Delays in malaria diagnosis can increase morbidity and mortality. Microscopy can be time-consuming and limited by skilled labor, infrastructure, and interobserver variability. Artificial intelligence (AI)-based tools for diagnostic screening can automate blood smear analysis without relying on a trained technician. Convolutional neural networks (CNN), deep learning neural networks that can identify visual patterns, are being explored for use in abnormality detection in medical images. A parameter that can be optimized in CNN models is the batch size or the number of images used during model training at once in one forward and backward pass. The choice of batch size in developing CNN-based malaria screening tools can affect model accuracy, training speed, and, ultimately, clinical usability. This study explores the impact of batch size on CNN model accuracy for malaria detection from thin blood smear images. Methods We used the publicly available "NIH-NLM-ThinBloodSmearsPf" dataset from the United States National Library of Medicine, consisting of blood smear images for Plasmodium falciparum. The collection consists of 13,779 "parasitized" and 13,779 "uninfected" single-cell images. We created four datasets containing all images, each with unique randomized subsets of images for model testing. Using Python, four identical 10-layer CNN models were developed and trained with varying batch sizes for 10 epochs against all datasets, resulting in 16 sets of outputs. Model prediction accuracy, training time, and F1-score, an accuracy metric used to quantify model performance, were collected. Results All models produced F1-scores of 94%-96%, with 10 of 16 instances producing F1-scores of 95%. After averaging all four dataset outputs by batch size, we observed that, as batch size increased from 16 to 128, the average combined false positives plus false negatives increased by 15.4% (130-150), and the average model F1-score accuracy decreased by 1% (95.3%-94.3%). The average training time also decreased by 28.11% (1,556-1,119 seconds). Conclusion In each dataset, we observe an approximately 1% decrease in F1-score as the batch size was increased. Clinically, a 1% deviation at the population level can create a relatively significant impact on outcomes. Results from this study suggest that smaller batch sizes could improve accuracy in models with similar layer complexity and datasets, potentially resulting in better clinical outcomes. Reduced memory requirement for training also means that model training can be achieved with more economical hardware. Our findings suggest that smaller batch sizes could be evaluated for improvements in accuracy to help develop an AI model that could screen thin blood smears for malaria.