PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Soft Computing”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5Linked to original sources
PubMed2026

Improving insurance deduction identification: a hybrid artificial intelligence model using machine learning and expert systems.

PURPOSE: Financial challenges in healthcare systems worldwide, especially in low- and middle-income countries like Iran, have increased hospitals' reliance on insurance reimbursements. Unrecognized insurance deductions often cause severe financial shortages, making efficient deduction management crucial. This study aimed to design a hybrid intelligent system for identifying and predicting insurance deductions by combining machine learning and expert system frameworks. DESIGN/METHODOLOGY/APPROACH: A mixed-methods design was applied in four stages. First, a scoping review identified the causes and patterns of insurance deductions. Second, interviews with 15 insurance experts produced a validated checklist and a dataset from inpatient billing records. Third, using the CRISP-DM methodology, machine learning algorithms were developed and tested in SPSS Modeler alongside a fuzzy expert system developed in MATLAB. Finally, the model was validated using the holdout method. FINDINGS: Four categories of deduction drivers were identified: service provision, registration errors, document submission issues, and revenue conversion processes. The CHAID decision tree outperformed other algorithms with a 99% precision rate and the lowest Mean Absolute Error (9.43). A brief assessment of potential overfitting was conducted to ensure that the CHAID model's high accuracy was interpreted cautiously and supported by the validation results. The fuzzy expert system with validated rules was adaptable for deduction classification, especially for cases unsuitable for quantitative modeling. ORIGINALITY/VALUE: The hybrid model improves detection and prevention of deductions, offering actionable insights for hospital administrators, insurers, and policymakers. Its implementation can enhance hospital information systems, streamline claims processing, and optimize revenue management amid financial constraints.

Machine Learning↗
PubMed2026

Machine learning vs. traditional methods for predicting postoperative cardiac complications after non-cardiac surgery: a systematic review and Bayesian network meta-analysis.

INTRODUCTION: Accurate prediction of peri-operative cardiac complications is critical to optimise pre-operative decision-making. Traditional risk prediction scores, such as the Revised Cardiac Risk Index, show only modest discrimination. Machine learning can model complex, non-linear relationships but their predictive performance compared with traditional scores remains unclear. METHODS: We performed a systematic review and Bayesian network meta-analysis. The primary outcome was postoperative adverse cardiac events following non-cardiac surgery. Prediction models were assessed relative to the Revised Cardiac Risk Index. As many studies evaluated multiple versions of each model type, the highest performing ('best version') and lowest performing ('worst version') results were analysed. Models were ranked using the surface under the cumulative ranking curve (SUCRA). RESULTS: Thirteen studies evaluating 54 models and 927,113 patients were included. Machine learning approaches generally outperformed traditional risk scores. Automated machine learning ranked highest (SUCRA 96.6) showed the greatest improvement in the best version analysis (mean difference (MD) 0.28 (95%CrI 0.16-0.40)) and remained superior in the sensitivity analysis (MD 0.30 (95%CrI 0.14-0.45)). Gradient boosting models showed superior performance over the Revised Cardiac Risk Index across analysis (best version: MD 0.20 (95%CrI 0.14-0.26), worst version: MD 0.18 (95%CrI 0.12-0.25), SUCRA 82.4). The Gupta Perioperative Risk for Myocardial Infarction or Cardiac Arrest score outperformed the Revised Cardiac Risk Index in the best version analysis (MD 0.16 (95%CrI 0.01-0.32)). Between-study heterogeneity was low. None of the included studies externally validated their machine learning models and only six were judged to be at low risk of bias. DISCUSSION: Most machine learning models showed better discrimination than traditional risk scores, with automated machine learning and gradient boosting models ranking highest. However, study quality, calibration reporting and absence of external validation limit immediate clinical adoption. Prospective, multicentre evaluation is required before integration of these models into peri-operative practice.

Humans↗
PubMed1988

Evaluating glass, polystyrene, and polypropylene containers for semen collection and sperm washing.

The effects of glass, polystyrene, and polypropylene containers on semen parameters as measured by Cell Soft computer-assisted semen analysis and hypoosmotic swelling (HOS) tests were assessed in unwashed specimens and again after sperm washing and swim-up procedures. A superiority in unwashed specimens was observed in glass versus polystyrene concerning velocity, motility percentage, and HOS testing (p less than 0.01). Also, superiority of glass versus polystyrene was demonstrated for linearity and ALH (p less than 0.05). Glass was only superior to polypropylene in categories of motility and HOS testing (p less than 0.05 and p less than 0.01, respectively). There was no category in which plastic was statistically superior to glass in the unwashed specimens. Concerning washed and swim-up specimens, there were no semen parameters in which there was any superiority demonstrated of either glass or plastic. Unless some future proof that the differences in semen parameters demonstrated in this study have no clinical significance, these data suggest that the collection of semen samples for sperm analysis or therapeutic use should be performed in glass containers.

Glass↗
PubMed1990

Detection of soft-tissue foreign bodies by plain radiography, xerography, computed tomography, and ultrasonography.

Detection of a soft-tissue foreign body is common yet often difficult, particularly when the foreign material is not radiopaque. Various imaging modalities have been advocated for detecting foreign bodies that are not revealed by plain radiography. The abilities of plain radiography, xerography, computed tomography, and ultrasonography to detect glass, wooden, and plastic foreign bodies in an in vitro preparation are compared. While all of these imaging techniques demonstrated a glass foreign body, only ultrasonography clearly identified wooden and plastic foreign bodies.

Evaluation Studies as Topic↗
PubMedDate not supplied

[Computed tomography in the diagnosis of soft tissue neoplasms of the trunk and extremities].

Analysis of CT data on 213 patients with soft tissue and trunk tumors has shown that a majority of malignant and benign tumors have a similar picture (except lipoma). Features of the contours of a tumor and its inner structure do not permit the assessment of its nature. The only significant differential-diagnostic sign of malignant soft tissue tumors is destruction of an adjacent bone, noted in 17.6%. The majority of malignant and benign soft tissue tumors (70.9%) on CT scans look like a single node; recurrent tumors look multinodular (78.2%). Verification of soft tissue tumors, revealed by CT, should be done using morphological methods.

Adult↗
PubMed1985

CT of soft-tissue neoplasms.

The computed tomographic scans (CT) of 84 patients with untreated soft-tissue neoplasms were studied, 75 with primary and nine with secondary lesions. Each scan was evaluated using several criteria: homogeneity and density, presence and type of calcification, presence of bony destruction, involvement of multiple muscle groups, definition of adjacent fat, border definition, and vessel or nerve involvement. CT demonstrated the lesion in all 84 patients and showed excellent anatomic detail in 64 of the 75 patients with primary neoplasms. CT did not differentiate vessel or nerve entrapment from neurovascular structures that were simply applied to the pseudocapsule of the tumor. Blurring of adjacent fat was an infrequent finding, but when it was present, the tumor was malignant. The CT findings were characteristic enough to suggest the histology of the neoplasm in only 13 lesions (nine lipomas, three hemangiomas, one neurofibroma). No malignant neoplasm had CT characteristics specific enough to differentiate it from any other malignant tumor. However, malignant neoplasms could be differentiated from benign neoplasms in 88% of the cases.

Adipose Tissue↗
PubMed1990

The value of computed tomography in the diagnosis of soft-tissue swellings of the hand.

Twenty patients with palpable swellings of the hand were investigated by computed tomography. The results, when compared with the pathological findings, lead us to consider this a technique of considerable value in the assessment of this kind of disease. The importance of angiography and, occasionally of magnetic resonance imaging, are also stressed.

Adolescent↗
PubMed1992

[A comparison between echography and computed tomography in assessing neoplastic recurrences in superficial soft tissues].

Thirty-seven superficial soft-tissue recurrences were evaluated with ultrasonography (US) and computed tomography (CT) to assess the correct diagnostic approach. US and CT examinations were performed at the same time. High-frequency US probes and a third-generation CT scanner were employed; all the lesions underwent also histology or cytology. US correctly identified as recurrences or fibrous tissue all the 37 lesions, whereas CT diagnosed 30 lesions only. Seven of the 14 recurrences < 2 cm diameter were not demonstrated. In conclusion, US provides more reliable information than CT relative to small lesions, which suggests that US must be performed just after therapy. Nevertheless, when bone involvement is suspected, CT is required and its use is also suggested to monitor distant metastases.

Biopsy, Needle↗
PubMed1979

Computed tomography evaluation of fatty tumors of the somatic soft tissues: clinical utility and radiologic-pathologic correlation.

The role of computed tomography (CT) in the evaluation of fatty tumors of the somatic soft tissues was investigated. Six surgically proven cases of fatty tumors were studied preoperatively by CT and standard radiographic means--conventional radiographs, xeroradiography, and angiography. Our case material included a simple lipoma, two infiltrative lipomas, an angiolipoma, and two liposarcomas. The radiologic-pathologic correlation was evaluated with respect to the various imaging modalities. The unique tissue characteristics of fatty tumors makes them particularly adaptable to CT scanning. In addition to its ability to define accurately tissue densities, the facility of CT in depicting depth, size, and extent of the lesion in the axial plane was found to be most useful in the preoperative evaluation of our case material.

Adipose Tissue↗
PubMed1986

Growth of human renal carcinoma in soft agar colony formation assays measured by computer-assisted volume analysis.

Technical methods for assessing the growth and chemotherapy sensitivity of human tumor cells growing in soft-agar culture have been less than ideal. Within the past year, there have been reports of studying the extent of growth of human tumor cells in these cultures by quantitating the change in cumulative volume for the growth units observed. The present report describes the results of computer-assisted volume analysis applied to soft-agar cultures of cells from 74 primary renal cell carcinomas, 14 primary transitional cell carcinomas of the renal pelvis, and four different human renal cell carcinoma xenografts. The extent of growth in vitro observed for cells from freshly excised human renal tumors showed the expected and statistically significant relationship to tumor grade and stage. The renal cell carcinoma xenografts proliferated to a much greater extent in vitro than the cells from freshly excised human renal carcinomas. The fundamental growth limit of 10(9) micron. cumulative growth unit volume per plate was confirmed by this series of experiments. Computer-assisted volume analysis appears to be a useful method to study the growth of freshly excised human renal carcinoma cells in vitro.

Agar↗
PubMed1994

Computer-assisted quantitative description of chromatin pattern in soft tissue tumors of the adult.

The chromatin pattern in Feulgen-stained nuclei from soft tissue tumors was quantitatively described by means of computer-assisted microscope analysis. The morphonuclear parameters described densitometric, run length, and co-occurrence matrix features. The present series of cases, which relied upon archival (ie, formalin-fixed, paraffin-embedded), tissues, included 19 benign (9 lipomas and 10 leiomyomas) cases, and 49 malignant (31 primitive non-recurrent, 14 primitive locally recurrent, and 4 metastatic) cases. The 31 primitive nonrecurrent cases included 12 liposarcomas, 11 leiomyosarcomas, 4 rhabdomyosarcomas, and 4 malignant fibrohistiocytomas. The results show that the quantitative description of chromatin patterns in Feulgen-stained nuclei made it possible to distinguish between certain benign and malignant soft tissue tumors. However, this was true only when specific histopathologic groups were taken into consideration. Indeed, the lipomas were markedly different from the liposarcomas, whereas the leiomyomas closely resembled the leiomyosarcomas. The quantitative description of the chromatin patterns also made it possible to identify certain clinically aggressive soft tissue tumors. In this context, the authors observed that the chromatin pattern in the cell nuclei from the group of patients whose tumors had recurred less than 10 months after first surgery was significantly more heterogeneous and less condensed than in the cell nuclei from patients whose tumors had recurred more than 10 months after this surgery. In the same manner, the morphonuclear parameters under study made it possible to establish a more marked distinction between the primitive and recurrent soft tissue tumors that developed a metastasis between 3 and 48 months after the diagnosis, and those tumors free of metastasis until 38 months after the diagnosis. The former group exhibited cell nuclei with a chromatin pattern markedly more condensed and heterogeneous than in the case of the cell nuclei belonging to the latter group.

Adult↗
PubMed1983

Soft-tissue hemorrhage in hemophiliac patients. Computed tomography and ultrasound study.

Fifty-four hemophiliac patients underwent a total of 94 studies using computed tomography (CT), ultrasound, or both. Not only common bleeding sites such as the iliopsoas muscles but also several unusual sites were encountered: these included the iliac bone, bowel wall, mesentery, rectus abdominis muscle, retroperitoneum, bladder wall, and scrotum. Both modalities gave comparable results, and each was helpful in (a) establishing the diagnosis, (b) evaluating the extent of bleeding and its effect on adjacent organs, and (c) demonstrating regression after treatment.

Abdomen↗
PubMed1984

The comparative value of bone scintigraphy and computed tomography in determining bone involvement by soft-tissue sarcomas.

In seventeen patients with a soft-tissue sarcoma, bone scintigrams were found to be more useful than computed tomograms for evaluating bone involvement. The scintigrams had higher predictive value and higher sensitivity, as there were no false-negative or false-positive scintigrams, while there were three false-positive computed tomograms. Accurate scintigraphy requires the use of high-resolution static gamma-camera images that show the tangential relationship between tumor and bone. The images that are usually made in surveying the skeleton for metastatic disease--routine whole-body bone scans, or even gamma-camera images that provide only anterior and posterior views--are inadequate. They did not demonstrate the true relationship of the tumor to bone in the patients in this study when activity within the tumor itself was superimposed over bone. In such patients, properly selected oblique views sometimes showed that the tumor was clearly separate from normal bone activity. Determination of the relationship of the soft-tissue tumor to bone is an important part of the accurate anatomical staging that is required to select appropriate surgical management.

Adolescent↗
PubMed1983

Computed tomography of the middle ear in the evaluation of cholesteatomas and other soft-tissue masses: comparison with pluridirectional tomography.

Computed tomographic (CT) scans and tomograms of 60 patients with various soft-tissue masses of the middle ear, including 30 with cholesteatomas, were studied. CT produced excellent images of middle ear soft-tissue masses and appears to be the diagnostic method of choice for cholesteatomas, glomus tympanicum tumors, and other soft-tissue masses. In one patient CT demonstrated pneumolabyrinth resulting from postsurgical fracture of the footplate of the stapes. Pneumolabyrinth is a newly reported CT finding in stapes footplate fracture.

Adolescent↗