Search Results (5)

Background/Objectives: This study aimed to develop and evaluate a noninvasive anemia screening method using fundus photographs analyzed by deep learning models, by transforming circular fundus photographs into square images suitable for convolutional neural network analysis. Methods: A total of 39,036 fundus images and clinical data collected from 2011 to 2023 were used. Eligible patients had clearly visible macula and optic discs and corresponding hemoglobin measurements. Three image preprocessing methods were applied—untransformed, stretching, and remapping. Results: Among preprocessing methods, the stretching method yielded the most accurate predictions. Deep learning analysis was conducted using multi-tasked cascaded convolutional neural networks. The hemoglobin prediction model based on EfficientNet B5 with remapping preprocessing achieved good performance (R² = 0.781, MAE = 1.23), while the anemia classification model demonstrated screening accuracy with AUC values exceeding 0.893. Conclusions: Deep learning analysis of fundus photographs demonstrates potential as a noninvasive screening method for anemia. This approach may be particularly beneficial for patients requiring regular hemoglobin monitoring. Full article

Bilirubin is a product of the metabolism of hemoglobin from red blood cells. Higher levels of bilirubin are a sign that either there is an unusual breaking down rate of red blood cells or the liver is not able to eliminate bilirubin, through bile, into the gastrointestinal tract. For adults, bilirubin is occasionally monitored through urine or invasive blood sampling, whilst all newborns are routinely monitored visually, or non-invasively with transcutaneous measurements (TcBs), due to their biological immaturity to conjugate bilirubin. Neonatal jaundice is a common condition, with higher levels of unconjugated bilirubin concentration having neurotoxic effects. Actual devices used in TcBs are focused on newborn populations, are hand-held, and, in some cases, operate in only two wavelengths, which does not necessarily guarantee reliable results over all skin tones. The same occurs with visual inspections. Based on that, a continuous bilirubin monitoring device for newborns is being developed to overcome visual inspection errors and to reduce invasive procedures. This device, operating optically with a mini-spectrometer in the visible range, is susceptible to patient movements and, consequently, to situations with a lower signal quality for reliable bilirubin concentration estimates on different types of skin. Therefore, as an intermediate development step and, based on skin spectra measurements from adults, this work addresses the device’s placement status prediction as a signal quality indication index. This was implemented by using machine learning (ML), with the best performances being achieved by support vector machine (SVM) models, based on the spectra acquired on the arm and forehead areas. Full article

Type 2 diabetes mellitus (T2DM) significantly increases the risk of peripheral artery disease (PAD), and diabetes is the leading cause of nontraumatic amputations. This study investigated the risk factors for transcutaneous oxygen pressure (TcPO2) in T2DM, a noninvasive method to quantify skin oxygenation and the underlying microvascular circulation. The study included 119 T2DM patients (91 male/28 female). TcPO2 measurements were conducted with the Tina TCM4 Series transcutaneous monitor (Radiometer, Copenhagen, Sweden) and skin electrodes. Patients with TcPO2 < 40 mmHg were younger (p = 0.001), had significantly higher systolic blood pressure (SBP) (p = 0.023), glycated hemoglobin (HbA₁c) (p = 0.013), fasting plasma glucose (fPG) (p = 0.038), total cholesterol (p = 0.006), LDL cholesterol (p = 0.004), and had more frequent smoking habits (p = 0.001) than those with TcPO2 ≥ 40 mmHg. The main predictors for the TcPO2 value (R² = 0.211) obtained via stepwise regression analysis were age, smoking, SBP, HbA₁c, fPG, and total and LDL cholesterol. Among all the listed predictors, smoking, HbA₁c, and LDL cholesterol were found to be the most significant, with negative parameter estimates of −3.051310 (p = 0.0007), −2.032018 (p = 0.0003), and −2.560353 (p = 0.0046). The results of our study suggest that in association with other risk factors, smoking is the main predictor for lower TcPO2 in T2DM. Full article

The pulse CO-Oximetry allows continuous, noninvasive monitoring of hemoglobin (SpHb). We assessed the impact of increased end-tidal carbon dioxide (EtCO₂) on the accuracy and trending ability of SpHb in laparoscopic surgery. Participants (n = 64) were randomly allocated to the low carbon dioxide (CO₂) group (EtCO₂: 30–35 mmHg) or the high CO₂ group (EtCO₂: 40–45 mmHg). The SpHb and laboratory hemoglobin (tHb) were obtained during surgery. The correlation coefficient (r) between SpHb and tHb showed greater tendency in the low CO₂ group (r = 0.68) than in the high CO₂ group (r = 0.43). The bias (precision) was −1.18 (1.09) with a limit of agreement (LOA) of −3.31 to 0.95 in low CO₂ group and −1.02 (1.24) with a LOA of −3.45 to 1.42 in high CO₂ group; they did not differ significantly between the groups (p = 0.246). The low CO₂ group showed a high concordance rate of 95.9% and a moderate correlation between ΔSpHb and ΔtHb (r = 0.53). However, the high CO₂ group showed a concordance rate of 77.8% and no correlation between ΔSpHb and ΔtHb (r = 0.11). In conclusion, increased EtCO₂ significantly reduced the trending ability of SpHb during laparoscopic surgery. Caution should be executed when interpreting SpHb values during laparoscopic surgery in patients with hypercapnia. Full article

Cyanosis is a pathological condition that is characterized by a bluish discoloration of the skin or mucous membranes. It may result from a number of medical conditions, including disorders of the respiratory system and central nervous system, cardiovascular diseases, peripheral vascular diseases, deep vein thrombosis, and regional ischemia. Cyanosis can also be elicited from methemoglobin. Therefore, a simple, rapid, and simultaneous monitoring of changes in oxygenated hemoglobin and deoxygenated hemoglobin is useful for protective strategies against organ ischemic injury. We previously developed a red-green-blue camera-based spectral imaging method for the measurements of melanin concentration, oxygenated hemoglobin concentration (C_HbO), deoxygenated hemoglobin concentration (C_HbR), total hemoglobin concentration (C_HbT) and tissue oxygen saturation (StO₂) in skin tissues. We leveraged this approach in this study and extended it to the simultaneous quantifications of methemoglobin concentration (C_metHb), C_HbO, C_HbR, and StO₂. The aim of the study was to confirm the feasibility of the method to monitor C_metHb, C_HbO, C_HbR, C_HbT, and StO₂. We performed in vivo experiments using rat dorsal skin during methemoglobinemia induced by the administration of sodium nitrite (NaNO₂) and changing the fraction of inspired oxygen (FiO₂), including normoxia, hypoxia, and anoxia. Spectral diffuse reflectance images were estimated from an RGB image by the Wiener estimation method. Multiple regression analysis based on Monte Carlo simulations of light transport was used to estimate C_HbO, C_HbR, C_metHb, C_HbT, and StO₂. C_metHb rapidly increased with a half-maximum time of less than 30 min and reached maximal values nearly 60 min after the administration of NaNO₂, whereas StO₂ dramatically dropped after the administration of NaNO₂, indicating the temporary production of methemoglobin and severe hypoxemia during methemoglobinemia. Time courses of C_HbT and StO₂, while changing the FiO₂, coincided with well-known physiological responses to hyperoxia, normoxia, and hypoxia. The results indicated the potential of this method to evaluate changes in skin hemodynamics due to loss of tissue viability and vitality. Full article