Emerging artificial intelligence-aided diagnosis and management methods for ischemic strokes and vascular occlusions: A comprehensive review.

Large-vessel occlusion (LVO) stroke is a promising field for the use of AI, especially machine learning (ML) because optimal results are highly dependent on timely diagnosis, communication, and treatment. In order to better understand the current state of artificial intelligence (AI) in relation to LVO strokes, its efficacy, and potential future applications, we searched relevant literature to perform a comprehensive evaluation of the topic. The databases PubMed, Embase, and Scopus were extensively searched for this review. Studies were then screened using title and abstract criteria and duplicate studies were excluded. By using pre-established inclusion and exclusion criteria, it was decided whether or not to include full-text papers in the final analysis. The studies were analyzed, and the relevant information was retrieved. In recognizing LVO on computed tomography, ML approaches were very accurate. There is a shortage of AI applications for thrombectomy patient selection, despite the fact that certain research accurately evaluates individual patient eligibility for endovascular therapy. Machine learning algorithms may reasonably predict clinical and angiographic outcomes as well as associated factors. AI has shown promise in the diagnosis and treatment of people who have just suffered a stroke. However, the usefulness of AI in management and forecasting remains restricted, necessitating more studies into machine learning applications that can guide decision making in the future.

Long-term complications associated with prosthetic repair of incisional hernias.

OBJECTIVE: To determine whether the type of prosthetic material and technique of placement influenced long-term complications after repair of incisional hernias. DESIGN: Retrospective cohort analytic study. SETTING: University-affiliated hospital. PATIENTS: Two hundred patients undergoing open repair of abdominal incisional hernias with prosthetic material between 1985 and 1994. INTERVENTIONS: Four types of prosthetic material were used and placed either as an onlay, underlay, sandwich, or finger interdigitation technique. The materials were monofilamented polypropylene mesh (Marlex, Davol Inc, Cranston, RI), double-filamented mesh (Prolene, Ethicon Inc, Somerville, NJ), expanded polytetrafluroethylene patch (Gore-Tex, WL Gore & Associates, Phoenix, Ariz) or multifilamented polyester mesh (Mersilene, Ethicon Inc). MAIN OUTCOME MEASURES: The incidence of recurrence and complications such as enterocutaneous fistula, bowel obstruction, and infection with each type of material and technique of repair were compared with univariate and multivariate analysis. RESULTS: On univariate analysis, multifilamented polyester mesh had a significantly higher mean number of complications per patient (4.7 vs 1.4-2.3; P<.002), a higher incidence of fistula formation (16% vs 0%-2%; P<.001), a greater number of infections (16% vs 0%-6%; P<.05), and more recurrent hernias (34% vs 10%-14%; P<.05) than the other materials used. The additional mean length of stay to treat complications was also significantly longer (30 vs 3-7 days; P<.001) when polyester mesh was used. The deleterious effect of polyester mesh on long-term complications was confirmed on multiple logistic regression (P=.002). The technique of placement had no influence on outcome. CONCLUSION: Polyester mesh should no longer be used for incisional hernia repair.

The prognostic value of immunoperoxidase staining with monoclonal antibodies NCRC-11 and 3E1.2 in breast cancer.

The variation in survival of women with clinically similar breast cancers may lead to difficulty in clinical management so it is important to recognise factors which indicate the prognosis. Immunoperoxidase staining patterns of primary breast tumours using monoclonal antibody NCRC-11 have been shown to relate to overall survival (Ellis et al., 1985) but the results have not been reproducible in other centres. In this study paraffin sections of 483 primary breast cancers were stained with NCRC-11 and 3E1.2 using an immunoperoxidase system. The tumour staining patterns were compared with overall survival using life tables and tested for relative prognostic significance by Cox's multivariate analysis. NCRC-11 related to survival in all 483 cases (chi 2 5.8, P = 0.02) but both antibodies achieved maximum prognostic significance in lymph node negative patients (chi 2 9.4, P less than 0.002 and chi 2 10.7, P less than 0.001) in whom no other factor was more significant. Immunoperoxidase staining patterns produced by monoclonal antibodies NCRC-11 and 3E1.2 are important prognostic factors in breast cancer.

Predicting survival in bilateral breast carcinoma.

Survival in 38 patients with bilateral breast cancer has been studied. The tumours were synchronous in 14 patients and metachronous in 24. Survival was less than that predicted for either tumour on the basis of a previously developed index involving lymph node status, oestrogen receptor content, progesterone receptor content, and patient age. Simple addition of the indices for the two tumours gave better predictor although this also overstated the prospects for survival for both synchronous and metachronous tumours. This experience suggests, therefore, that the prospects for survival for patients with suggests, therefore, that the prospects of survival for patients with synchronous or metachronous bilateral breast carcinoma is poor, and worse than might reasonably be anticipated.

The prognostic importance of steroid receptors in endometrial carcinoma.

Three hundred forty-nine cases of primary endometrial carcinoma (endometrioid, adenosquamous, and clear-cell) were studied to investigate the relative prognostic importance of age, menopausal status, stage, histology, myometrial invasion, and estrogen and progesterone receptor content. Excluding menopausal status, all of these variables had a significant relationship to overall survival in a univariate analysis. Using a Cox multivariate regression analysis, stage, age, and an estrogen receptor value of more than 70 fmol/mg protein, combined with a progesterone receptor value of more than 30 fmol/mg protein, were independently associated with survival. The results demonstrate that for maximum prognostic information, both estrogen and progesterone content of tumors should be measured. Maximum prognostic information is obtained by using cutoff levels that are much higher than those traditionally accepted. This has particular relevance for patient stratification in clinical trials investigating receptor information and response to adjuvant or therapeutic treatment.

Estrogen receptors in bilateral breast cancer.

Estrogen receptor status, tumor histology, and the interval between the development of tumors were assessed in 99 patients with bilateral breast cancer. Tumors were first grouped into those simultaneously detected in both breasts or within 12 months of each other (synchronous bilateral breast cancer, of which there were 64) and second, those detected within more than 12 months of each other (asynchronous bilateral breast cancer, of which there were 35). Nineteen percent of all tumors were lobular carcinomas. Overall, the rate of receptor discordance between the two tumors was not significantly different from that previously reported between biopsies of primary tumor and metastases in patients with unilateral breast cancer. Synchronous receptor-positive tumors occurred significantly more frequently than expected, suggesting that the development of the two tumors was influenced by a common mechanism. In patients with asynchronous bilateral breast cancer there was a significantly longer interval between tumors if both were receptor-positive compared with concordant receptor-negative tumors and tumors with discordant receptor status. There was a significant discordance in the receptor status of asynchronous tumors when the histology also differed, indicating that the tumors in this group were likely to be separate primary tumors.

Validation of a prognostic index in breast cancer.

The validation of a prognostic index for patients with primary breast cancer is described. The actual survival data in a group of 383 patients was compared with expected survival predicted by an index based on axillary lymph node status, oestrogen receptor, progesterone receptor and age. There was no significant difference between actual and predicted deaths for five ranges of index value at 2 years and for the three highest ranges of index value at 5 years. However, in the two lowest ranges, the index significantly underpredicted deaths at 5 years. The Cox proportional hazards model was used to determine if there was any significantly better combination of coefficients and covariates to predict survival in the test group. The original index--1 = N + E + P + A, where N = 0 if no nodes are involved, 13 if one to three nodes are involved, and 31 if more than three nodes are involved; E = 15 if oestrogen receptor value is less than 10 fmol/mg cytosol protein and 0 otherwise; P = 12.5 if progesterone receptor value is less than 10 fmol/mg cytosol protein and 0 otherwise; and A = number of years over age 65--was as good as any competing model in ranking survival prospects in the test group. However, it was a less sensitive predictor in this group than in the original set of patients. A second index based on tumour size, hormone receptor status and age, for use when lymph node status was unavailable, was tested by the same method and validated.(ABSTRACT TRUNCATED AT 250 WORDS)

Evaluation of a new oestrogen receptor assay.

Replicate assays of oestrogen receptor (ER) concentration on 81 specimens of human breast carcinoma were performed to compare the ligand binding Sephadex separation method with a polystyrene bead linked anti-oestrogen receptor monoclonal antibody technique (enzyme immunoassay [EIA], Abbott Laboratories). Each specimen was homogenized and the cytosol divided into four fractions. Replicate assays by each method gave an estimate of reproducibility. The mean CV (coefficient of variation = standard deviation/mean) for the ligand binding method was 9.73% compared with a mean CV of 17.9% for the EIA method. In the clinically significant range of ER values, around the cut-off point between negative and positive assays, there was no difference in the precision of the two assays (Mann Whitney U-test). The correlation between methods gave a Pearson's Product Moment Correlation Coefficient (r value) of 0.822, significant at the P less than 0.001 level, indicating a close correlation between the two methods. The highest CVs for both methods were in the range of oestrogen receptor concentrations, below 10 fmol/mg cytosol protein. Using 10 fmol/mg cytosol protein as a cut-off between negative and positive assays, 9.87% of the specimens would be reclassified as either positive or negative by the new assay method. The new assay method is, therefore, acceptable for clinical use.

Psychiatric disturbance in Hodgkin's disease.

We describe the onset of psychotic depression in a young man receiving intensive therapy for Hodgkin's disease. We have found other examples of psychiatric disturbance in the course of reviewing the charts of 40 men with Hodgkin's disease and 20 with testicular cancer. We propose that patients with oncologic disease and their families receive counseling before initiation of treatment and be advised about the availability of psychiatric help should it become necessary.