Diagnostic Tasks Research Articles

Advancements in AI-driven diagnostic radiology: Enhancing accuracy and efficiency

Background: Healthcare delivery has transformed significantly with the integration of clinical decision support systems (CDS) and medical imaging. Convolutional neural networks (CNNs), a type of artificial intelligence (AI) algorithm, have exhibited remarkable accuracy in discerning intricate patterns and anomalies within medical images, surpassing human capability. Aim: This study aims to explore the impact of AI augmentation on diagnostic tasks, focusing on enhancing sensitivity, accuracy, and interrater agreement across various medical conditions. Additionally, it seeks to investigate how AI simplifies complex processes and integrates with existing technologies, extending its role in CDS systems beyond diagnostic accuracy. Methods: The research examines the effectiveness of AI in interpreting CT imaging and diagnosis. Furthermore, it assesses the integration of AI with radiology to enhance the detection of cerebral hemorrhages on head CT scans in time-pressed clinical settings. The research was performed using search engines such as google scholar and Pubmed. Results: The findings indicate that AI augmentation significantly enhances diagnostic capabilities, improves physician confidence, reduces interpretation time, and optimizes workflow efficiency. AI not only improves accuracy but also simplifies processes, thereby revolutionizing healthcare delivery. Conclusion: As artificial intelligence continues to evolve, its revolutionary potential in healthcare becomes increasingly evident.

EXPERIMENTAL DIAGNOSTICS OF COMMUNICATION AND SPEECH SKILLS OF PRESCHOOL CHILDREN WITH DOWN SYNDROME

The article scientifically substantiates and characterizes the experimental method of psychological-pedagogical study of communication and speech skills in preschool children with Down syndrome. The criteria and indicators of the formation of communication and speech skills in the children of the research group were determined. It was determined that normative indicators of communicative and speech development are the standard for comparing information obtained in the process of diagnostic research. It was established that in the modern scientific publications of Ukraine there are no generalized methods of diagnosing communication and speech abilities in children with Down syndrome. The existing methods of diagnosis are singled out, which are used in an adapted and modified form to study the state of formation of individual components of the speech system and communication skills. The diagnostic methodology includes successive stages of research: analysis of the content of medical and psychological-pedagogical documentation; questionnaires and surveys of parents and correctional teachers; indirect (hidden) observation of independent behavior of children with this genetic anomaly; testing in artificially created conditions. The structure of a complex diagnostic study of the state of formation of communication and speech skills in children with this genetic anomaly is characterized. The elements of each component of communicative and speech development are singled out, according to which the psychological and pedagogical study is carried out. Special diagnostic tasks are proposed for studying the state of formation of the cognitive-linguistic component of communicative-speech development. A general level base is proposed, which subordinates the level of formation of communication and speech skills in preschool children with Down syndrome (low, medium, sufficient, high). It was established that each level depends on the presence of different forms of speech, understanding of spoken speech, the volume of passive and active vocabulary, the ability to establish interpersonal contacts and maintain them, the use of existing communication skills to regulate relations with other people, the ability to distinguish the emotional states of the interlocutor.

Between Donating and Alienating: Face Transplants and the Problem of Biomedical Objectification of Human Being

The paper addresses some philosophical aspects of face transplantation and starts with a brief overview of more or less successful surgeries in international clinical practice. Related discussions about medical and ethical risks are also brought into the picture. The issue of the ethical and axiological grounds and consequences of face allotransplantation is placed into the context of a broader problem of biomedical objectification. The author suggests understanding the biomedical objectification in that the patient is regarded as a clinical body taken out of the psychosocial context of her/his life, considered redundant for diagnostic and therapeutic tasks. This view finds expression in various practices that alienate the patient’s subjectivity, including the alienation of her/his name, face or body from her/his personality. Within the existent donation practices, two types of biomedical objectification can be outlined, such as instrumentalisation and alienation for protective purposes. In terms of face transplant, objectification as instrumentalisation consists in reducing the face to a collection of tissues and turning it into a biomedical artifact endowed with instrumental value. In this context, the distinction between the notions of “somatic face” (facial structures) and “psychosocial face” (subject identity) is introduced. As for alienation for protective purposes, the recipient who has to adjust to her/his new face is required to detach from the donor’s personality. The author concludes that face transplantation, similar to donation practices in general, may cause the tension between the rhetoric of gift-giving, essential for the development of transplantology, and the logic of alienation inherent in biomedicine.

P.110 Evaluating AI performance in written neurosurgery exams: a comparative analysis of large language models

Background: The integration of Artificial Intelligence (AI) in medical education is an area of growing importance. While AI models have been evaluated extensively in multiple-choice question formats, their proficiency in written exams remains to be explored. Methods: Four AI models—GPT-4 (OpenAI), Claude-2.1 (Anthropic), Gemini Pro (Google), and Perplexity 70B (Perplexity)—were tested using the Canadian Royal College Sample Neurosurgery Exam. The written exam covered diagnostic reasoning, knowledge of neurosurgical conditions, and understanding of radiographic imaging techniques. Results: GPT-4 and Perplexity 70B both achieved a score of 68.42%, followed by Claude-2.1 with 60.53%, and Gemini Pro with 57.89%. The models showed proficiency in answering questions that required factual knowledge, such as identifying pathogens in spinal epidural abscess. However, they struggled with more complex diagnostic reasoning tasks, particularly in explaining the pathophysiology behind a sudden rise in blood pressure during surgery and interpreting radiographic characteristics of intracranial abscesses on MRI. Conclusions: The findings indicate that while AI models like GPT-4 and Perplexity 70B are adept at handling factual neurosurgical questions, their performance in complex diagnostic reasoning in a written format is less consistent. This underscores the need for more advanced and specialized AI training, particularly in the nuances of medical diagnostics and decision-making.

Practical Application of Deep Learning in Diagnostic Neuropathology-Reimagining a Histological Asset in the Era of Precision Medicine.

In the past few decades, neuropathology has experienced several paradigm shifts with the introduction of new technologies. Deep learning, a rapidly progressing subfield of machine learning, seems to be the next innovation to alter the diagnostic workflow. In this review, we will explore the recent changes in the field of neuropathology and how this has led to an increased focus on molecular features in diagnosis and prognosis. Then, we will examine the work carried out to train deep learning models for various diagnostic tasks in neuropathology, as well as the machine learning frameworks they used. Focus will be given to both the challenges and successes highlighted therein, as well as what these trends may tell us about future roadblocks in the widespread adoption of this new technology. Finally, we will touch on recent trends in deep learning, as applied to digital pathology more generally, and what this may tell us about the future of deep learning applications in neuropathology.

Enhancing brain tumor detection in MRI images through explainable AI using Grad-CAM with Resnet 50

This study addresses the critical challenge of detecting brain tumors using MRI images, a pivotal task in medical diagnostics that demands high accuracy and interpretability. While deep learning has shown remarkable success in medical image analysis, there remains a substantial need for models that are not only accurate but also interpretable to healthcare professionals. The existing methodologies, predominantly deep learning-based, often act as black boxes, providing little insight into their decision-making process. This research introduces an integrated approach using ResNet50, a deep learning model, combined with Gradient-weighted Class Activation Mapping (Grad-CAM) to offer a transparent and explainable framework for brain tumor detection. We employed a dataset of MRI images, enhanced through data augmentation, to train and validate our model. The results demonstrate a significant improvement in model performance, with a testing accuracy of 98.52% and precision-recall metrics exceeding 98%, showcasing the model’s effectiveness in distinguishing tumor presence. The application of Grad-CAM provides insightful visual explanations, illustrating the model’s focus areas in making predictions. This fusion of high accuracy and explainability holds profound implications for medical diagnostics, offering a pathway towards more reliable and interpretable brain tumor detection tools.

VOLTA: an enVironment-aware cOntrastive ceLl represenTation leArning for histopathology

In clinical oncology, many diagnostic tasks rely on the identification of cells in histopathology images. While supervised machine learning techniques necessitate the need for labels, providing manual cell annotations is time-consuming. In this paper, we propose a self-supervised framework (enVironment-aware cOntrastive cell represenTation learning: VOLTA) for cell representation learning in histopathology images using a technique that accounts for the cell’s mutual relationship with its environment. We subject our model to extensive experiments on data collected from multiple institutions comprising over 800,000 cells and six cancer types. To showcase the potential of our proposed framework, we apply VOLTA to ovarian and endometrial cancers and demonstrate that our cell representations can be utilized to identify the known histotypes of ovarian cancer and provide insights that link histopathology and molecular subtypes of endometrial cancer. Unlike supervised models, we provide a framework that can empower discoveries without any annotation data, even in situations where sample sizes are limited.

Scattering moment matching-based interpretable domain adaptation for transfer diagnostic tasks

One significant fact familiar to the signal processing-based diagnostic community but generally ignored by the transfer learning-based diagnostic community is that the cyclostationarity of the monitored signal conveys the actual diagnostic information. Popular network architectures, e.g., ResNet, and domain discrepancy metrics, e.g., maximum mean discrepancy, in current transfer diagnostic research are generally borrowed from the transfer learning community yet do not explicitly consider machine fault physics. As Jérôme Antoni points out, signal processing and machine learning methods are not mutually exclusive but should complement each other. The current article aims to develop an interpretable domain adaptation method for transfer diagnostic tasks by simultaneously exploiting the ideas of cyclostationary signal processing and domain adaptation techniques. By taking NTScatNet as the network backbone and scattering moment distance as the domain discrepancy metric, the proposed scattering moment matching-based domain adaptation method is more interpretable and matches fault physics better than conventional deep transfer learning methods. Besides, the proposed method does not require target domain data during the training phase, thus relaxing the assumption of standard domain adaptation. The effectiveness and superiority of the proposed domain adaptation method were verified on four transfer diagnostic case studies, i.e., transfer diagnostic across bearing specifications, transfer diagnostic across escalator roller specifications, transfer diagnostic across transducers on bearing datasets, and transfer diagnostic across transducers on the gearbox datasets.

Use of forensic examination opportunities during the investigation of corruption criminal offenses committed by judges

The article emphasizes the significant pre-trial importance of forensic examinations in investigating corrupt criminal offenses as one of the forms of utilizing specialized knowledge. The authors disclose the definition of forensic examination. Based on the works of criminologists, survey results from practitioners, and the study of verdicts from the Higher Anti-Corruption Court, it was established that forensic examinations are assigned to state specialized expert institutions but to various subjects of forensic activity. A list of forensic examinations types, primarily appointed in the investigation of criminal offenses committed by judges, is also identified. The most common types of forensic examinations in the investigation of corruption criminal offenses committed by judges are considered. The authors emphasize the importance of forensic criminalistic examination of audio and video materials, forensic document examination, forensic portrait examination, forensic handwriting examination, forensic computer-technical examination, forensic dactyloscopic examination, psychological examination, and forensic linguistic (semantic-textual) examination. It is outlined that conducting examinations in corruption-related proceedings is an effective means of determining the crime mechanism, identifying comparative sample and traces of the suspect, and the subject of the unlawful benefit. The main tasks set for the expert to solve during the investigation of corruption criminal offenses committed by judges are systematized. In the modern context, attention is focused on solving identification and diagnostic tasks. All these achievements are substantiated by statistical data results and interviews with practitioners, as well as through the analysis of criminal proceedings in the specified category of offenses.

ПОДХОД К ОЦЕНКЕ ЧАСТОТЫ СПЕКТРАЛЬНОЙ СОСТАВЛЯЮЩЕЙ ЦИФРОВОГО СИГНАЛА ПО СПЕКТРУ С НИЗКИМ РАЗРЕШЕНИЕМ

This paper examines certain methods of obtaining the exact frequency of the spectral component from the signal spectrum with insufficient resolution in order to clarify the accuracy of these methods and their applicability. The basic principles and the sequence of actions are given for the implementation of parabolic interpolation and frequency demodulation. These methods are applied to a synthesized signal containing a frequency component that cannot be determined directly from a low-resolution spectrum. The methods considered differ in the complexity of calculations and the accuracy of the results obtained. An introduction is made about the applicability of the considered methods for various tasks of vibration diagnostics. Purpose of the study. The article examines methods for obtaining an accurate frequency of a spectral component from a signal spectrum with insufficient resolution. The aim of the study is to determine the accuracy and applicability of the described methods. Materials and methods. The following methods were used to achieve the stated goal: parabolic interpolation and frequency demodulation. The article presents the basic principles and sequence of actions for implementing these methods. To verify the effectiveness of the used methods, a signal was synthesized containing a frequency component that cannot be directly determined from a low-resolution spectrum. Results. The methods of parabolic interpolation and frequency demodulation were applied to the synthesized signal. The results showed that the specified methods allow obtaining accurate values of the frequency of the spectral component even at low spectrum resolution. The considered methods differ in computational complexity and the accuracy of the obtained results. Conclusion. Based on the conducted research, it can be concluded that the methods of parabolic interpolation and frequency demodulation are effective for obtaining an accurate frequency of a spectral component from a signal spectrum with insufficient resolution. The results of the study can be used in various vibration diagnostics tasks. The conclusion notes that the choice of a specific method depends on the complexity of the calculations and the required accuracy of the results.

Chemical fault diagnosis network based on single domain generalization

Recent developments in fault diagnosis have leveraged domain generalization to address the issue of domain shift. Most existing methods focus on learning domain-invariant representations from multiple source domains. However, collecting valuable fault samples from varying operational conditions is challenging, and it is common for available data to originate from a single operational condition. Thus, this paper introduces a Multi-scale generative and adversarial Metric networks (MGAMN) for Chemical Process Fault Diagnosis. To enhance model generalization, a domain generation module was developed to create augmented domains with significant distributional differences from the source domain. The diagnostic task module then extracts domain-invariant features from both the source and augmented domains. A multi-scale generation strategy is established, utilizing multi-scale deep separable convolutions (Dsc) to ensure that the generated samples contain rich state information. Additionally, an adversarial training and metric learning strategy is designed to learn generalized features capable of resisting unknown domain shifts. Extensive diagnostic experiments on the non-isothermal continuous stirred tank reactor (CSTR) and the Tennessee Eastman Process (TEP) chemical datasets validate the effectiveness of the proposed method. Moreover, ablation studies confirm the effectiveness of the proposed modular strategy, demonstrating significant potential for practical applications.

Reporting radiographers in Norway – A qualitative study on implementation, organisation, and outcomes

IntroductionWorldwide, there is an increasing use of imaging services and a shortage of radiologists. One potential solution to this challenge involves introducing task shifting, where radiographers actively contribute to reporting diagnostic images alongside radiologists. This study explored the purpose and value of reporting radiographers in Norway's imaging departments. MethodsThis study used a qualitative design with a descriptive approach. Semi-structured interviews were conducted with eleven participants, comprising managers, radiologists, and reporting radiographers, from four hospital trusts in south Norway. The collected data were analysed using inductive content analysis. ResultsThe analysis generated three main categories: “Organisation,” “Barriers and facilitators,” and “Experienced outcome.” The study showed that successfully implementing reporting radiographers required careful planning and preparation due to radiologists' resistance. The radiologists and managers experienced that reporting radiographers contributed to increased service quality and better training of radiographers and resident physicians. Reporting radiographers found the combination of reporting and diagnostic radiography tasks rewarding and challenging simultaneously. ConclusionThe implementation of reporting radiographers in imaging departments in Norway was described as successful, positively impacting service quality, reporting capacity, and quality development. However, preparation and planning are needed to overcome barriers to task-shifting. Implications for practiceThis study shows that with management involvement and careful planning, reporting radiographers contribute to a high-quality imaging service.

Explaining the predictions of kernel SVM models for neuroimaging data analysis

Machine learning methods have shown great performance in many areas, including neuroimaging data analysis. However, model performance is only one objective in neuroimaging analysis. Gaining insight from the data is also critical in this field, such as identifying regions where detected signals are relevant to cognitive and diagnostic tasks. To fulfill this need, enabling the explainability of a model’s decision-making process is critical. Predictions of complex machine learning models are notoriously difficult to explain. This limits the use of complex models like kernel support vector machines (SVM) in neuroimaging analysis. Recently, several permutation-based methods have been developed to explain these complex models. However, the explanation results are affected by class-irrelevant features like suppressor variables and high background noise variables. This problem may also happen when explaining linear models. One possible reason is that the permutation process will produce unrealistic data instances when features are not independent, e.g. correlated. These unrealistic data instances will influence the explanation results. In neuroimaging analysis, the activation pattern, the estimated weight of the assumed generative model corresponding to the current classifier, is used to deal with this problem for linear models. This method does not rely on a permutation process but rather on the available data information. In this paper, we propose a novel method of Explanation through Activation Pattern (EAP) to explain the SVM models with different types of kernels for neuroimaging data analysis. Our method can generate a global feature importance score by estimating the activation pattern of kernel SVM models. We evaluate our method against three popular methods on both simulation datasets and a publicly available EEG/MEG dataset on visual tasks. The experimental results demonstrate that the proposed EAP method can provide explanations with low computational cost and is less affected by class-irrelevant features than the other three methods. In the experiment using the MEG/EEG dataset of visual tasks, the proposed EAP method provides agreement results with the brain’s electrical activity patterns reported in the literature on the visual tasks EEG/MEG data and is significantly faster than the other explanation methods.

Automated Classification of Abdominal Ultrasound lmages of the Pancreas Based on the Spectral Representation of the Border’s Contours

The purpose of the research is to develop a methodology for classifying complexly structured halftone images based on a multimodal approach using methods of morphological analysis, spectral analysis and neural network modeling.Methods. А method for classifying the contours of the boundaries of segments of a complexly structured image is described. Тhe method is based on the fact that in chronic diseases of the pancreas, there is a violation of the integrity of the contour of its border and its waviness increases due to retractions and bulges caused by an alterative inflammatory process. Тhe method includes the stages of normalization of ultrasound images and image segmentation with the selection of the contour of the object of interest. Тo classify the contour of a segment boundary, it is proposed to use Fourier analysis and neural network technologies. Тhe method is illustrated using the example of classifying the contour of the border of the pancreas on its transcutaneous acoustic image.Results. Еxperimental studies of the proposed methods and means for classifying medical risk were carried out on diagnostic tasks according to the following classes: "chronic pancreatitis" – "without pathology". For experimental studies, video sequences of ultrasound images of the pancreas provided by an endoscopist were used. Тhe purpose of the experimental studies was to analyze the classification quality indicators of image classifiers with class segments "Chronic pancreatitis" and "Without pathology". Тhe training sample of video images (frames of video sequences) included 200 examples, one hundred from each class. Тhe quality indicator "Sensitivity" of classification for two classes is 85,7%, the indicator "Specificity" is 87,1%.Тhe use of the contour analysis method in classifiers of ultrasound images of the pancreas opens up new opportunities for accessible and objective diagnosis of pancreatic diseases, expanding the capabilities of intelligent clinical decision support systems.

A segmentation-based algorithm for classification of benign and malignancy Thyroid nodules with multi-feature information.

The aim of this study is to propose a new diagnostic model based on "segmentation + classification" to improve the routine screening of Thyroid nodule ultrasonography by utilizing the key domain knowledge of medical diagnostic tasks. A Multi-scale segmentation network based on a pyramidal pooling structure of multi-parallel void spaces is proposed. First, in the segmentation network, the exact information of the underlying feature space is obtained by an Attention Gate. Second, the inflated convolutional part of Atrous Spatial Pyramid Pooling (ASPP) is cascaded for multiple downsampling. Finally, a three-branch classification network combined with expert knowledge is designed, drawing on doctors' clinical diagnosis experience, to extract features from the original image of the nodule, the regional image of the nodule, and the edge image of the nodule, respectively, and to improve the classification accuracy of the model by utilizing the Coordinate attention (CA) mechanism and cross-level feature fusion. The Multi-scale segmentation network achieves 94.27%, 93.90% and 88.85% of mean precision (mPA), Dice value (Dice) and mean joint intersection (MIoU), respectively, and the accuracy, specificity and sensitivity of the classification network reaches 86.07%, 81.34% and 90.19%, respectively. Comparison tests show that this method outperforms the U-Net, AGU-Net and DeepLab V3+ classical models as well as the nnU-Net, Swin UNetr and MedFormer models that have emerged in recent years. This algorithm, as an auxiliary diagnostic tool, can help physicians more accurately assess the benign or malignant nature of Thyroid nodules. It can provide objective quantitative indicators, reduce the bias of subjective judgment, and improve the consistency and accuracy of diagnosis. Codes and models are available at https://github.com/enheliang/Thyroid-Segmentation-Network.git.

USING A WIRELESS SENSOR NODE TO MEASURE THE ACCELERATION OF THE SWING ROCKING MACHINE NODES

Technical diagnosis of the drive of well rod pump units (WRPU) remains an urgent task, despite the significant amount of research in this field. One of the areas of diagnosis is the measurement and control of the angular velocity of the rocking machine elements, which requires the provision of synchronous registration and control of acceleration signals at many points of the control object. The authors proposed to implement such a system based on the wireless sensor module Steval-MKSBOX1V1 of STMicroelectronics. The results of the experimental approbation of the use of the specified module showed the effectiveness of its use for solving diagnostic tasks, since the module contains a significant set of sensors in combination with a unit for processing, storing and transmitting information via a wireless Bluetooth interface. An additional advantage of using the selected measuring module is the possibility of remote reprogramming of the module's software to perform the tasks of controlling the kinematic parameters of the installation in the process of conducting research directly at the technological facility. The use of three coordinate accelerometers as part of the measuring module allows to significantly increase the reliability of control in the diagnostic process.

Few-Shot Synthetic Online Transfer Learning for Cross-Site Neurological Disease Diagnosis

Cross-site datasets expand the data size and could improve the disease diagnosis capabilities of machine learning models. However, differences in data distribution between different sites can lead to poor model generalizability. Although transfer learning is a mainstream method often used to tackle the issue, most transfer learning studies assume that all the target samples are given in the training procedure, which is not available in clinical applications where the target samples arrive sequentially. Online transfer learning (OTL) aims to accomplish clinical diagnostic tasks by adaptively updating the ensemble model containing source and target classifiers. However, OTL is limited by zero initialization and requires numbers of samples to iterate. This results in the underperformance of OTL in clinical applications where few samples can be obtained. In this article, we propose a new framework named few-shot synthetic OTL (FSOTL) to address this issue. FSOTL uses synthetic data to warm up the model in an online fashion. It not only alleviates the problem of scarcity of samples in the target domain but also enables the model to gain more knowledge. Our experiments show that FSOTL performs more stably and achieves more accurate results with few target samples, thereby offering a promising cross-site online computer-aided diagnosis system for large-scale applications.

The effects of gaze-display feedback on medical students’ self-monitoring and learning in radiology

Self-monitoring is essential for effectively regulating learning, but difficult in visual diagnostic tasks such as radiograph interpretation. Eye-tracking technology can visualize viewing behavior in gaze displays, thereby providing information about visual search and decision-making. We hypothesized that individually adaptive gaze-display feedback improves posttest performance and self-monitoring of medical students who learn to detect nodules in radiographs. We investigated the effects of: (1) Search displays, showing which part of the image was searched by the participant; and (2) Decision displays, showing which parts of the image received prolonged attention in 78 medical students. After a pretest and instruction, participants practiced identifying nodules in 16 cases under search-display, decision-display, or no feedback conditions (n = 26 per condition). A 10-case posttest, without feedback, was administered to assess learning outcomes. After each case, participants provided self-monitoring and confidence judgments. Afterward, participants reported on self-efficacy, perceived competence, feedback use, and perceived usefulness of the feedback. Bayesian analyses showed no benefits of gaze displays for post-test performance, monitoring accuracy (absolute difference between participants’ estimated and their actual test performance), completeness of viewing behavior, self-efficacy, and perceived competence. Participants receiving search-displays reported greater feedback utilization than participants receiving decision-displays, and also found the feedback more useful when the gaze data displayed was precise and accurate. As the completeness of search was not related to posttest performance, search displays might not have been sufficiently informative to improve self-monitoring. Information from decision displays was rarely used to inform self-monitoring. Further research should address if and when gaze displays can support learning.

MEDICAL FUZZY-EXPERT SYSTEM FOR PREDICTION OF ENGRAFTMENT DEGREE OF DENTAL IMPLANTS IN PATIENTS WITH CHRONIC LIVER DISEASE

The paper presents an information technology for assessing the degree of engraftment of dental implants in the event of a pathology violation through the use of fuzzy sets, which allows using this method for medical diagnostic tasks. Main scientific results: developed algorithms and mathematical models that formalize the process supporting diagnostic decisions based on fuzzy logic; developed mathematical models of membership functions that formalize the presentation of qualitative and qualitative informational features based on the rules of fuzzy logic, which can be used in information expert systems when assessing the degree of engraftment of dental implants in case of disease with pathological diseases.

The selective deployment of AI in healthcare: An ethical algorithm for algorithms.

Machine-learning algorithms have the potential to revolutionise diagnostic and prognostic tasks in health care, yet algorithmic performance levels can be materially worse for subgroups that have been underrepresented in algorithmic training data. Given this epistemic deficit, the inclusion of underrepresented groups in algorithmic processes can result in harm. Yet delaying the deployment of algorithmic systems until more equitable results can be achieved would avoidably and foreseeably lead to a significant number of unnecessary deaths in well-represented populations. Faced with this dilemma between equity and utility, we draw on two case studies involving breast cancer and melanoma to argue for the selective deployment of diagnostic and prognostic tools for some well-represented groups, even if this results in the temporary exclusion of underrepresented patients from algorithmic approaches. We argue that this approach is justifiable when the inclusion of underrepresented patients would cause them to be harmed. While the context of historic injustice poses a considerable challenge for the ethical acceptability of selective algorithmic deployment strategies, we argue that, at least for the case studies addressed in this article, the issue of historic injustice is better addressed through nonalgorithmic measures, including being transparent with patients about the nature of the current epistemic deficits, providing additional services to algorithmically excluded populations, and through urgent commitments to gather additional algorithmic training data from excluded populations, paving the way for universal algorithmic deployment that is accurate for all patient groups. These commitments should be supported by regulation and, where necessary, government funding to ensure that any delays for excluded groups are kept to the minimum. We offer an ethical algorithm for algorithms-showing when to ethically delay, expedite, or selectively deploy algorithmic systems in healthcare settings.