Effectiveness of preconditioned adipose-derived mesenchymal stem cells with photobiomodulation for the treatment of diabetic foot ulcers: a systematic review

Lasers in Medical Science - The primary goal of this systematic review article was to provide an outline of the use of diabetic autologous adipose-derived mesenchymal stem cells (DAAD-MSCs) in the...     

Clinical and economic burden of wound care in the tropics: a 5‐year institutional population health review

The aim of this study is to evaluate the clinical and economic burden of wound care in the Tropics via a 5‐year institutional population health review. Within our data analysis, wounds are broadly classified into neuro‐ischaemic ulcers (NIUs), venous leg ulcers (VLUs), pressure injuries (PIs), and surgical site infections (SSIs). Between 2013 and 2017, there were a total of 56 583 wound‐related inpatient admissions for 41 461 patients, with a 95.1% increase in wound episodes per 1000 inpatient admissions over this period (142 and 277 wound episodes per 1000 inpatient admissions in 2013 and 2017, respectively). In 2017, the average length of stay for each wound episode was 17.7 days, which was 2.4 times that of an average acute admission at our institution. The average gross charge per wound episode was USD $12 967. Among the 12 218 patients with 16 674 wound episodes in 2017, 71.5% were more than 65 years of age with an average Charlson Comorbidity Index (CCI) of 7.2. Half (51.9%) were moderately or severely frail, while 41.3% had two or more wound‐related admission episodes. In 2017, within our healthcare cluster, the gross healthcare costs for all inpatient wound episodes stand at USD $216 million within hospital care and USD $596 000 within primary care. Most NIU patients (97.2%) had diabetes and they had the most comorbidities (average CCI 8.4) and were the frailest group of patients (44.9% severely frail). The majority of the VLU disease burden was at the specialist outpatient setting, with the average 1‐year VLU recurrence rate at 52.5% and median time between healing and recurrence at 9.5 months. PI patients were the oldest (86.5% more than 65 years‐old), constituted the largest cohort of patients with 3874 patients at an incidence of 64.6 per 1000 admissions in 2017, and have a 1‐year all‐cause mortality rate of 14.3%. For SSI patients, there was a 125% increase of 14.2 SSI wound episodes per 1000 inpatient admissions in 2013 to 32.0 in 2017, and a 413% increase in wound‐related 30‐day re‐admissions, from 40 in 2013 (4.1% of all surgeries) to 205 (8.3% of all surgeries) in 2017. The estimated gross healthcare cost per patient ranges from USD $15789–17 761 across the wound categories. Similar to global data, there is a significant and rising trend in the clinical and economic burden of wound care in Tropics.     

Extracting data from electronic medical records: validation of a natural language processing program to assess prostate biopsy results

Objective

The extraction of specific data from electronic medical records (EMR) remains tedious and is often performed manually. Natural language processing (NLP) programs have been developed to identify and extract information within clinical narrative text. We performed a study to assess the validity of an NLP program to accurately identify patients with prostate cancer and to retrieve pertinent pathologic information from their EMR.

Materials and methods

A retrospective review was performed of a prospectively collected database including patients from the Southern California Kaiser Permanente Medical Region that underwent prostate biopsies during a 2-week period. A NLP program was used to identify patients with prostate biopsies that were positive for prostatic adenocarcinoma from all pathology reports within this period. The application then processed 100 consecutive patients with prostate adenocarcinoma to extract 10 variables from their pathology reports. The extraction and retrieval of information by NLP was then compared to a blinded manual review.

Results

A consecutive series of 18,453 pathology reports were evaluated. NLP correctly detected 117 out of 118 patients (99.1 %) with prostatic adenocarcinoma after TRUS-guided prostate biopsy. NLP had a positive predictive value of 99.1 % with a 99.1 % sensitivity and a 99.9 % specificity to correctly identify patients with prostatic adenocarcinoma after biopsy. The overall ability of the NLP application to accurately extract variables from the pathology reports was 97.6 %.

Conclusions

Natural language processing is a reliable and accurate method to identify select patients and to extract relevant data from an existing EMR in order to establish a prospective clinical database.