Smartphone app for non-invasive detection of anemia using only patient-sourced photos.
Ontology highlight
ABSTRACT:
SUBMITTER: Mannino RG
PROVIDER: S-EPMC6279826 | biostudies-other | 2018 Dec
REPOSITORIES: biostudies-other
Publications
Smartphone app for non-invasive detection of anemia using only patient-sourced photos.
Mannino Robert G RG Myers David R DR Tyburski Erika A EA Caruso Christina C Boudreaux Jeanne J Leong Traci T Clifford G D GD Lam Wilbur A WA
Nature communications 20181204 1
We introduce a paradigm of completely non-invasive, on-demand diagnostics that may replace common blood-based laboratory tests using only a smartphone app and photos. We initially targeted anemia, a blood condition characterized by low blood hemoglobin levels that afflicts >2 billion people. Our app estimates hemoglobin levels by analyzing color and metadata of fingernail bed smartphone photos and detects anemia (hemoglobin levels <12.5 g dL<sup>-1</sup>) with an accuracy of ±2.4 g dL<sup>-1</su ...[more]
Similar Datasets
Project description:The COVID-19 pandemic has highlighted the need for innovative approaches to its diagnosis. Here we present CoVradar, a novel and simple colorimetric method that combines nucleic acid analysis with dynamic chemical labeling (DCL) technology and the Spin-Tube device to detect SARS-CoV-2 RNA in saliva samples. The assay includes a fragmentation step to increase the number of RNA templates for analysis, using abasic peptide nucleic acid probes (DGL probes) immobilized to nylon membranes in a specific dot pattern to capture RNA fragments. Duplexes are formed by labeling complementary RNA fragments with biotinylated SMART bases, which act as templates for DCL. Signals are generated by recognizing biotin with streptavidin alkaline phosphatase and incubating with a chromogenic substrate to produce a blue precipitate. CoVradar results are analysed by CoVreader, a smartphone-based image processing system that can display and interpret the blotch pattern. CoVradar and CoVreader provide a unique molecular assay capable of detecting SARS-CoV-2 viral RNA without the need for extraction, preamplification, or pre-labeling steps, offering advantages in terms of time (∼3 h/test), cost (∼€1/test manufacturing cost) and simplicity (does not require large equipment). This solution is also promising for developing assays for other infectious diseases.
| S-EPMC10060197 | biostudies-literature
Project description:Acute coronary syndrome (ACS) mostly arises from so-called vulnerable coronary plaques, particularly prone for rupture. Vulnerable plaques comprise a specific type of plaque, called the thin-cap fibroatheroma (TFCA). A TCFA is characterized by a large lipid-rich necrotic core, a thin fibrous cap, inflammation, neovascularization, intraplaque hemorrhage, microcalcifications or spotty calcifications, and positive remodeling. Vulnerable plaques are often not visible during coronary angiography. However, different plaque features can be visualized with the use of intracoronary imaging techniques, such as intravascular ultrasound (IVUS), potentially with the addition of near-infrared spectroscopy (NIRS), or optical coherence tomography (OCT). Non-invasive imaging techniques, such as computed tomography coronary angiography (CTCA), cardiovascular magnetic resonance (CMR) imaging, and nuclear imaging, can be used as an alternative for these invasive imaging techniques. These invasive and non-invasive imaging modalities can be implemented for screening to guide primary or secondary prevention therapies, leading to a more patient-tailored diagnostic and treatment strategy. Systemic pharmaceutical treatment with lipid-lowering or anti-inflammatory medication leads to plaque stabilization and reduction of cardiovascular events. Additionally, ongoing studies are investigating whether modification of vulnerable plaque features with local invasive treatment options leads to plaque stabilization and subsequent cardiovascular risk reduction.
| S-EPMC8911129 | biostudies-literature
Project description:BackgroundPreoperative anemia is common and associated with adverse postoperative outcomes. Assessment of hemoglobin concentrations may facilitate optimization prior to surgery. However, phlebotomy-based hemoglobin measurement may contribute to patient discomfort and iatrogenic blood loss, which makes non-invasive hemoglobin estimation attractive in this setting.Study design and methodsThis is a prospective study of adult patients presenting for preoperative evaluation before elective surgery at a tertiary care medical center. The Masimo Pronto Pulse CO-Oximeter was utilized to estimate blood hemoglobin concentrations (SpHb), which were then compared with hemoglobin concentrations obtained via complete blood count. Receiver operating curves were used to identify SpHb values maximizing specificity for anemia detection while meeting a minimum sensitivity of 80%.ResultsA total of 122 patients were recruited with a median (interquartile range) age of 66 (58, 72) years. SpHb measurements were obtained in 112 patients (92%). SpHb generally overestimated hemoglobin with a mean (± 1.96 × standard deviation) difference of 0.8 (-2.2, 3.9) g/dL. Preoperative anemia, defined by hemoglobin <12.0 g/dL in accordance with institutional protocol, was present in 22 patients (20%). The optimal SpHb cut-point to identify anemia was 13.5 g/dL: sensitivity 86%, specificity 81%, negative predictive value 96%, and positive predictive value 53%. Utilizing this cut-point, 60% (73/122) of patients could have avoided phlebotomy-based hemoglobin assessment, while an anemia diagnosis would have been missed in <3% (3/122).ConclusionThe use of SpHb devices for anemia screening in surgical patients is feasible with the potential to reliably rule-out anemia despite limited accuracy.
| S-EPMC9898154 | biostudies-literature
Project description:There are few data on the range and severity of symptoms of SARS-CoV-2 infection or the impact on life quality in infected, previously healthy, young adults such as Swiss Armed Forces personnel. It is also unclear if an app can be used to remotely monitor symptoms in persons who test positive. Using a smartphone app called ITITP (Illness Tracking in Tested Persons) and weekly pop-up questionnaires, we aimed to evaluate the spectrum, duration, and impact of symptoms reported after a positive SARS-CoV-2 test according to sex, age, location, and comorbidities, and to compare these to responses from persons who tested negative. We followed up 502 participants (57% active participation), including 68 (13.5%) positive tested persons. Hospitalisation was reported by 6% of the positive tested participants. We found that positives reported significantly more symptoms that are typical of COVID-19 compared to negatives. These symptoms with odds ratio (OR > 1) were having difficulty breathing (OR 3.35; 95% CI: 1.16, 9.65; p = 0.03), having a reduced sense of taste (OR 5.45; 95% CI: 1.22, 24.34; p = 0.03) and a reduced sense of smell (OR 18.24; 95% CI: 4.23, 78.69; p < 0.001). Using a random forest model, we showed that tiredness was the single symptom that was rated as having a significant impact on daily activities, whereas the other symptoms, although frequent, had less impact. The study showed that the use of an app was feasible to remotely monitor symptoms in persons infected with SARS-CoV-2 and could be adapted for other settings and new pandemic phases such as the current Omicron wave.
| S-EPMC8908571 | biostudies-literature
Project description:Sickle cell disease affects 25% of people living in Central and West Africa and, if left undiagnosed, can cause life threatening "silent" strokes and lifelong damage. However, ubiquitous testing procedures have yet to be implemented in these areas, necessitating a simple, rapid, and accurate testing platform to diagnose sickle cell disease. Here, we present a label-free, sensitive, and specific testing platform using only a small blood sample (<1 ?l) based on the higher density of sickle red blood cells under deoxygenated conditions. Testing is performed with a lightweight and compact 3D-printed attachment installed on a commercial smartphone. This attachment includes an LED to illuminate the sample, an optical lens to magnify the image, and two permanent magnets for magnetic levitation of red blood cells. The sample is suspended in a paramagnetic medium with sodium metabisulfite and loaded in a microcapillary tube that is inserted between the magnets. Red blood cells are levitated in the magnetic field based on equilibrium between the magnetic and buoyancy forces acting on the cells. Using this approach, we were able to distinguish between the levitation patterns of sickle versus control red blood cells based on their degree of confinement.
| S-EPMC4615037 | biostudies-literature
Project description:BackgroundSevere chemotherapy-induced peripheral neuropathy (CIPN) can cause long-term dysfunction of the hands and feet, interfere with activities of daily living, and diminish the quality of life. Monitoring to identify CIPN and adjust treatment before it progressing to a life-altering severity relies on patients self-reporting subjective symptoms to their clinical team. Objective assessment is not a standard component of CIPN monitoring due to the requirement for specially trained health care professionals and equipment. Smartphone apps have the potential to conveniently collect both subjective and objective CIPN data directly from patients, which could improve CIPN monitoring.ObjectiveThe objective of this cross-sectional pilot study was to assess the feasibility of functional CIPN assessment via a smartphone app in patients with cancer that have received neurotoxic chemotherapy.MethodsA total of 26 patients who had completed neurotoxic chemotherapy were enrolled and classified as CIPN cases (n=17) or controls (n=9) based on self-report symptoms. All participants completed CIPN assessments within the NeuroDetect app a single time, including patient-reported surveys (CIPN20 [European Organization for Research and Treatment of Cancer Quality of Life Questionnaire for Chemotherapy-induced Peripheral Neuropathy 20-item scale] and PRO-CTCAE [Patient-Reported Outcomes version of the Common Terminology Criteria for Adverse Events]) and functional assessments (Gait and Balance and 9-Hole Peg Test). Functional assessment data were decomposed into features. The primary analysis was done to identify features indicative of the difference between CIPN cases and controls using partial least squares analyses. Exploratory analyses were performed to test if any features were associated with specific symptom subtypes or patient-reported survey scores. Patient interviews were also conducted to understand the challenges they experienced with the app.ResultsComparisons between CIPN cases and controls indicate that CIPN cases had shorter step length (P=.007), unique swaying acceleration patterns during a walking task, and shorter hand moving distance in the dominant hands during a manual dexterity task (variable importance in projection scores ≥2). Exploratory analyses showed similar signatures associated with symptoms subtypes, CIPN20, and PRO-CTCAE. The interview results showed that some patients had difficulties due to technical issues, which indicated a need for additional training or oversight during the initial app download.ConclusionsOur results supported the feasibility of remote CIPN assessment via a smartphone app and suggested that functional assessments may indicate CIPN manifestations in the hands and feet. Additional work is needed to determine which functional assessments are most indicative of CIPN and could be used for CIPN monitoring within clinical care.
| S-EPMC8406129 | biostudies-literature
Project description:Despite decades of efforts, non-invasive sensitive detection of small malignant brain tumors still remains challenging. Here we report a dual-modality 124I-labeled gold nanostar (124I-GNS) probe for sensitive brain tumor imaging with positron emission tomography (PET) and subcellular tracking with two-photon photoluminescence (TPL) and electron microscopy (EM). Experiment results showed that the developed nanoprobe has potential to reach sub-millimeter intracranial brain tumor detection using PET scan, which is superior to any currently available non-invasive imaging modality. Microscopic examination using TPL and EM further confirmed that GNS nanoparticles permeated the brain tumor leaky vasculature and accumulated inside brain tumor cells following systemic administration. Selective brain tumor targeting by enhanced permeability and retention effect and ultrasensitive imaging render 124I-GNS nanoprobe promise for future brain tumor-related preclinical and translational applications.
| S-EPMC6948110 | biostudies-literature
Project description:Background and aimsAnaemia is a major health burden worldwide. Although the finding of conjunctival pallor on clinical examination is associated with anaemia, inter-observer variability is high, and definitive diagnosis of anaemia requires a blood sample. We aimed to detect anaemia by quantifying conjunctival pallor using digital photographs taken with a consumer camera and a popular smartphone. Our goal was to develop a non-invasive screening test for anaemia.Patients and methodsThe conjunctivae of haemato-oncology in- and outpatients were photographed in ambient lighting using a digital camera (Panasonic DMC-LX5), and the internal rear-facing camera of a smartphone (Apple iPhone 5S) alongside an in-frame calibration card. Following image calibration, conjunctival erythema index (EI) was calculated and correlated with laboratory-measured haemoglobin concentration. Three clinicians independently evaluated each image for conjunctival pallor.ResultsConjunctival EI was reproducible between images (average coefficient of variation 2.96%). EI of the palpebral conjunctiva correlated more strongly with haemoglobin concentration than that of the forniceal conjunctiva. Using the compact camera, palpebral conjunctival EI had a sensitivity of 93% and 57% and specificity of 78% and 83% for detection of anaemia (haemoglobin < 110 g/L) in training and internal validation sets, respectively. Similar results were found using the iPhone camera, though the EI cut-off value differed. Conjunctival EI analysis compared favourably with clinician assessment, with a higher positive likelihood ratio for prediction of anaemia.ConclusionsErythema index of the palpebral conjunctiva calculated from images taken with a compact camera or mobile phone correlates with haemoglobin and compares favourably to clinician assessment for prediction of anaemia. If confirmed in further series, this technique may be useful for the non-invasive screening for anaemia.
| S-EPMC4829242 | biostudies-literature
Project description:Non-invasive detection of aberrant DNA methylation could provide invaluable biomarkers for earlier detection of triple negative breast cancer (TNBC) which could help clinicians for easier and more efficient treatment options. We evaluated genome-wide DNA methylation data derived from TNBC and normal breast tissues, peripheral blood of TNBC cases and controls, and reference samples of sorted blood and mammary cells. Differentially methylated regions (DMRs) between TNBC and normal breast tissues were stringently selected, verified, and externally validated. A machine learning algorithm was applied to select the top DMRs, which then were evaluated on plasma-derived circulating cell-free DNA (cfDNA) samples of TNBC patients and healthy controls. We identified 23 DMRs accounting for the methylation profile of blood cells and reference mammary cells and then selected six top DMRs for cfDNA analysis. We quantified un-/methylated copies of these DMRs by droplet digital PCR analysis in a plasma test set from TNBC patients and healthy controls and confirmed our findings obtained on tissues. Differential cfDNA methylation was confirmed in an independent validation set of plasma samples. A methylation score combining signatures of the top three DMRs overlapping with the SPAG6, LINC10606, and TBCD/ZNF750 genes had the best capability to discriminate TNBC patients from controls (AUC=0.74 in test set and AUC=0.77 in validation set). Our findings demonstrate the usefulness of cfDNA-based methylation signatures as non-invasive liquid biopsy markers for diagnosis of TNBC.
2022-11-23 | GSE207998 | GEO
Project description:Anemia, defined as a low hemoglobin concentration, has a large impact on the health of the world's population. We describe the use of a ubiquitous device, the smartphone, to predict hemoglobin concentration and screen for anemia. This was a prospective convenience sample study conducted in Emergency Department (ED) patients of an academic teaching hospital. In an algorithm derivation phase, images of both conjunctiva were obtained from 142 patients in Phase 1 using a smartphone. A region of interest targeting the palpebral conjunctiva was selected from each image. Image-based parameters were extracted and used in stepwise regression analyses to develop a prediction model of estimated hemoglobin (HBc). In Phase 2, a validation model was constructed using data from 202 new ED patients. The final model based on all 344 patients was tested for accuracy in anemia and transfusion thresholds. Hemoglobin concentration ranged from 4.7 to 19.6 g/dL (mean 12.5). In Phase 1, there was a significant association between HBc and laboratory-predicted hemoglobin (HBl) slope = 1.07 (CI = 0.98-1.15), p<0.001. Accuracy, sensitivity, and specificity of HBc for predicting anemia was 82.9 [79.3, 86.4], 90.7 [87.0, 94.4], and 73.3 [67.1, 79.5], respectively. In Phase 2, accuracy, sensitivity and specificity decreased to 72.6 [71.4, 73.8], 72.8 [71, 74.6], and 72.5 [70.8, 74.1]. Accuracy for low (<7 g/dL) and high (<9 g/dL) transfusion thresholds was 94.4 [93.7, 95] and 86 [85, 86.9] respectively. Error trended with increasing HBl values (slope 0.27 [0.19, 0.36] and intercept -3.14 [-4.21, -2.07] (p<0.001) such that HBc tended to underestimate hemoglobin in higher ranges and overestimate in lower ranges. Higher quality images had a smaller bias trend than lower quality images. When separated by skin tone results were unaffected. A smartphone can be used in screening for anemia and transfusion thresholds. Improvements in image quality and computational corrections can further enhance estimates of hemoglobin.
| S-EPMC8279386 | biostudies-literature