Bayesian regression versus machine learning for rapid age estimation of archaeological features identified with lidar at Angkor.

Lidar (light-detection and ranging) has revolutionized archaeology. We are now able to produce high-resolution maps of archaeological surface features over vast areas, allowing us to see ancient land-use and anthropogenic landscape modification at previously un-imagined scales. In the tropics, this has enabled documentation of previously archaeologically unrecorded cities in various tropical regions, igniting scientific and popular interest in ancient tropical urbanism. An emerging challenge, however, is to add temporal depth to this torrent of new spatial data because traditional archaeological investigations are time consuming and inherently destructive. So far, we are aware of only one attempt to apply statistics and machine learning to remotely-sensed data in order to add time-depth to spatial data. Using temples at the well-known massive urban complex of Angkor in Cambodia as a case study, a predictive model was developed combining standard regression with novel machine learning methods to estimate temple foundation dates for undated Angkorian temples identified with remote sensing, including lidar. The model's predictions were used to produce an historical population curve for Angkor and study urban expansion at this important ancient tropical urban centre. The approach, however, has certain limitations. Importantly, its handling of uncertainties leaves room for improvement, and like many machine learning approaches it is opaque regarding which predictor variables are most relevant. Here we describe a new study in which we investigated an alternative Bayesian regression approach applied to the same case study. We compare the two models in terms of their inner workings, results, and interpretive utility. We also use an updated database of Angkorian temples as the training dataset, allowing us to produce the most current estimate for temple foundations and historic spatiotemporal urban growth patterns at Angkor. Our results demonstrate that, in principle, predictive statistical and machine learning methods could be used to rapidly add chronological information to large lidar datasets and a Bayesian paradigm makes it possible to incorporate important uncertainties-especially chronological-into modelled temporal estimates.

Diachronic modeling of the population within the medieval Greater Angkor Region settlement complex.

Angkor is one of the world's largest premodern settlement complexes (9th to 15th centuries CE), but to date, no comprehensive demographic study has been completed, and key aspects of its population and demographic history remain unknown. Here, we combine lidar, archaeological excavation data, radiocarbon dates, and machine learning algorithms to create maps that model the development of the city and its population growth through time. We conclude that the Greater Angkor Region was home to approximately 700,000 to 900,000 inhabitants at its apogee in the 13th century CE. This granular, diachronic, paleodemographic model of the Angkor complex can be applied to any ancient civilization.

Semi-supervised machine learning approaches for predicting the chronology of archaeological sites: A case study of temples from medieval Angkor, Cambodia.

Archaeologists often need to date and group artifact types to discern typologies, chronologies, and classifications. For over a century, statisticians have been using classification and clustering techniques to infer patterns in data that can be defined by algorithms. In the case of archaeology, linear regression algorithms are often used to chronologically date features and sites, and pattern recognition is used to develop typologies and classifications. However, archaeological data is often expensive to collect, and analyses are often limited by poor sample sizes and datasets. Here we show that recent advances in computation allow archaeologists to use machine learning based on much of the same statistical theory to address more complex problems using increased computing power and larger and incomplete datasets. This paper approaches the problem of predicting the chronology of archaeological sites through a case study of medieval temples in Angkor, Cambodia. For this study, we have a large dataset of temples with known architectural elements and artifacts; however, less than ten percent of the sample of temples have known dates, and much of the attribute data is incomplete. Our results suggest that the algorithms can predict dates for temples from 821-1150 CE with a 49-66-year average absolute error. We find that this method surpasses traditional supervised and unsupervised statistical approaches for under-specified portions of the dataset and is a promising new method for anthropological inquiry.

A case of paradoxical presentation of a postural postdural puncture headache after combined spinal-epidural anesthesia.

We report a case of paradoxical presentation of a postural postdural puncture headache secondary to dural puncture with a 25-gauge Whitacre needle for combined spinal-epidural anesthesia. This 27-year-old female patient presented to the emergency department with elevated blood pressure and a global headache 9 days after administration of epidural anesthesia for a spontaneous vaginal delivery after an uncomplicated pregnancy. The patient reported that the headache was more intense when lying down and immediately improved when she sat or stood up from a recumbent position. The patient was discharged from emergency department after an improvement following treatment with labetalol, ondansetron, ketorolac, and fluid resuscitation.

Anesthetic and Analgesic Management for Outpatient Knee Arthroplasty.

PURPOSE OF REVIEW: Total knee arthroplasty traditionally has been associated with significant postoperative pain that can limit recovery and prolong hospital length of stay. Recently, however, due to financial pressures and an emphasis on improving patient satisfaction, many institutions are implementing outpatient and short-stay programs for patients undergoing this procedure. An effective perioperative anesthetic plan is an essential quality of a successful outpatient joint replacement program. RECENT FINDINGS: Improved technology and innovation has led to more effective and efficient strategies that contribute to a smoother and quicker postoperative course. The use of peripheral nerve blocks in conjunction with a variety of systemic analgesics has reduced post-operative pain compared to older modalities. Specifically, the adductor canal and IPACK blocks have become increasingly popular due to their analgesic efficacy and muscle sparing characteristics. Outpatient knee arthroplasty is becoming a reality with advancements in surgical pathways that incorporate these newer modalities with an emphasis on multidisciplinary coordination.

Spinal anesthesia for orthopedic surgery: a detailed video assessment of quality.

BACKGROUND: Subarachnoid blocks are considered routine anesthetic procedures important in the daily practices of most anesthesiologists. However, few data exist regarding modern failure rates or quality-compromising behaviors. METHODS: Sixty adult patients having orthopedic surgery under spinal anesthesia were enrolled in this prospective and observational video study. Through a detailed high definition video review, we aimed to define our subarachnoid block failure rate and identify associated quality-compromising behaviors. RESULTS: An intrathecal injection either failed to generate a surgical block or was aborted secondary to difficulty in 7 patients (11.6%). A procedurally difficult subarachnoid block occurred in 17 patients (29%). Eight patients required greater than 10 mins of needling to complete the subarachnoid block. Body mass index represented an independent risk factor for long procedure times. There were 27 incidences of quality-compromising behaviors that included likely violation of aseptic technique, hemorrhage, poor positioning, damaged needles, thecal sac transfixation, high-lumbar needle placement, repetition of previously failed maneuvers, failure to provide skin anesthesia, and prolonged procedure times. Certified registered nurse anesthetist status predicted a greater-than-4-fold risk of subarachnoid block failure. DISCUSSION: The failure rate and quality-compromising behaviors identified in this study challenge the generalized assumption that performing a subarachnoid block in the orthopedic population is a simple procedure. The number and nature of the combined failed and difficult subarachnoid blocks suggest the need for quality improvement. Further research is needed to assess whether the use of image guidance may be a possible solution to navigate difficult anatomical pathology and confirm correct needle and drug placement.

Correlation of adverse neurological outcomes with increasing volumes and delayed administration of autologous epidural blood patches for postdural puncture headaches.

INTRODUCTION: Epidural blood patches (EBPs) usually afford rapid and successful treatment outcomes for postdural puncture headaches (PDPH) with few adverse sequelae. PATIENTS AND METHODS: In order to identify potential risk factors for any adverse outcomes of EBP, a Medline search, 1966 to the present, of case reports and series of any adverse outcomes following EBP for PDPH was conducted. The literature search identified 26 patient cases with 21 cases defined as adverse neurological outcomes, and further stratified as compression or noncompression syndromes, and five cases defined as persistent cranial nerve (CN) palsies. Cases were also stratified by age, sex, and blood volumes of EBP or delays in administration, and compared for statistically significant differences in continuous variables by unpaired, two-tailed t-tests and for significant correlations between predictor variables, including EBP volumes and delays in administration, and adverse neurological outcomes, by simple linear regression analysis. RESULTS: There were no statistically significant sex differences in the mean ages or weights of the study population, or in the total volumes of autologous blood injected in EBPs. When the study population was compared for adverse neurological outcomes by compression or noncompression syndromes, patients experiencing compression syndromes received significantly more EBP volumes (35.36 mL) than patients experiencing noncompression (17.46 mL) syndromes (P = 0.025). Regression analysis confirmed a significant direct linear relationship between increasing EBP volumes and worsening adverse neurological outcomes (P = 0.008). In patients with CN palsies associated with PDPH and unrelieved by EBP, regression analysis again confirmed significant direct linear relationships between increasing days waited to perform EBP and increasing duration of CN palsies in months (P = 0.001). CONCLUSIONS: Epidural blood patches for the management of PDPH, especially PDPH associated with CN palsies, should be administered as soon as the diagnosis of PDPH is made with lower volumes of autologous blood (< or =20 mL) to assure the best treatment outcomes.