Computer vision detects inflammatory arthritis in standardized smartphone photographs in an Indian patient cohort.

Introduction: Computer vision extracts meaning from pixelated images and holds promise in automating various clinical tasks. Convolutional neural networks (CNNs), a deep learning network used therein, have shown promise in analyzing X-ray images and joint photographs. We studied the performance of a CNN on standardized smartphone photographs in detecting inflammation in three hand joints and compared it to a rheumatologist's diagnosis. Methods: We enrolled 100 consecutive patients with inflammatory arthritis with an onset period of less than 2 years, excluding those with deformities. Each patient was examined by a rheumatologist, and the presence of synovitis in each joint was recorded. Hand photographs were taken in a standardized manner, anonymized, and cropped to include joints of interest. A ResNet-101 backbone modified for two class outputs (inflamed or not) was used for training. We also tested a hue-augmented dataset. We reported accuracy, sensitivity, and specificity for three joints: wrist, index finger proximal interphalangeal (IFPIP), and middle finger proximal interphalangeal (MFPIP), taking the rheumatologist's opinion as the gold standard. Results: The cohort consisted of 100 individuals, of which 22 of them were men, with a mean age of 49.7 (SD 12.9) years. The majority of the cohort (n = 68, 68%) had rheumatoid arthritis. The wrist (125/200, 62.5%), MFPIP (94/200, 47%), and IFPIP (83/200, 41.5%) were the three most commonly inflamed joints. The CNN achieved the highest accuracy, sensitivity, and specificity in detecting synovitis in the MFPIP (83, 77, and 88%, respectively), followed by the IFPIP (74, 74, and 75%, respectively) and the wrist (62, 90, and 21%, respectively). Discussion: We have demonstrated that computer vision was able to detect inflammation in three joints of the hand with reasonable accuracy on standardized photographs despite a small dataset. Feature engineering was not required, and the CNN worked despite a diversity in clinical diagnosis. Larger datasets are likely to improve accuracy and help explain the basis of classification. These data suggest a potential use of computer vision in screening and follow-up of inflammatory arthritis.

Diagnosis of essential hypertension in humans by the determination of plasma renal cortexin using enzyme-linked immunosorbent assay.

BACKGROUND: More than 90% of all hypertensive persons are reported to have essential hypertension (EH), a particular form of elevated blood pressure, for which no diagnostic test is currently available. The level of plasma renal (R) cortexin (PRC), a hypotensive protein produced in the kidney cortex cells, was reported to be reduced from 218 nM in the plasma of normotensive persons (NP) to 0 nM in the plasma of patients with EH. The feasibility of using the determination of PRC by enzyme-linked immunosorbent assay (ELISA) as a diagnostic test for EH was investigated. METHODS: The PRC was determined by ELISA using electrophoretically pure cortexin as the antigen. A total of 344 persons (male and female) with EH, with or without diabetes mellitus (DM), and receiving or not receiving any anti-hypertensive and/or anti-diabetic medication at presentation, as well as an equal number of age- and gender-matched NP participated in the study. RESULTS: All persons with EH, with or without co-existing DM, were found to have 0 nM PRC, regardless of whether they were receiving anti-hypertensive and anti-diabetic drugs, including those who had been taking these medications over an extended period of time (3 months). CONCLUSIONS: The determination of PRC as a marker protein by ELISA, a rapid method that can be carried out in any diagnostic laboratory, was shown to be suitable for the diagnosis of EH, even in those subjects who had co-existing DM and were receiving both anti-hypertensive and anti-diabetic medication.

Acetyl salicylic acid (aspirin) improves synthesis of maspin and lowers incidence of metastasis in breast cancer patients [corrected].

Maspin, a 42 kDa protein produced in normal breast cells, has been shown to inhibit the invasion and metastasis of breast cancer in an animal model. Ingestion of acetylsalicylic acid (aspirin) by breast cancer patients has been reported to restore the systemic synthesis of maspin through the stimulation of systemic nitric oxide production. Studies were carried out to determine the effect of aspirin on the incidence of breast cancer metastasis, which is reported to occur in 50% of patients who have previously received chemotherapy, radiation, and/or surgery. Thirty-five female patients (aged 41-65 years) with breast cancer who had previously received these therapies took one 75 mg/70 kg body weight enteric-coated aspirin tablet every 24 h, after an adequate meal, for 3 years. Their plasma nitric oxide and maspin levels were measured. The occurrence of metastasis was ascertained monthly by a qualified oncologist, and confirmed, if necessary, by biopsy. Daily ingestion of aspirin by participants resulted in an increase in maspin levels from 0.95 ± 0.04 to 4.63 ± 0.05 nM after 24 h. These levels were maintained for 3 years. These studies suggest that daily ingestion of aspirin might significantly reduce the incidence of breast cancer metastasis in patients who have previously received anticancer therapies.

Purification and mechanism of action of "cortexin," a novel antihypertensive protein hormone from kidney and its role in essential hypertension in men.

Because kidney tissue damage is associated with both hypertension and impaired nitric oxide (NO) production, we investigated the possibility whether the kidney tissue contains any activator of endothelial NO synthase (eNOS) that could be important in essential hypertension. An activator protein of M(r) 43000 Da for eNOS from the goat kidney cortex homogenate was purified to homogeneity by chromatographic techniques. This activator trivially, called "cortexin," was determined by enzyme-linked immunosorbent assay using anticortexin antibody. NO was determined by the formation of methemoglobin. Injection of 0.5 nmol cortexin/kg body weight to rabbit pretreated with l-epinephrine that increased the systolic and diastolic pressures to 195 +/- 3.40 mm Hg and 98.14 +/- 6.64 mm Hg, respectively, reduced and kept the elevated pressures at normal ranges of 133.57 +/- 12.14 (systolic) and 51.03 +/- 3.21 (diastolic) for 45 hours with simultaneous increase of plasma NO level. The inhibition of cortexin-induced NO synthesis nullified the antihypertensive effect of cortexin. The plasma cortexin level in newly diagnosed persons with essential hypertension was 0 pmol/mL (median), which contrasted with 218.94 pmol cortexin/mL (median), in normotensive persons (P < .0005; n = 25). We concluded that the impaired production of cortexin in the cortex of kidney might lead to essential hypertension.