An artificial intelligence-assisted diagnostic platform for rapid near-patient hematology.
Ontology highlight
ABSTRACT:
SUBMITTER: Bachar N
PROVIDER: S-EPMC9290600 | biostudies-literature | 2021 Oct
REPOSITORIES: biostudies-literature
Publications
An artificial intelligence-assisted diagnostic platform for rapid near-patient hematology.
Bachar Neta N Benbassat Dana D Brailovsky David D Eshel Yochay Y Glück Dan D Levner Daniel D Levy Sarah S Pecker Sharon S Yurkovsky Evgeny E Zait Amir A Sever Cordelia C Kratz Alexander A Brugnara Carlo C
American journal of hematology 20210802 10
Hematology analyzers capable of performing complete blood count (CBC) have lagged in their prevalence at the point-of-care. Sight OLO (Sight Diagnostics, Israel) is a novel hematological platform which provides a 19-parameter, five-part differential CBC, and is designed to address the limitations in current point-of-care hematology analyzers using recent advances in artificial intelligence (AI) and computer vision. Accuracy, repeatability, and flagging capabilities of OLO were compared with the ...[more]
Similar Datasets
Project description:Introduction: Accurate and rapid diagnostics paired with effective tracking and tracing systems are key to halting the spread of infectious diseases, limiting the emergence of new variants and to monitor vaccine efficacy. The current gold standard test (RT-qPCR) for COVID-19 is highly accurate and sensitive, but is time-consuming, and requires expensive specialised, lab-based equipment. Methods: Herein, we report on the development of a SARS-CoV-2 (COVID-19) rapid and inexpensive diagnostic platform that relies on a reverse-transcription loop-mediated isothermal amplification (RT-LAMP) assay and a portable smart diagnostic device. Automated image acquisition and an Artificial Intelligence (AI) deep learning model embedded in the Virus Hunter 6 (VH6) device allow to remove any subjectivity in the interpretation of results. The VH6 device is also linked to a smartphone companion application that registers patients for swab collection and manages the entire process, thus ensuring tests are traced and data securely stored. Results: Our designed AI-implemented diagnostic platform recognises the nucleocapsid protein gene of SARS-CoV-2 with high analytical sensitivity and specificity. A total of 752 NHS patient samples, 367 confirmed positives for coronavirus disease (COVID-19) and 385 negatives, were used for the development and validation of the test and the AI-assisted platform. The smart diagnostic platform was then used to test 150 positive clinical samples covering a dynamic range of clinically meaningful viral loads and 250 negative samples. When compared to RT-qPCR, our AI-assisted diagnostics platform was shown to be reliable, highly specific (100%) and sensitive (98-100% depending on viral load) with a limit of detection of 1.4 copies of RNA per µL in 30 min. Using this data, our CE-IVD and MHRA approved test and associated diagnostic platform has been approved for medical use in the United Kingdom under the UK Health Security Agency's Medical Devices (Coronavirus Test Device Approvals, CTDA) Regulations 2022. Laboratory and in-silico data presented here also indicates that the VIDIIA diagnostic platform is able to detect the main variants of concern in the United Kingdom (September 2023). Discussion: This system could provide an efficient, time and cost-effective platform to diagnose SARS-CoV-2 and other infectious diseases in resource-limited settings.
| S-EPMC10572354 | biostudies-literature
Project description:BackgroundShorter, more effective treatments for tuberculosis (TB) are urgently needed. While many TB drugs are available, identification of the best regimens is challenging because of the large number of possible drug-dose combinations. We have found consistently that responses of cells or whole animals to drug-dose stimulations fit a parabolic response surface (PRS), allowing us to identify and optimize the best drug combinations by testing only a small fraction of the total search space. Previously, we used PRS methodology to identify three regimens (PRS Regimens I-III) that in murine models are much more effective than the standard regimen used to treat TB. However, PRS Regimens I and II are unsuitable for treating drug-resistant TB and PRS Regimen III includes an experimental drug. Here, we use PRS methodology to identify from an expanded pool of drugs new highly effective near-universal drug regimens comprising only approved drugs.Methods and findingsWe evaluated combinations of 15 different drugs in a human macrophage TB model and identified the most promising 4-drug combinations. We then tested 14 of these combinations in Mycobacterium tuberculosis-infected BALB/c mice and chose for PRS dose optimization and further study the two most potent regimens, designated PRS Regimens IV and V, consisting of clofazimine (CFZ), bedaquiline (BDQ), pyrazinamide (PZA), and either amoxicillin/clavulanate (AC) or delamanid (DLM), respectively. We then evaluated the efficacy in mice of optimized PRS Regimens IV and V, as well as a 3-drug regimen, PRS Regimen VI (CFZ, BDQ, and PZA), and compared their efficacy to PRS Regimen III (CFZ, BDQ, PZA, and SQ109), previously shown to reduce the time to achieve relapse-free cure in mice by 80% compared with the Standard Regimen (isoniazid, rifampicin, PZA, and ethambutol). Efficacy measurements included early bactericidal activity, time to lung sterilization, and time to relapse-free cure. PRS Regimens III-VI all rapidly sterilized the lungs and achieved relapse-free cure in 3 weeks (PRS Regimens III, V, and VI) or 5 weeks (PRS Regimen IV). In contrast, mice treated with the Standard Regimen still had high numbers of bacteria in their lungs after 6-weeks treatment and none achieved relapse-free cure in this time-period.ConclusionsWe have identified three new regimens that rapidly sterilize the lungs of mice and dramatically shorten the time required to achieve relapse-free cure. All mouse drug doses in these regimens extrapolate to doses that are readily achievable in humans. Because PRS Regimens IV and V contain only one first line drug (PZA) and exclude fluoroquinolones and aminoglycosides, they should be effective against most TB cases that are multidrug resistant (MDR-TB) and many that are extensively drug-resistant (XDR-TB). Hence, these regimens have potential to shorten dramatically the time required for treatment of both drug-sensitive and drug-resistant TB. If clinical trials confirm that these regimens dramatically shorten the time required to achieve relapse-free cure in humans, then this radically shortened treatment has the potential to improve treatment compliance, decrease the emergence of drug resistance, and decrease the healthcare burden of treating both drug-sensitive and drug-resistant TB.
| S-EPMC6510528 | biostudies-literature
Project description:Unreliable predictions can occur when an artificial intelligence (AI) system is presented with data it has not been exposed to during training. We demonstrate the use of conformal prediction to detect unreliable predictions, using histopathological diagnosis and grading of prostate biopsies as example. We digitized 7788 prostate biopsies from 1192 men in the STHLM3 diagnostic study, used for training, and 3059 biopsies from 676 men used for testing. With conformal prediction, 1 in 794 (0.1%) predictions is incorrect for cancer diagnosis (compared to 14 errors [2%] without conformal prediction) while 175 (22%) of the predictions are flagged as unreliable when the AI-system is presented with new data from the same lab and scanner that it was trained on. Conformal prediction could with small samples (N = 49 for external scanner, N = 10 for external lab and scanner, and N = 12 for external lab, scanner and pathology assessment) detect systematic differences in external data leading to worse predictive performance. The AI-system with conformal prediction commits 3 (2%) errors for cancer detection in cases of atypical prostate tissue compared to 44 (25%) without conformal prediction, while the system flags 143 (80%) unreliable predictions. We conclude that conformal prediction can increase patient safety of AI-systems.
| S-EPMC9755280 | biostudies-literature
Project description:Pain relief is a major concern for patients who have undergone surgery, and it is an eternal pursuit for anesthesiologists. However, postoperative pain management is far from satisfactory, though the past decades have witnessed great progress in the development of novel analgesics and analgesic techniques. A Cochrane systematic review showed that patient-controlled analgesia (PCA) achieved better pain relief and greater patient satisfaction than traditional "on-demand" parenteral analgesia, suggesting that it might be the manner of analgesia implementation that matters for effective postoperative pain management. A wireless intelligent PCA (Wi-PCA) system that incorporated remote monitoring, an intelligent alarm, intelligent analysis and assessment of the PCA equipment, as well as automatically recording and reserving key information functions under a wireless environment was introduced in our department in 2018. The practice showed that the Wi-PCA system significantly reduced the incidence of moderate to severe postoperative pain and relevant adverse effects, shortened hospital stays, and improved patient satisfaction with postoperative pain relief. Nevertheless, for both traditional and Wi-PCA, analgesics are only administered when pain occurs, leaving behind a realm of possibilities for better postoperative pain management. With the rapid development of machinery and deep learning algorithms, artificial intelligence (AI) is changing the mode of clinical decision making. Integrating the big data collected by state-of-the-art monitoring sensors, the Internet of Things and AI algorithms, an AI-assisted PCA (Ai-PCA) may be a promising future direction for postoperative pain management.
| S-EPMC7326064 | biostudies-literature
Project description:Until vaccines and effective therapeutics become available, the practical solution to transit safely out of the current coronavirus disease 19 (CoVID-19) lockdown may include the implementation of an effective testing, tracing and tracking system. However, this requires a reliable and clinically validated diagnostic platform for the sensitive and specific identification of SARS-CoV-2. Here, we report on the development of a de novo, high-resolution and comparative genomics guided reverse-transcribed loop-mediated isothermal amplification (LAMP) assay. To further enhance the assay performance and to remove any subjectivity associated with operator interpretation of results, we engineered a novel hand-held smart diagnostic device. The robust diagnostic device was further furnished with automated image acquisition and processing algorithms and the collated data was processed through artificial intelligence (AI) pipelines to further reduce the assay run time and the subjectivity of the colorimetric LAMP detection. This advanced AI algorithm-implemented LAMP (ai-LAMP) assay, targeting the RNA-dependent RNA polymerase gene, showed high analytical sensitivity and specificity for SARS-CoV-2. A total of ~200 coronavirus disease (CoVID-19)-suspected NHS patient samples were tested using the platform and it was shown to be reliable, highly specific and significantly more sensitive than the current gold standard qRT-PCR. Therefore, this system could provide an efficient and cost-effective platform to detect SARS-CoV-2 in resource-limited laboratories.
| S-EPMC7552048 | biostudies-literature
Project description:Although digoxin is important in heart rate control, the utilization of digoxin is declining due to its narrow therapeutic window. Misdiagnosis or delayed diagnosis of digoxin toxicity is common due to the lack of awareness and the time-consuming laboratory work that is involved. Electrocardiography (ECG) may be able to detect potential digoxin toxicity based on characteristic presentations. Our study attempted to develop a deep learning model to detect digoxin toxicity based on ECG manifestations. This study included 61 ECGs from patients with digoxin toxicity and 177,066 ECGs from patients in the emergency room from November 2011 to February 2019. The deep learning algorithm was trained using approximately 80% of ECGs. The other 20% of ECGs were used to validate the performance of the Artificial Intelligence (AI) system and to conduct a human-machine competition. Area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to evaluate the performance of ECG interpretation between humans and our deep learning system. The AUCs of our deep learning system for identifying digoxin toxicity were 0.912 and 0.929 in the validation cohort and the human-machine competition, respectively, which reached 84.6% of sensitivity and 94.6% of specificity. Interestingly, the deep learning system using only lead I (AUC = 0.960) was not worse than using complete 12 leads (0.912). Stratified analysis showed that our deep learning system was more applicable to patients with heart failure (HF) and without atrial fibrillation (AF) than those without HF and with AF. Our ECG-based deep learning system provides a high-accuracy, economical, rapid, and accessible way to detect digoxin toxicity, which can be applied as a promising decision supportive system for diagnosing digoxin toxicity in clinical practice.
| S-EPMC8038815 | biostudies-literature
Project description:Focused cardiac ultrasound (FoCUS) is becoming standard practice in a wide spectrum of clinical settings. There is limited data evaluating the real-world use of FoCUS with artificial intelligence (AI). Our objective was to determine the accuracy of FoCUS AI-assisted left ventricular ejection fraction (LVEF) assessment and compare its accuracy between novice and experienced users. In this prospective, multicentre study, participants requiring a transthoracic echocardiogram (TTE) were recruited to have a FoCUS done by a novice or experienced user. The AI-assisted device calculated LVEF at the bedside, which was subsequently compared to TTE. 449 participants were enrolled with 424 studies included in the final analysis. The overall intraclass coefficient was 0.904, and 0.921 in the novice (n = 208) and 0.845 in the experienced (n = 216) cohorts. There was a significant bias of 0.73% towards TTE (p = 0.005) with a level of agreement of 11.2%. Categorical grading of LVEF severity had excellent agreement to TTE (weighted kappa = 0.83). The area under the curve (AUC) was 0.98 for identifying an abnormal LVEF (<50%) with a sensitivity of 92.8%, specificity of 92.3%, negative predictive value (NPV) of 0.97 and a positive predictive value (PPV) of 0.83. In identifying severe dysfunction (<30%) the AUC was 0.99 with a sensitivity of 78.1%, specificity of 98.0%, NPV of 0.98 and PPV of 0.76. Here we report that FoCUS AI-assisted LVEF assessments provide highly reproducible LVEF estimations in comparison to formal TTE. This finding was consistent among senior and novice echocardiographers suggesting applicability in a variety of clinical settings.
| S-EPMC10613290 | biostudies-literature
Project description:Background and aimsThe diagnosis of chronic atrophic gastritis (CAG) under normal white-light endoscopy depends on the endoscopist's experience and is not ideal. Artificial intelligence (AI) is increasingly used to diagnose diseases with good results. This review aimed to evaluate the accuracy of AI-assisted diagnosis of CAG through a meta-analysis.MethodsWe conducted a comprehensive literature search of four databases: PubMed, Embase, Web of Science, and the Cochrane Library. Studies published by November 21, 2022, on AI diagnosis CAG with endoscopic images or videos were included. We assessed the diagnostic performance of AI using meta-analysis, explored the sources of heterogeneity through subgroup analysis and meta-regression, and compared the accuracy of AI and endoscopists in diagnosing CAG.ResultsEight studies that included a total of 25,216 patients of interest, 84,678 image training set images, and 10,937 test set images/videos were included. The results of the meta-analysis showed that the sensitivity of AI in identifying CAG was 94% (95% confidence interval [CI]: 0.88-0.97, I2 = 96.2%), the specificity was 96% (95% CI: 0.88-0.98, I2 = 98.04%), and the area under the summary receiver operating characteristic curve was 0.98 (95% CI: 0.96-0.99). The accuracy of AI in diagnosing CAG was significantly higher than that of endoscopists.ConclusionsAI-assisted diagnosis of CAG in endoscopy has high accuracy and clinical diagnostic value.Systematic review registrationhttp://www.crd.york.ac.uk/PROSPERO/, identifier: CRD42023391853.
| S-EPMC10185804 | biostudies-literature
Project description:BACKGROUND:Patients are increasingly seeking Web-based symptom checkers to obtain diagnoses. However, little is known about the characteristics of the patients who use these resources, their rationale for use, and whether they find them accurate and useful. OBJECTIVE:The study aimed to examine patients' experiences using an artificial intelligence (AI)-assisted online symptom checker. METHODS:An online survey was administered between March 2, 2018, through March 15, 2018, to US users of the Isabel Symptom Checker within 6 months of their use. User characteristics, experiences of symptom checker use, experiences discussing results with physicians, and prior personal history of experiencing a diagnostic error were collected. RESULTS:A total of 329 usable responses was obtained. The mean respondent age was 48.0 (SD 16.7) years; most were women (230/304, 75.7%) and white (271/304, 89.1%). Patients most commonly used the symptom checker to better understand the causes of their symptoms (232/304, 76.3%), followed by for deciding whether to seek care (101/304, 33.2%) or where (eg, primary or urgent care: 63/304, 20.7%), obtaining medical advice without going to a doctor (48/304, 15.8%), and understanding their diagnoses better (39/304, 12.8%). Most patients reported receiving useful information for their health problems (274/304, 90.1%), with half reporting positive health effects (154/302, 51.0%). Most patients perceived it to be useful as a diagnostic tool (253/301, 84.1%), as a tool providing insights leading them closer to correct diagnoses (231/303, 76.2%), and reported they would use it again (278/304, 91.4%). Patients who discussed findings with their physicians (103/213, 48.4%) more often felt physicians were interested (42/103, 40.8%) than not interested in learning about the tool's results (24/103, 23.3%) and more often felt physicians were open (62/103, 60.2%) than not open (21/103, 20.4%) to discussing the results. Compared with patients who had not previously experienced diagnostic errors (missed or delayed diagnoses: 123/304, 40.5%), patients who had previously experienced diagnostic errors (181/304, 59.5%) were more likely to use the symptom checker to determine where they should seek care (15/123, 12.2% vs 48/181, 26.5%; P=.002), but they less often felt that physicians were interested in discussing the tool's results (20/34, 59% vs 22/69, 32%; P=.04). CONCLUSIONS:Despite ongoing concerns about symptom checker accuracy, a large patient-user group perceived an AI-assisted symptom checker as useful for diagnosis. Formal validation studies evaluating symptom checker accuracy and effectiveness in real-world practice could provide additional useful information about their benefit.
| S-EPMC7055765 | biostudies-literature
Project description:PURPOSE:To establish and validate a universal artificial intelligence (AI) platform for collaborative management of cataracts involving multilevel clinical scenarios and explored an AI-based medical referral pattern to improve collaborative efficiency and resource coverage. METHODS:The training and validation datasets were derived from the Chinese Medical Alliance for Artificial Intelligence, covering multilevel healthcare facilities and capture modes. The datasets were labelled using a three-step strategy: (1) capture mode recognition; (2) cataract diagnosis as a normal lens, cataract or a postoperative eye and (3) detection of referable cataracts with respect to aetiology and severity. Moreover, we integrated the cataract AI agent with a real-world multilevel referral pattern involving self-monitoring at home, primary healthcare and specialised hospital services. RESULTS:The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance in three-step tasks: (1) capture mode recognition (area under the curve (AUC) 99.28%-99.71%), (2) cataract diagnosis (normal lens, cataract or postoperative eye with AUCs of 99.82%, 99.96% and 99.93% for mydriatic-slit lamp mode and AUCs >99% for other capture modes) and (3) detection of referable cataracts (AUCs >91% in all tests). In the real-world tertiary referral pattern, the agent suggested 30.3% of people be 'referred', substantially increasing the ophthalmologist-to-population service ratio by 10.2-fold compared with the traditional pattern. CONCLUSIONS:The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance and effective service for cataracts. The context of our AI-based medical referral pattern will be extended to other common disease conditions and resource-intensive situations.
| S-EPMC6855787 | biostudies-literature